Carnall Farrar’s request for NHS England data permitting detailed insights into population needs and challenges facing the system when shaping sustainable health and social care services

Carnall Farrar Ltd (CF) is a management consultancy and data science company whose mission is to improve healthcare. CF works with several purchasers, providers, and systems across NHS organisations in England, including NHS Trusts, Foundation Trusts, Integrated Care Boards (ICBs), and Commissioning Support Units (CSUs). CF has strong relationships with the Department of Health and Social Care (DHSC), NHS England (NHSE), and the Office for Health Improvements and Disparities (within DHSC). These organisations commission CF to work on projects procured both through direct commissioning agreements, and competitive procurement processes as part of access to over six public sector specific frameworks.

CFs client base consists primarily of NHS organisations. During 2023/24, CF has worked with over 30 health and social care systems in England and their suppliers to support health system strategy, service transformation, financial sustainability, and integrated care delivery including:

• Providers of healthcare services

• Integrated Care Boards (ICBs)

• Commissioning Support Units (CSUs)

• Hospital Trusts

• Private secondary care providers

• Mental Health trusts

• Community Provider Trusts

• NHS Suppliers

• Pharmacies

• NHS England

• Office for Health Improvement and Disparities (formerly Public Health England)

Some examples of these clients include

• Association of the British Pharmaceutical Industry

• Barnet Council

• Barts Health

• NHS Bath and North East Somerset, Swindon and Wiltshire ICB

• Cambridge University Health Partners

• Cambridge University Hospitals NHS FT

• Central and NW London NHS FT

• NHS Humber and North Yorkshire ICB

• NHS Devon

• Lewisham and Greenwich NHS Trust

• Liverpool University Hospitals NHS Foundation Trust

• Manchester Foundation Trust

• NHS Greater Manchester

• MSD

• NHS England

• NHS Confederation

• NHS Sussex

• NHS South East Region

• NHS Transformation (SDEs)

• NHS North Central London ICB

• NHS North East London ICB

• NHS Oldham

• Novartis

• South London Mental Health Partnership

• NHS South West London ICS

• Surrey and Borders Partnership NHS FT

• NHS Surrey Downs Health and Care

• NHS Surrey Heartlands ICB

• Surrey Heath PCN

• University Hospitals Bristol and Weston NHS FT

• North Bristol NHS Trust

• Wales Cancer Network

CF has handled large volumes of data which has been obtained directly from NHS clients. CF has been successful in using this data to provide meaningful analytics which have positively impacted NHS organisations. However, the data available directly from each NHS organisation is aggregate data and does not include diagnostic (clinical) codes, or the ability to benchmark organisations or systems. The results, although useful, are limited.

CF obtains data from NHS England to expand the products currently on offer for NHS Clients. The record level data disseminated, although pseudonymised, is richer and more accurate than the data held by individual NHS organisations. Using the data under this Agreement, CF aims to provide more in-depth tools and products for NHS clients, therefore producing more accurate insight into the areas of the NHS requiring improvement and how these improvements can be made.

CF also uses the data from NHS England to provide services to commercial organisations in the life sciences industry, healthcare charities and AHSNs. These entities leverage CF’s outputs and insights to collaborate with NHS organisations, fostering initiatives that promote patient health and improve their wellbeing. The data supports the development of innovative solutions, service improvement, outcome tracking and real world evidence generation required by the NHS, NICE and NHS England. The overarching goal is to enhance patient care and facilitate improved access to innovative services. Additionally, clients use these outputs to provide information the NHS needs related to business cases, healthcare utilisation, health inequalities, burden of disease, clinical pathway analysis, health economic analysis, real world evidence generation and outcomes analysis. The outputs, shared directly or indirectly with the NHS, contribute to enhancing patient care. All outputs are aggregated with small numbers suppressed, in line with the HES analysis guide and the mental health suppression rules.

The data from NHS England is processed in line with the purpose of processing as outlined above, as a legitimate interest under General Data Protection Regulation Article 6 (1) (f) and Article 9(2)(j), for the purposes of delivering improved patient outcomes and broader benefits to the health and social care arena. CF, as the sole Data Controller, determines the methods and purpose of processing, ensuring that the data are processed under strict conditions and proportionate to the purpose.

Data sent from NHS England to CF follows the national opt out policy already therefore CF do not need to apply opt outs.

The NHS England data outputs are shared directly with the NHS and AHSNs or will be shared indirectly to the NHS via pharmaceutical and other life sciences companies and AHSNs using bespoke materials, reports, dashboards, tools, research papers and through a tool called the CF Insights and Collaboration Engine (ICE) produced by CF. They are generated and shared exclusively for the advancement of patient health and care, and are not wholly commercial.

CF requires NHS England data in order provide additional benefits to NHS clients by expanding the capabilities of existing products and reducing costs to the NHS. Previously only three products have been produced using the data under this Agreement:

- CF Foresight

- CF Capacity

- CF Benchmarks

- CF Insights and Collaboration Engine (ICE)

These products meet CFs ongoing objectives to improve patient flow (i.e., a patient’s entire journey from entering care to discharge), ensuring that patients receive high quality care at the right time and in the right place. They will also support determining the right size clinical services to meet future demand and provide insights into opportunities through benchmarking.

Further details about each of these tools are provided below:

1) CF Foresight:

Purpose:

This tool predicts demand and patient flow through a hospital over the short to medium term (1-4 months). Hospitals can look at upcoming demand compared to their current capacity, identifying potential pressure points. The tool can also test the impact of different potential interventions on demand and flow, informing data driven strategic decisions.

Case Study:

A basic version of the tool was initially tested by Northampton General Hospital NHS Trust. CF is working with NHS England’s Data and Analytical Product team to co-design the next version of the tool to provide a national overview of demand and flow. CF’s own tool was paused during the COVID-19 pandemic but is now in greater demand as systems attempt to catch up on their backlog of elective procedures. This was further developed with Kettering General Hospital NHS Foundation Trust and Northampton General Hospital NHS Trust in October and November 2021 to combine non-elective and elective pathways, specifically addressing their waitlist with increased activity, their activity with increased capacity, and their capacity capabilities with an increase in workforce availability. In 2022, CF have been leveraging this product to deliver system control centres in NHS Surrey ICB, NHS Humber and North Yorkshire ICB, and NHS North Central London ICB.

Data required:

A five-year extract of the following data sets:

- Hospital Episode Statistics (HES) Admitted Patient Care (APC)

- HES Outpatients (OP)

- HES Critical Care (CC)

- HES Accident and Emergency (A&E)

- Emergency Care Data Set (ECDS)

- Diagnostic Imaging Dataset (DIDs)

Why that data is required:

The tool incorporates machine learning model to predict future performance. The more years of data that are available for training, the better the accuracy of the model. Eight years of data is considered sufficient to account for annual variation. The HES APC, CC, A&E, and ECDS data are required to train patient level models for predicting attendance, admission, four-hour breaches, and discharges within the hospital. The row level data is also required to model the specific interventions that trusts plan on using to improve performance. These interventions often require clinical coding to identify the impacted patients e.g., increasing discharge rates in frail elderly population within orthopaedics. CF requires the latest available datasets to ensure that NHS commissioners and providers, who will receive CF analytics products, can make effective decisions based on the most up-to-date information.

The DIDs data is required to predict pathways that relevant patients might take in various disease areas including cancer diagnosis and progression. It provides invaluable, detailed information to build on participants’ disease phenotypes (e.g., tumour size and spread in cancer). This data also adds to the understanding of patients’ histories on individual and cohort level and their relationship with genomic alterations, all of which are beneficial for the tool in predicting downstream pathways and outcomes that might impact on demand and patient flow through hospitals.

CF acknowledges that DIDs includes data from 217 NHS providers and covers data on diagnostic imaging tests on a large proportion of NHS patients in England. The DIDs reports on imaging activity, referral source, and timeliness, and approximately 44.0 million imaging tests were reported in England in the year to March 2022. DIDs captures information about referral source and patient type, details of the test (type of test and body site), demographic information such as GP registered practice, patient postcode, ethnicity, gender, and date of birth, plus items about waiting times for each diagnostic imaging event, from time of test request through to time of reporting. CF have therefore minimised the data requested as far as possible; CF have not requested all of the available fields from within the DIDs dataset, but only those fields necessary to carry out the analysis detailed in this Agreement are requested. Data is restricted to 8 historic years only.

2) CF Capacity:

Purpose:

This tool predicts in which year demand in an acute NHS organisation will exceed capacity based on demographic and non-demographic growth. It allows a system to model a variety of clinical configurations across sites, to maximise the operational effectiveness whilst minimising the negative impacts on patient safety, access, and hospital performance.

It is hoped that this tool, with the right bed-based capacity data, when combined with local data, will allow NHS and social care organisations to determine the necessary bed requirements. Given anticipated demand and associated operational assumptions, the capacity requirements by different type of beds based on requirements can be specified using this tool.

Case Study:

In 2019, CF used this tool in Guernsey to ensure that the new hospital will be correctly sized, for the Barking, Havering, and Redbridge University NHS Trust to reconfigure services to optimise current capacity across two sites and at Whipp’s Cross Hospital where CF assisted in the design of the hospital to ensure it met future capacity requirements.

Additionally, CF combined the features within the CF Foresight and Capacity tools at the start of the pandemic in 2020 to support system-wide modelling of demand and capacity in the five STPs of London, 32 LAs, and 9 community providers. CF used historical data from HES APC, A&E, and OP alongside COVID-19 sitreps, to develop browser-based software that enabled over 50 NHS users to:

• Allow NHS organisations to extend their current capacity through re-configuration and productivity improvements (CF Capacity)

• Allow NHS organisation to create the optimal configuration of capacity given the constraints of workforce and clinical effectiveness (CF Capacity)

• Predict future activity (CF Foresight)

• Quantify the impact of plans on future occupancy (CF Foresight)

• Develop plans to change activity over a selected period of time (CF Foresight)

• Track activity against baseline to assess real-time efficacy of the new plan (CF Foresight)

• Identify where and when demand will exceed capacity (new system level features)

• Provide forecasts on the likely demand for different discharge pathways to community and social care providers (new system level features)

Since the completion of this work in May 2020, the team have observed continued engagement with the tool. There were approximately 800 total interactions up until September 2020 at which point CF could no longer track users as this work was transferred into the NHSE foundry tooling. Using this tool, several key insights were uncovered:

An evolution of this model has been used for NHS Nottinghamshire CCG (2020), Hampshire Hospitals NHS Foundation Trust (2021), North West London ICB (2022), and North Central London ICB (2022). In these projects, HES and ECDS data was used to create deprivation heat maps to visualise the characteristics of the population and note if there were any pockets of areas with high deprivation/ high elderly population/ high proportion of black, Asian and minority ethnicity (BAME). This was linked to the corresponding patient flow to identify mismatched access to care and capacity constraints.

Data required:

An eight-year extract of the following data sets:

- HES APC

- ECDS

- Diagnostic Imaging Dataset (DIDs)

Why that data is required:

This tool predicts up to 5 years into the future and relies on historical activity data to predict the trend and changes in activity over and above that expected from demographic changes. Eight years of historic data is the minimum amount of data CF requires to capture longer term trends. Activity is categorised by point of delivery (outpatient, inpatient, emergency department), age, and healthcare resource group (HRG) code (where possible). This activity data is then mapped to capacity within the hospital. In order to capture the value from the capacity available, CF models scenarios that improve efficiency or reconfigure services. The outputs from the reconfiguration analysis will feed into a separate model, which predicts the effect of different service configurations on finance, workforce, estates, capital, and finance. This requires row level data including clinical codes. Access to mental health datasets should allow CF to analyse the acute patient pathways for mental health service users, and enable a better understanding of the clinical needs now and in the future.

3) CF Benchmarks:

Purpose:

To provide a set of automated reports that allow for a rapid diagnostic of ICBs)/places/local authorities. An automated set of reports that benchmarks ICBs across hospital demand, projected demand, life expectancy, deprivation, hospital performance, Quality and Outcomes Framework (QOF), expenditure, workforce, and populations segmentation. This product allows for a rapid diagnostic of a geographic area, freeing up time to focus on improvement rather than number analysis.

The report topics that are included are:

- Population Segmentation

- Drivers of the deficit

- Inpatient activity

- A&E performance

- Outpatient activity

Case Study:

CF has combined the HES data, the Secondary Use Services (SUS) data and the ECDS data into a single aggregated data pipeline with an internally facing browser interface for CF consultants to use on NHSE projects. This allowed both commissioners and providers to assess performance across the system and see trends in their key activity and quality metrics against their compare performance to peers as well as understand the scale of opportunity to improve performance. CF have used this tool to yield benefits in the following areas:

Hampshire and Isle of Wight ICB:

CF supported the elective recovery of Hampshire and Isle of Wight ICB in 2021. CF developed a demand and capacity model to support future planning and recovery. Additionally, CF created four speciality business cases and a medium-term plan, which were signed off and approved by the Planned Care Board, starting the process to establish specialty elective hubs and pathway changes across the system.

The work produced a series of deliverables that support the elective recovery of the ICB:

• Comprehensive demand and capacity model that allowed an understanding of the gaps in theatres and beds across the system and the future waiting list challenge for each trust

• Four specialty business cases, approved by the Planned Care Board, that set out clear next steps for the specialties and an approach to hub working that could tackle the longest waiters

• Holistic medium-term (1-3 years) plan that set out a clear ambition and necessary enablers that would allow the delivery of elective care across the ICB.

CF also supported the successful bid for the ICB to receive £10m in funding as an elective accelerator system and the submission of an elective recovery planning submission to NHS England.

Data required:

- HES APC

- ECDS

- HES A&E (for historical data)

- HES OP

- Community Services Dataset (CSDS)

- DIDs

Why that data is required:

CF will use these datasets to enable system financial leadership and regulators to understand the strategic financial challenge of a local area and benchmark against national peers. Mental health data is required to enable clients to monitor performance against internal targets and benchmark against national peers whilst the bridge file is required to support planning for mental health patients based on the benchmarked opportunities. The HES and Mental health data are required for benchmarking inpatient activity, outpatient activity, A&E performance, and populations segmentation. Eight years of data is required as time-series analysis to assess trends in performance, expenditure, utilisation, demand, seasonal patterns in utilisation, and directional trends in performance.

The data is required at the patient level as CF’s benchmarking uses national data at the patient level to create explanatory models for each report. These explanatory models are required to compare the performance at the regional, local, site and specialty based on time of day and patient movements within the healthcare system e.g.. quantifying the differential impact across sites that the number of people in an emergency department has on the probability of a patient breaching the 4 hour target.

There is a desire to link patient level data with CSDS and DIDs, leaving it pseudonymised, to make it more actionable and to understand variations in slightly defined groups, which clearly consist of suppressed small numbers. For high-risk and high-cost patients, the ability to link data allows for a more pathway-centric view.

As a secondary uses data set, CSDS re-uses clinical and operational data for purposes other than direct patient care. CSDS sets out national definitions for the extraction of data about children and adults. These activities could take place in settings such as health centres, Sure Start centres, day care facilities, schools or community centres, mobile facilities, or a patient's own home. As such the scope of this dataset is far-reaching and includes a large proportion of the population of England, for example in September 2022 alone, there were 1,398,795 referrals received relating to 1,030,395 persons needing care. CF have therefore minimised the data requested from the CSDS dataset to the least amount required; data is minimised to 8 historic years only and the number of fields requested have been minimised so that only those necessary to perform the analysis detailed in this Agreement have been requested.

4) CF Insights & Collaboration Engine (ICE):

Purpose:

The ICE is a web-based analytics tool that provides users with a holistic view of the relative current position of an Integrated Care System (ICS)’s population health outcomes compared to other ICSs, across physical and mental health, community and hospital-based care, and health and social care to build a transformation plan. Additionally, ICE allows users to set and track targets for transformation goals and evaluate whether the transformation programmes have been effective. It integrates aggregated HES, QOF and publicly available data, such as population demographics. This enables users to analyse healthcare data, extract various insights and generate reports to support enhancements in patient care. The data within ICE is also analysed for the purposes of evaluating whether large initiatives are effective or whether redirection is necessary. This analysis informs commissioners, clinicians and clinical networks on adoption of innovation, adherence to national policy guidelines including NICE, patient pathways and benchmarking. All the data undergoes aggregation and small numbers are suppressed, including secondary suppression as outlined in the HES analysis guide.

ICE incorporates the linkage of community data sets with acute data and mental health data. This tool uses aggregated HES data to provide a useful understanding of the place and interplay of providers needed to be able to chart patient journeys across community, mental health, and acute services with primary care to follow.

ICE analyses data at the ICS, Local Authority and Lower Super Output Layer levels. Given the fluidity of geographic boundaries across ICSs, places and neighbourhoods from an NHS and local authority perspective, there is a need to customise the geographic definition of a unit, which at various levels would not be consistent. To be able to cut the data at various desired levels consistently, very granular data is needed, down to the record level by LSOA, so that it can be cut and re-aggregated into the view that would be most meaningful for CF's clients. The resulting display has aggregated data with a small number of suppressions. The analysis involves drilling down and reconstructing as well as building up from the lowest level. Indicators of public health such as indices of multiple deprivation (IMD) are used to normalise relevant comparisons.

Case Study:

CF released a free version of this tool in February 2022 to all 42 ICBs, which has been used by North Central London ICB, Staffordshire and Stoke on Trent, and Bristol, North Somerset, and Gloucestershire ICB, while the full paid version has been deployed to Sussex Health and Care ICB (https://ics.cfdata.io/) where it is was used to address inequalities in population outcomes and evaluate initiatives to improve population health. The paid version is also being used by Surrey Heartlands ICB to aid development, monitoring and evaluation of their transformation plan.

Data required:

- HES APC

- ECDS

- HES OP

Why that data is required:

CF use HES APC, OP and ECDS data to create integration metrics within physical and mental health, community and hospital-based care, health and social care chasms and ICS, locality breakdowns. CF are also considering implementing neighbourhood breakdown to provide better visibility in more granular level to ICSs.

The list of data required has been expanded slightly due to client requests to drill down into data with more granularity. Based on feedback, there is a desire to expand upon the metrics for further exploration and to allow for deeper analysis and the display of additional measures without patient-level linkage.

Lawful basis

The lawful bases for processing this data under UK GDPR is as follows:

• Article 6(1)(f) – it is necessary for the legitimate interests in being able to provide tools and services that will benefit healthcare organisations

• Article 9(2)(j) – it is necessary for reasons that are in the public interest in the area of public health. CF provides tools and services to public healthcare organisations that help them to monitor and improve the standards and quality of care that they offer. The processing is designed to benefit patients and society as a whole through facilitating better healthcare in the UK. Processing is necessary for archiving purposes in the public interest, scientific or historical research purposes or statistical purposes in accordance with Article 89(1) based on Union or Member State law which shall be proportionate to the aim pursued, respect the right to data protection and provide for suitable and specific measures to safeguard the fundamental rights and the interests of the data subject.

To determine the lawfulness of processing the data for these legitimate interests, CF has undertaken a Legitimate Interests Assessment (LIA) and determined that:

i. The processing is necessary for the purpose:

The processing of patient data is required to provide accurate analysis of patient pathways, outcomes and performance. Aggregate data does not allow the patient level predictions and evaluations required to perform the detailed analysis and modelling required for:

(1) CF Foresight: Predicting patient admission and discharge data, modelling patient level intervention

(2) CF Capacity: Mapping individual patients to activity groups, identifying opportunities within care pathways

(3) CF Benchmarking: Creating patient segmentation groups, modelling A&E performance, identifying financial opportunities for clinical pathways

(4) CF Insights & Collaboration Engine (ICE): Supporting Integrated Care Systems (ICSs) and Boards (ICBs), identifying focus areas to improve population health outcomes, providing ICBs a tool for ongoing self-assessment

ii. The processing is proportionate to the purpose:

The processing of this data will relate solely to the improvement of the health and social care system in England and Wales through providing detailed recommendations and initiatives that aggregate data cannot provide due to the unconnected nature of the data-sets.

The negative impact on individual patients is minimal and CF predicts that patients will benefit from the enhanced service provided by the tools and analysis this data processing produces. This data processing will not identify individuals and the output of this processing will not lead to data-sets that can be used to identify individuals.

iii. The purpose cannot be achieved by processing the data in another more obvious or less intrusive way:

The correlations between behaviours at the level of the individual patient are lost when using aggregate data. These correlations are crucial for capturing the true impact of initiatives and identifying the underlying causes for health system under-performance. Summary statistics mask these relationships and can lead to biased analysis especially when modelling system performance across multiple points of delivery.

iv. The interests of the individual data subjects do not override the legitimate interest:

CF has considered that the data is health data, including data about children or other vulnerable people, which the data subjects are likely to consider particularly private and that some individuals would feel uncomfortable about the processing of their health data outside of the NHS. However, the data sets are pseudonymised and therefore, the possible impacts of the processing will be minimal as CF is not able to de-pseudonymise the data nor will CF attempt to identify patients using any means. CF has put in place policy safeguards to ensure the security and privacy of patient records and limit the impact on patients to positive enhancements of care.

CF believes that the above provides sufficient legitimate interests for lawful processing of the data requested under this Agreement.

CF is the sole Controller for the purposes of this Agreement and CF will be directly processing the data. Amazon Web Services (AWS) is a Processor for CF. Data processing and storage will take place within CF's secure cloud platform which is based on an AWS UK environment. The servers that store and process the data under this Agreement will be within UK sovereignty (London). The data under this Agreement will be solely used for the purposes stated above and only substantive employees of CF will have access to this data. No employee of AWS will access this data.

Benefits to the Health and Social Care System:

CF will support access of the data to NHS clients, enabling more effective use of the data, validation of data through feedback and, crucially, supporting more effective integration of data. The analytical products that CF builds will help NHS clients to make better decisions. A crucial component of the analytical work with NHS clients is to ensure a legacy of embedded analytical capability. CF aims to improve the flow of data across the NHS, closing the gap between action and feedback. This will help reduce data latency and improve data quality, two key components to effective use of data to create a health system that learns from every patient.

The data held under this Agreement will only be used to provide services to NHS and other organisations within England and Wales. CF is a commercial organisation. However, the data are not used for commercial purposes such as sales targeting or commercial insurance.

CF is committed to improving healthcare in the UK and is commissioned by a number of different purchasers and providers of healthcare from NHS organisations and NHS suppliers to solve pre-defined structural, organisational, or operational issues. Part of the service CF offers is the ability to perform detailed analysis using healthcare data to provide insights into the drivers of key problems to enable evidence-based decision making for NHS leadership.

CF will use the data supplied by NHS England to enhance the analytical services CF provide to NHS and other clients, by developing several additional analytical outputs as described in the purpose statements.

Commercial arrangements are put in place between CF and the client organisation. Only CF primary users will have access to NHS England data. Tools created for NHS customers and suppliers will only contain aggregated data (with small numbers suppressed).

An amendment to this DSA in 2025 extends the initial 5-year data deletion rolling basis to 8-years. This change is necessary to retain healthcare data dating back to 2019/20, which will serve as a critical benchmark for assessing the long-term impact of the COVID-19 pandemic on healthcare services.

The healthcare data from 2019/20 represents the pre-pandemic baseline, and its retention is essential for conducting comparative analyses. Extending the retention period will enable us to evaluate pandemic-related changes in healthcare delivery, patient outcomes, and service utilisation patterns over time. Without this historical data, it would be challenging to gain a comprehensive understanding of the pandemic’s effects on healthcare systems and services.

CF works on multiple projects at any one time for several different national, regional, and local organisations across the NHS. Therefore, it is not possible to provide full details of all outputs, as these are highly specific to the requirements for each client. CF will only share aggregated analysis with its NHS clients in presentations, reports, or cloud-based visualisation tools, in full compliance with the small numbers guidance. In general, all outputs can be grouped into one of several categories detailed below:

• CF provides detailed reports to clients, which contain data in table format containing aggregated, non-patient identifiable data with small numbers suppressed in line with the HES Analysis Guide. These reports may also contain visualisations created using data based on aggregated, non-patient identifiable results of quantitative analysis.

• CF presents the aggregated, non-patient identifiable results with small numbers suppressed, in the form of tables and visualisations, at meetings with NHS client stakeholders.

• CF provides interactive visualisations to NHS clients in the form of cloud-based tools; the software tools that CF builds will allow some analysis to be done on aggregated data (with small numbers suppressed), in house by the providers/commissioners. CF will not allow the providers and commissioners to directly access the patient level data.

• Benchmarking applies across all services. National benchmarks will be derived from the national data. The outputs from queries against these data will be transferred to visualisation software for communication to CF clients.

All outputs will only contain results in highly aggregated format and as statistical summaries and measures of association. Small numbers will be suppressed. Record level information will not be released to any third party. Examples of the specific tool outputs are set out below:

1) CF Foresight

Output: A browser-based tool that enables providers and commissioners to view predictions of waitlists, future attendances, admissions, discharges, and occupancy as well as model the impact of interventions to improve performance and patient flow.

Timelines: A tailored version of this tool has been developed to support system control centres that were required by ICBs by December 2022, and is currently in use by Surrey Heartlands ICB. This tool is also currently being used to support Manchester University NHS Foundation Trust with forecasting and planning the productivity increase required to recover of elective services such that there are no 65+ week waiters and MFT reaches 103% of 19/20 activity levels by March 2024.

2) CF Capacity

Output: A Python (visualisation software) and Excel based tool which visualises and models the impact of reconfiguration and efficiency improvements.

Timelines: The basic Excel version has been used since 2020 and during 2022 CF have developed an additional automated python-based mapping tool that automates the approach. This has been trialled at two clients during 2022 and is currently live at one. In April – May 2023, CF used a version of CF Capacity to create a capacity and demand model for Mental Health services in SEL. The model resulted in a recommendation that the system increase its bedded capacity and the model was handed over to BI teams in SLaM and Oxleas to continue to use and update.

3) CF Benchmark

Output: A browser based interactive explorer of the population segments, health system performance and financial performance, and an automated PowerPoint presentation.

Timelines: This tool is used internally by CF staff members to provide insights and benchmarking to all of CF's NHS clients. This tool was most recently used, May 2023, to support NCL ICS with creating a baseline understanding of the geographical distribution of maternal and neonatal activity.

4) CF Insight and Collaboration Engine (ICE)

Output: A web-based analytics tool that provides users with a holistic view of the relative current position of an Integrated Care System (ICS)’s population health outcomes compared to other ICSs and the ability to set and track targets for transformation goals and evaluate whether the transformation programmes have been effective.

Timelines: The full version of this tool is used by NHS Sussex ICB and NHS Surrey Heartlands ICB.

A limited free version has been used by North Central London ICB, NHS Staffordshire and Stoke on-Trent ICB, and Bristol, North Somerset and Gloucestershire ICB, helping them to understand their current position, supporting focus areas to improve integration and evaluating the impact of initiatives to improve population health outcomes and reduce inequalities.

All outputs will only contain results in highly aggregated format and as statistical summaries and measures of association. Small numbers will be suppressed in line with the HES Analysis Guide. Record level information will not be released to any third party.

Between the period June 2022 and June 2023, CF has played a vital role in supporting numerous NHS organisations, leveraging Data provided by NHS England to uncover deep insight beyond that of which the NHS organisation are able to achieve themselves due to analytical capability and capacity constraints. Hospital Episode Statistic data has directly contributed to driving financial and performance improvements among CF's clients. CF has leveraged the Data to support the following organisations:

• NHS Devon ICB

• NHS Hampshire and Isle of White ICB

• Homerton Healthcare NHS Foundation Trust

• NHS Kent and Medway ICB

• Manchester University NHS Foundation Trust

• NHS Confed

• NHS England

• NHS North Central London ICB

• Nottingham University Hospitals NHS Trust

• Oldham Council

• NHS South-East London ICB

• NHS Sussex ICB

• University College London Hospitals NHS Trust

• Whittington Health NHS Trust

All four types of CF tools have been used in this period. Below are examples that have yielded benefits for the organisations and the populations that they serve.

CF Foresight Case Study: Manchester University NHS Foundation Trust

Due to the COVID-19 pandemic, the Trust has a significant backlog of patients waiting for treatment, with over 10,000 waiting over 65 weeks and average waits at 23 weeks. CF was commissioned in May 2023 to develop an elective recovery plan to return to 103% of 2019/20 activity levels and eliminate >65 week waits by March 2024.

The core of the approach to developing the elective recovery plan was to conduct a baseline assessment of activity, capacity, waiting workforce across the trust, at as granular a level of possible (site and specialty). HES data (APC and OP) was foundational to conducting this baseline assessment. This data allowed the development of insights that guided the elective recovery and site optimisation plan for both the under-utilized elective hub and the whole site. Examples of key insights developed using data received through DARS were:

• Specialties at MFT are widely distributed, with the average specialty operating across 5 of MFT's 10 sites.

• Activity has reduced across the Trust since 2019/20 but varies significantly by site and point of delivery with Manchester Royal Infirmary inpatient activity down by 16% and elective day case down by 28%.

• Non-elective length of stay increases at the Manchester Royal Infirmary can be explained in totality by changes in complexity unlike other sites.

• Orthopaedics, Paediatric surgery and Ophthalmology have the largest admitted waiting lists, each with over 2,500 people.

• Orthopaedics, ophthalmology, general surgery, ENT and Dental will each have 2,500 admitted clocks to stop by March 2024 to avoid any 65 week-wait breaches.

Insights developed have been used to generate a site optimisation plan for the Trafford Elective Hub. This includes consolidation of HVLC services currently delivered across MFT, to the elective hub which will result in a significant proportion of the longest waiting people (+65 weeks) being seen by March 2024.

CF Capacity Case Study: Southeast London ICS Mental Health Demand

CF were commissioned to leverage a data-driven approach to gain deeper insights. The program focused on analysing historical and current demand for mental health urgent and emergency care in the system. CF combined data analysis and active engagement with stakeholders. The HES APC and ECDS data sets were used to support key analyses and modelling:

• Current state assessment analysis (e.g., demand in acute mental health services, including inpatients, and emergency care)

• Historical demand to understand the demographics, locations and conditions for presenting and where possible, how this has changed with time.

• Length of time spent in A&E for mental health-related attendances compared to all attendances.

• Creating a capacity and demand model for inpatient admissions for older acute care and PICU (psychiatric intensive care) beds across both trusts.

CF conducted a detailed handover to best enable BI teams in SLaM and Oxleas to continue to use and update the model. The model resulted in a recommendation that the system increase its bedded capacity, owing to continually high occupancy levels with demand greater than capacity, and a high spend on out-of-area placement and private beds.

The program provided actionable recommendations through data analysis to improve access to non-emergency crisis services. Stakeholder alignment was achieved through 68 interviews with key stakeholders from various organizations. Critical data insights led to data-related improvements within the system. The demand and capacity model helped forecast future demand for mental health services, resulting in positive impacts on crisis care delivery and informed decision-making.

CF Benchmark Case Study: North Central London ICS ‘Start Well’ Programme

The Start Well Programme in North Central London (NCL) focuses on improving maternity, neonatal, children, and young people's services in an acute hospital setting, catering to a diverse population of around 1.5 million people across five boroughs. The program was initiated in response to calls for action following the publication of the NHS Long Term Plan and the Ockenden Report, as well as the need to learn from changes made during the pandemic. The aim was to urgently address health inequalities within the sector.

Data from HES APC was used in parallel with data from the model hospital and Secondary Usage Services (SUS) inpatient to analyse maternal and neonatal activity across NCL, creating a geographical breakdown of maternal, neonatal and children’s and young peoples’ services. Data analyses were supplemented with 60 clinician interviews to validate outputs and distil strengths and challenges. In addition, all trusts in London were analysed to generate a benchmark comparison between number of deliveries in NCL trusts as compared to peers.

The result of this phase of the Start Well Programme was a comprehensive case for change document that clearly outlined the opportunities for improvement in the NCL system compared to best practice, while acknowledging the strengths of the system. This output provides a basis for further phases of the programme to address the areas where improvements could be made.

The leadership development programme successfully aligned senior leaders from across the system on the importance of the change process and allowed clinical and operational leaders from different organisations to get to know one another. The senior leaders committed to engaging with the change process as the programme moves forward and vowed to bring their staff along with them.

CF Insights and Collaboration Engine (ICE) Case Study: Sussex Integrated Care System

CF were commissioned by NHS Sussex from June-August 2022 to co-develop a tailored version of CF's ICE to cover population health outcomes and health inequalities. The tool developed uses data from as tables of Hospital Episode Statistics (APC, ECDS, OP, CC, AE), as well as other sources, to derive metrics used for performance evaluation, goal setting and tracking.

Sussex ICS have a suite of performance reporting tools and dashboards and a strong performance reporting function, with each service area producing a weekly report that details performance for operational teams to respond to and adjust plans on a timely basis, but the new formation of the ICS meant they required a strategic oversight capability that functioned in tandem with existing teams to identify opportunity areas for improvement, set strategic goals at ICS, Place and local level with the aim to improving outcomes and tackle health inequalities by implementing targeted initiatives, and tracking the impact of the initiatives on outcomes over time.

CF worked closely alongside the Chief Medical Officer and Planning Performance & Intelligence (PPI) team throughout – taking a user-centric approach to development. Over 40 stakeholders were engaged through several interviews, 13 focus groups and over 6 user experience testing sessions.

• CF co-developed the suite of over 100 metrics that the NHS Sussex Executive Team needs to make decisions. The breadth of metrics included understanding the population context and wider determinants of health, through to health behaviours and lifestyle, availability and uptake of services and health outcomes. The tool allows a view of metrics by Core20 and across lower tier Local Authorities wherever possible.

• CF co-designed the user journey and tool interface and iterated it through user experience testing. We established data pipelines for new metrics to ensure metrics automatically updated at the necessary frequency and geographic granularity.

• CF developed as relevant peer groups weighted by multiple factors such as deprivation, rurality etc and a ‘no change’ synthetic counterfactual to estimate impact of initiatives.

• CF updated the reporting process and methodology so that executives have the right information at the right time. Including mapping the different possible users and governance for where information from the tool would be presented and designing user-friendly reporting templates.

Based on the ICE data presented and the local insights, Sussex identified four pressing priorities as CVD, Cancer, Falls & Respiratory Illnesses.

The strategic capability provided the information needed at an executive level for data- led decision making, using a dynamic user interface which will allow users to quickly understand the data and spend more time considering the solutions. This helped support Sussex ICS in their objectives; including improving outcomes in population health and healthcare, tackling inequalities, enhancing productivity and value for money and helping the NHS to support broader social and economic development.

Carnall Farrar Ltd (CF) is a management consultancy and data science company whose mission is to improve healthcare. CF works with several purchasers, providers, and systems across NHS organisations in England, including NHS Trusts, Foundation Trusts, Integrated Care Boards (ICBs), and Commissioning Support Units (CSUs). CF has strong relationships with the Department of Health and Social Care (DHSC), NHS England (NHSE), and the Office for Health Improvements and Disparities (within DHSC). These organisations commission CF to work on projects procured both through direct commissioning agreements, and competitive procurement processes as part of access to over six public sector specific frameworks.

CFs client base consists primarily of NHS organisations. During 2023/24, CF has worked with over 30 health and social care systems in England and their suppliers to support health system strategy, service transformation, financial sustainability, and integrated care delivery including:

• Providers of healthcare services

• Integrated Care Boards (ICBs)

• Commissioning Support Units (CSUs)

• Hospital Trusts

• Private secondary care providers

• Mental Health trusts

• Community Provider Trusts

• NHS Suppliers

• Pharmacies

• NHS England

• Office for Health Improvement and Disparities (formerly Public Health England)

Some examples of these clients include

• Association of the British Pharmaceutical Industry

• Barnet Council

• Barts Health

• NHS Bath and North East Somerset, Swindon and Wiltshire ICB

• Cambridge University Health Partners

• Cambridge University Hospitals NHS FT

• Central and NW London NHS FT

• NHS Humber and North Yorkshire ICB

• NHS Devon

• Lewisham and Greenwich NHS Trust

• Liverpool University Hospitals NHS Foundation Trust

• Manchester Foundation Trust

• NHS Greater Manchester

• MSD

• NHS England

• NHS Confederation

• NHS Sussex

• NHS South East Region

• NHS Transformation (SDEs)

• NHS North Central London ICB

• NHS North East London ICB

• NHS Oldham

• Novartis

• South London Mental Health Partnership

• NHS South West London ICS

• Surrey and Borders Partnership NHS FT

• NHS Surrey Downs Health and Care

• NHS Surrey Heartlands ICB

• Surrey Heath PCN

• University Hospitals Bristol and Weston NHS FT

• North Bristol NHS Trust

• Wales Cancer Network

CF has handled large volumes of data which has been obtained directly from NHS clients. CF has been successful in using this data to provide meaningful analytics which have positively impacted NHS organisations. However, the data available directly from each NHS organisation is aggregate data and does not include diagnostic (clinical) codes, or the ability to benchmark organisations or systems. The results, although useful, are limited.

CF obtains data from NHS England to expand the products currently on offer for NHS Clients. The record level data disseminated, although pseudonymised, is richer and more accurate than the data held by individual NHS organisations. Using the data under this Agreement, CF aims to provide more in-depth tools and products for NHS clients, therefore producing more accurate insight into the areas of the NHS requiring improvement and how these improvements can be made.

CF also uses the data from NHS England to provide services to commercial organisations in the life sciences industry, healthcare charities and AHSNs. These entities leverage CF’s outputs and insights to collaborate with NHS organisations, fostering initiatives that promote patient health and improve their wellbeing. The data supports the development of innovative solutions, service improvement, outcome tracking and real world evidence generation required by the NHS, NICE and NHS England. The overarching goal is to enhance patient care and facilitate improved access to innovative services. Additionally, clients use these outputs to provide information the NHS needs related to business cases, healthcare utilisation, health inequalities, burden of disease, clinical pathway analysis, health economic analysis, real world evidence generation and outcomes analysis. The outputs, shared directly or indirectly with the NHS, contribute to enhancing patient care. All outputs are aggregated with small numbers suppressed, in line with the HES analysis guide and the mental health suppression rules.

The data from NHS England is processed in line with the purpose of processing as outlined above, as a legitimate interest under General Data Protection Regulation Article 6 (1) (f) and Article 9(2)(j), for the purposes of delivering improved patient outcomes and broader benefits to the health and social care arena. CF, as the sole Data Controller, determines the methods and purpose of processing, ensuring that the data are processed under strict conditions and proportionate to the purpose.

Data sent from NHS England to CF follows the national opt out policy already therefore CF do not need to apply opt outs.

The NHS England data outputs are shared directly with the NHS and AHSNs or will be shared indirectly to the NHS via pharmaceutical and other life sciences companies and AHSNs using bespoke materials, reports, dashboards, tools, research papers and through a tool called the CF Insights and Collaboration Engine (ICE) produced by CF. They are generated and shared exclusively for the advancement of patient health and care, and are not wholly commercial.

CF requires NHS England data in order provide additional benefits to NHS clients by expanding the capabilities of existing products and reducing costs to the NHS. Previously only three products have been produced using the data under this Agreement:

- CF Foresight

- CF Capacity

- CF Benchmarks

- CF Insights and Collaboration Engine (ICE)

These products meet CFs ongoing objectives to improve patient flow (i.e., a patient’s entire journey from entering care to discharge), ensuring that patients receive high quality care at the right time and in the right place. They will also support determining the right size clinical services to meet future demand and provide insights into opportunities through benchmarking.

Further details about each of these tools are provided below:

1) CF Foresight:

Purpose:

This tool predicts demand and patient flow through a hospital over the short to medium term (1-4 months). Hospitals can look at upcoming demand compared to their current capacity, identifying potential pressure points. The tool can also test the impact of different potential interventions on demand and flow, informing data driven strategic decisions.

Case Study:

A basic version of the tool was initially tested by Northampton General Hospital NHS Trust. CF is working with NHS England’s Data and Analytical Product team to co-design the next version of the tool to provide a national overview of demand and flow. CF’s own tool was paused during the COVID-19 pandemic but is now in greater demand as systems attempt to catch up on their backlog of elective procedures. This was further developed with Kettering General Hospital NHS Foundation Trust and Northampton General Hospital NHS Trust in October and November 2021 to combine non-elective and elective pathways, specifically addressing their waitlist with increased activity, their activity with increased capacity, and their capacity capabilities with an increase in workforce availability. In 2022, CF have been leveraging this product to deliver system control centres in NHS Surrey ICB, NHS Humber and North Yorkshire ICB, and NHS North Central London ICB.

Data required:

A five-year extract of the following data sets:

- Hospital Episode Statistics (HES) Admitted Patient Care (APC)

- HES Outpatients (OP)

- HES Critical Care (CC)

- HES Accident and Emergency (A&E)

- Emergency Care Data Set (ECDS)

- Diagnostic Imaging Dataset (DIDs)

Why that data is required:

The tool incorporates machine learning model to predict future performance. The more years of data that are available for training, the better the accuracy of the model. Five years of data is considered sufficient to account for annual variation. The HES APC, CC, A&E, and ECDS data are required to train patient level models for predicting attendance, admission, four-hour breaches, and discharges within the hospital. The row level data is also required to model the specific interventions that trusts plan on using to improve performance. These interventions often require clinical coding to identify the impacted patients e.g., increasing discharge rates in frail elderly population within orthopaedics. CF requires the latest available datasets to ensure that NHS commissioners and providers, who will receive CF analytics products, can make effective decisions based on the most up-to-date information.

The DIDs data is required to predict pathways that relevant patients might take in various disease areas including cancer diagnosis and progression. It provides invaluable, detailed information to build on participants’ disease phenotypes (e.g., tumour size and spread in cancer). This data also adds to the understanding of patients’ histories on individual and cohort level and their relationship with genomic alterations, all of which are beneficial for the tool in predicting downstream pathways and outcomes that might impact on demand and patient flow through hospitals.

CF acknowledges that DIDs includes data from 217 NHS providers and covers data on diagnostic imaging tests on a large proportion of NHS patients in England. The DIDs reports on imaging activity, referral source, and timeliness, and approximately 44.0 million imaging tests were reported in England in the year to March 2022. DIDs captures information about referral source and patient type, details of the test (type of test and body site), demographic information such as GP registered practice, patient postcode, ethnicity, gender, and date of birth, plus items about waiting times for each diagnostic imaging event, from time of test request through to time of reporting. CF have therefore minimised the data requested as far as possible; CF have not requested all of the available fields from within the DIDs dataset, but only those fields necessary to carry out the analysis detailed in this Agreement are requested. Data is restricted to 5 historic years only.

2) CF Capacity:

Purpose:

This tool predicts in which year demand in an acute NHS organisation will exceed capacity based on demographic and non-demographic growth. It allows a system to model a variety of clinical configurations across sites, to maximise the operational effectiveness whilst minimising the negative impacts on patient safety, access, and hospital performance.

It is hoped that this tool, with the right bed-based capacity data, when combined with local data, will allow NHS and social care organisations to determine the necessary bed requirements. Given anticipated demand and associated operational assumptions, the capacity requirements by different type of beds based on requirements can be specified using this tool.

Case Study:

In 2019, CF used this tool in Guernsey to ensure that the new hospital will be correctly sized, for the Barking, Havering, and Redbridge University NHS Trust to reconfigure services to optimise current capacity across two sites and at Whipp’s Cross Hospital where CF assisted in the design of the hospital to ensure it met future capacity requirements.

Additionally, CF combined the features within the CF Foresight and Capacity tools at the start of the pandemic in 2020 to support system-wide modelling of demand and capacity in the five STPs of London, 32 LAs, and 9 community providers. CF used historical data from HES APC, A&E, and OP alongside COVID-19 sitreps, to develop browser-based software that enabled over 50 NHS users to:

• Allow NHS organisations to extend their current capacity through re-configuration and productivity improvements (CF Capacity)

• Allow NHS organisation to create the optimal configuration of capacity given the constraints of workforce and clinical effectiveness (CF Capacity)

• Predict future activity (CF Foresight)

• Quantify the impact of plans on future occupancy (CF Foresight)

• Develop plans to change activity over a selected period of time (CF Foresight)

• Track activity against baseline to assess real-time efficacy of the new plan (CF Foresight)

• Identify where and when demand will exceed capacity (new system level features)

• Provide forecasts on the likely demand for different discharge pathways to community and social care providers (new system level features)

Since the completion of this work in May 2020, the team have observed continued engagement with the tool. There were approximately 800 total interactions up until September 2020 at which point CF could no longer track users as this work was transferred into the NHSE foundry tooling. Using this tool, several key insights were uncovered:

An evolution of this model has been used for NHS Nottinghamshire CCG (2020), Hampshire Hospitals NHS Foundation Trust (2021), North West London ICB (2022), and North Central London ICB (2022). In these projects, HES and ECDS data was used to create deprivation heat maps to visualise the characteristics of the population and note if there were any pockets of areas with high deprivation/ high elderly population/ high proportion of black, Asian and minority ethnicity (BAME). This was linked to the corresponding patient flow to identify mismatched access to care and capacity constraints.

Data required:

A five-year extract of the following data sets:

- HES APC

- ECDS

- Diagnostic Imaging Dataset (DIDs)

Why that data is required:

This tool predicts up to 5 years into the future and relies on historical activity data to predict the trend and changes in activity over and above that expected from demographic changes. Five years of historic data is the minimum amount of data CF requires to capture longer term trends. Activity is categorised by point of delivery (outpatient, inpatient, emergency department), age, and healthcare resource group (HRG) code (where possible). This activity data is then mapped to capacity within the hospital. In order to capture the value from the capacity available, CF models scenarios that improve efficiency or reconfigure services. The outputs from the reconfiguration analysis will feed into a separate model, which predicts the effect of different service configurations on finance, workforce, estates, capital, and finance. This requires row level data including clinical codes. Access to mental health datasets should allow CF to analyse the acute patient pathways for mental health service users, and enable a better understanding of the clinical needs now and in the future.

3) CF Benchmarks:

Purpose:

To provide a set of automated reports that allow for a rapid diagnostic of ICBs)/places/local authorities. An automated set of reports that benchmarks ICBs across hospital demand, projected demand, life expectancy, deprivation, hospital performance, Quality and Outcomes Framework (QOF), expenditure, workforce, and populations segmentation. This product allows for a rapid diagnostic of a geographic area, freeing up time to focus on improvement rather than number analysis.

The report topics that are included are:

- Population Segmentation

- Drivers of the deficit

- Inpatient activity

- A&E performance

- Outpatient activity

Case Study:

CF has combined the HES data, the Secondary Use Services (SUS) data and the ECDS data into a single aggregated data pipeline with an internally facing browser interface for CF consultants to use on NHSE projects. This allowed both commissioners and providers to assess performance across the system and see trends in their key activity and quality metrics against their compare performance to peers as well as understand the scale of opportunity to improve performance. CF have used this tool to yield benefits in the following areas:

Hampshire and Isle of Wight ICB:

CF supported the elective recovery of Hampshire and Isle of Wight ICB in 2021. CF developed a demand and capacity model to support future planning and recovery. Additionally, CF created four speciality business cases and a medium-term plan, which were signed off and approved by the Planned Care Board, starting the process to establish specialty elective hubs and pathway changes across the system.

The work produced a series of deliverables that support the elective recovery of the ICB:

• Comprehensive demand and capacity model that allowed an understanding of the gaps in theatres and beds across the system and the future waiting list challenge for each trust

• Four specialty business cases, approved by the Planned Care Board, that set out clear next steps for the specialties and an approach to hub working that could tackle the longest waiters

• Holistic medium-term (1-3 years) plan that set out a clear ambition and necessary enablers that would allow the delivery of elective care across the ICB.

CF also supported the successful bid for the ICB to receive £10m in funding as an elective accelerator system and the submission of an elective recovery planning submission to NHS England.

Data required:

- HES APC

- ECDS

- HES A&E (for historical data)

- HES OP

- Community Services Dataset (CSDS)

- DIDs

Why that data is required:

CF will use these datasets to enable system financial leadership and regulators to understand the strategic financial challenge of a local area and benchmark against national peers. Mental health data is required to enable clients to monitor performance against internal targets and benchmark against national peers whilst the bridge file is required to support planning for mental health patients based on the benchmarked opportunities. The HES and Mental health data are required for benchmarking inpatient activity, outpatient activity, A&E performance, and populations segmentation. Five years of data is required as time-series analysis to assess trends in performance, expenditure, utilisation, demand, seasonal patterns in utilisation, and directional trends in performance.

The data is required at the patient level as CF’s benchmarking uses national data at the patient level to create explanatory models for each report. These explanatory models are required to compare the performance at the regional, local, site and specialty based on time of day and patient movements within the healthcare system e.g.. quantifying the differential impact across sites that the number of people in an emergency department has on the probability of a patient breaching the 4 hour target.

There is a desire to link patient level data with CSDS and DIDs, leaving it pseudonymised, to make it more actionable and to understand variations in slightly defined groups, which clearly consist of suppressed small numbers. For high-risk and high-cost patients, the ability to link data allows for a more pathway-centric view.

As a secondary uses data set, CSDS re-uses clinical and operational data for purposes other than direct patient care. CSDS sets out national definitions for the extraction of data about children and adults. These activities could take place in settings such as health centres, Sure Start centres, day care facilities, schools or community centres, mobile facilities, or a patient's own home. As such the scope of this dataset is far-reaching and includes a large proportion of the population of England, for example in September 2022 alone, there were 1,398,795 referrals received relating to 1,030,395 persons needing care. CF have therefore minimised the data requested from the CSDS dataset to the least amount required; data is minimised to 5 historic years only and the number of fields requested have been minimised so that only those necessary to perform the analysis detailed in this Agreement have been requested.

4) CF Insights & Collaboration Engine (ICE):

Purpose:

The ICE is a web-based analytics tool that provides users with a holistic view of the relative current position of an Integrated Care System (ICS)’s population health outcomes compared to other ICSs, across physical and mental health, community and hospital-based care, and health and social care to build a transformation plan. Additionally, ICE allows users to set and track targets for transformation goals and evaluate whether the transformation programmes have been effective. It integrates aggregated HES, QOF and publicly available data, such as population demographics. This enables users to analyse healthcare data, extract various insights and generate reports to support enhancements in patient care. The data within ICE is also analysed for the purposes of evaluating whether large initiatives are effective or whether redirection is necessary. This analysis informs commissioners, clinicians and clinical networks on adoption of innovation, adherence to national policy guidelines including NICE, patient pathways and benchmarking. All the data undergoes aggregation and small numbers are suppressed, including secondary suppression as outlined in the HES analysis guide.

ICE incorporates the linkage of community data sets with acute data and mental health data. This tool uses aggregated HES data to provide a useful understanding of the place and interplay of providers needed to be able to chart patient journeys across community, mental health, and acute services with primary care to follow.

ICE analyses data at the ICS, Local Authority and Lower Super Output Layer levels. Given the fluidity of geographic boundaries across ICSs, places and neighbourhoods from an NHS and local authority perspective, there is a need to customise the geographic definition of a unit, which at various levels would not be consistent. To be able to cut the data at various desired levels consistently, very granular data is needed, down to the record level by LSOA, so that it can be cut and re-aggregated into the view that would be most meaningful for CF's clients. The resulting display has aggregated data with a small number of suppressions. The analysis involves drilling down and reconstructing as well as building up from the lowest level. Indicators of public health such as indices of multiple deprivation (IMD) are used to normalise relevant comparisons.

Case Study:

CF released a free version of this tool in February 2022 to all 42 ICBs, which has been used by North Central London ICB, Staffordshire and Stoke on Trent, and Bristol, North Somerset, and Gloucestershire ICB, while the full paid version has been deployed to Sussex Health and Care ICB (https://ics.cfdata.io/) where it is was used to address inequalities in population outcomes and evaluate initiatives to improve population health. The paid version is also being used by Surrey Heartlands ICB to aid development, monitoring and evaluation of their transformation plan.

Data required:

- HES APC

- ECDS

- HES OP

Why that data is required:

CF use HES APC, OP and ECDS data to create integration metrics within physical and mental health, community and hospital-based care, health and social care chasms and ICS, locality breakdowns. CF are also considering implementing neighbourhood breakdown to provide better visibility in more granular level to ICSs.

The list of data required has been expanded slightly due to client requests to drill down into data with more granularity. Based on feedback, there is a desire to expand upon the metrics for further exploration and to allow for deeper analysis and the display of additional measures without patient-level linkage.

Lawful basis

The lawful bases for processing this data under UK GDPR is as follows:

• Article 6(1)(f) – it is necessary for the legitimate interests in being able to provide tools and services that will benefit healthcare organisations

• Article 9(2)(j) – it is necessary for reasons that are in the public interest in the area of public health. CF provides tools and services to public healthcare organisations that help them to monitor and improve the standards and quality of care that they offer. The processing is designed to benefit patients and society as a whole through facilitating better healthcare in the UK. Processing is necessary for archiving purposes in the public interest, scientific or historical research purposes or statistical purposes in accordance with Article 89(1) based on Union or Member State law which shall be proportionate to the aim pursued, respect the right to data protection and provide for suitable and specific measures to safeguard the fundamental rights and the interests of the data subject.

To determine the lawfulness of processing the data for these legitimate interests, CF has undertaken a Legitimate Interests Assessment (LIA) and determined that:

i. The processing is necessary for the purpose:

The processing of patient data is required to provide accurate analysis of patient pathways, outcomes and performance. Aggregate data does not allow the patient level predictions and evaluations required to perform the detailed analysis and modelling required for:

(1) CF Foresight: Predicting patient admission and discharge data, modelling patient level intervention

(2) CF Capacity: Mapping individual patients to activity groups, identifying opportunities within care pathways

(3) CF Benchmarking: Creating patient segmentation groups, modelling A&E performance, identifying financial opportunities for clinical pathways

(4) CF Insights & Collaboration Engine (ICE): Supporting Integrated Care Systems (ICSs) and Boards (ICBs), identifying focus areas to improve population health outcomes, providing ICBs a tool for ongoing self-assessment

ii. The processing is proportionate to the purpose:

The processing of this data will relate solely to the improvement of the health and social care system in England and Wales through providing detailed recommendations and initiatives that aggregate data cannot provide due to the unconnected nature of the data-sets.

The negative impact on individual patients is minimal and CF predicts that patients will benefit from the enhanced service provided by the tools and analysis this data processing produces. This data processing will not identify individuals and the output of this processing will not lead to data-sets that can be used to identify individuals.

iii. The purpose cannot be achieved by processing the data in another more obvious or less intrusive way:

The correlations between behaviours at the level of the individual patient are lost when using aggregate data. These correlations are crucial for capturing the true impact of initiatives and identifying the underlying causes for health system under-performance. Summary statistics mask these relationships and can lead to biased analysis especially when modelling system performance across multiple points of delivery.

iv. The interests of the individual data subjects do not override the legitimate interest:

CF has considered that the data is health data, including data about children or other vulnerable people, which the data subjects are likely to consider particularly private and that some individuals would feel uncomfortable about the processing of their health data outside of the NHS. However, the data sets are pseudonymised and therefore, the possible impacts of the processing will be minimal as CF is not able to de-pseudonymise the data nor will CF attempt to identify patients using any means. CF has put in place policy safeguards to ensure the security and privacy of patient records and limit the impact on patients to positive enhancements of care.

CF believes that the above provides sufficient legitimate interests for lawful processing of the data requested under this Agreement.

CF is the sole Controller for the purposes of this Agreement and CF will be directly processing the data. Amazon Web Services (AWS) is a Processor for CF. Data processing and storage will take place within CF's secure cloud platform which is based on an AWS UK environment. The servers that store and process the data under this Agreement will be within UK sovereignty (London). The data under this Agreement will be solely used for the purposes stated above and only substantive employees of CF will have access to this data. No employee of AWS will access this data.

Benefits to the Health and Social Care System:

CF will support access of the data to NHS clients, enabling more effective use of the data, validation of data through feedback and, crucially, supporting more effective integration of data. The analytical products that CF builds will help NHS clients to make better decisions. A crucial component of the analytical work with NHS clients is to ensure a legacy of embedded analytical capability. CF aims to improve the flow of data across the NHS, closing the gap between action and feedback. This will help reduce data latency and improve data quality, two key components to effective use of data to create a health system that learns from every patient.

The data held under this Agreement will only be used to provide services to NHS and other organisations within England and Wales. CF is a commercial organisation. However, the data are not used for commercial purposes such as sales targeting or commercial insurance.

CF is committed to improving healthcare in the UK and is commissioned by a number of different purchasers and providers of healthcare from NHS organisations and NHS suppliers to solve pre-defined structural, organisational, or operational issues. Part of the service CF offers is the ability to perform detailed analysis using healthcare data to provide insights into the drivers of key problems to enable evidence-based decision making for NHS leadership.

CF will use the data supplied by NHS England to enhance the analytical services CF provide to NHS and other clients, by developing several additional analytical outputs as described in the purpose statements.

Commercial arrangements are put in place between CF and the client organisation. Only CF primary users will have access to NHS England data. Tools created for NHS customers and suppliers will only contain aggregated data (with small numbers suppressed).

CF works on multiple projects at any one time for several different national, regional, and local organisations across the NHS. Therefore, it is not possible to provide full details of all outputs, as these are highly specific to the requirements for each client. CF will only share aggregated analysis with its NHS clients in presentations, reports, or cloud-based visualisation tools, in full compliance with the small numbers guidance. In general, all outputs can be grouped into one of several categories detailed below:

• CF provides detailed reports to clients, which contain data in table format containing aggregated, non-patient identifiable data with small numbers suppressed in line with the HES Analysis Guide. These reports may also contain visualisations created using data based on aggregated, non-patient identifiable results of quantitative analysis.

• CF presents the aggregated, non-patient identifiable results with small numbers suppressed, in the form of tables and visualisations, at meetings with NHS client stakeholders.

• CF provides interactive visualisations to NHS clients in the form of cloud-based tools; the software tools that CF builds will allow some analysis to be done on aggregated data (with small numbers suppressed), in house by the providers/commissioners. CF will not allow the providers and commissioners to directly access the patient level data.

• Benchmarking applies across all services. National benchmarks will be derived from the national data. The outputs from queries against these data will be transferred to visualisation software for communication to CF clients.

All outputs will only contain results in highly aggregated format and as statistical summaries and measures of association. Small numbers will be suppressed. Record level information will not be released to any third party. Examples of the specific tool outputs are set out below:

1) CF Foresight

Output: A browser-based tool that enables providers and commissioners to view predictions of waitlists, future attendances, admissions, discharges, and occupancy as well as model the impact of interventions to improve performance and patient flow.

Timelines: A tailored version of this tool has been developed to support system control centres that were required by ICBs by December 2022, and is currently in use by Surrey Heartlands ICB. This tool is also currently being used to support Manchester University NHS Foundation Trust with forecasting and planning the productivity increase required to recover of elective services such that there are no 65+ week waiters and MFT reaches 103% of 19/20 activity levels by March 2024.

2) CF Capacity

Output: A Python (visualisation software) and Excel based tool which visualises and models the impact of reconfiguration and efficiency improvements.

Timelines: The basic Excel version has been used since 2020 and during 2022 CF have developed an additional automated python-based mapping tool that automates the approach. This has been trialled at two clients during 2022 and is currently live at one. In April – May 2023, CF used a version of CF Capacity to create a capacity and demand model for Mental Health services in SEL. The model resulted in a recommendation that the system increase its bedded capacity and the model was handed over to BI teams in SLaM and Oxleas to continue to use and update.

3) CF Benchmark

Output: A browser based interactive explorer of the population segments, health system performance and financial performance, and an automated PowerPoint presentation.

Timelines: This tool is used internally by CF staff members to provide insights and benchmarking to all of CF's NHS clients. This tool was most recently used, May 2023, to support NCL ICS with creating a baseline understanding of the geographical distribution of maternal and neonatal activity.

4) CF Insight and Collaboration Engine (ICE)

Output: A web-based analytics tool that provides users with a holistic view of the relative current position of an Integrated Care System (ICS)’s population health outcomes compared to other ICSs and the ability to set and track targets for transformation goals and evaluate whether the transformation programmes have been effective.

Timelines: The full version of this tool is used by NHS Sussex ICB and NHS Surrey Heartlands ICB.

A limited free version has been used by North Central London ICB, NHS Staffordshire and Stoke on-Trent ICB, and Bristol, North Somerset and Gloucestershire ICB, helping them to understand their current position, supporting focus areas to improve integration and evaluating the impact of initiatives to improve population health outcomes and reduce inequalities.

All outputs will only contain results in highly aggregated format and as statistical summaries and measures of association. Small numbers will be suppressed in line with the HES Analysis Guide. Record level information will not be released to any third party.

Between the period June 2022 and June 2023, CF has played a vital role in supporting numerous NHS organisations, leveraging Data provided by NHS England to uncover deep insight beyond that of which the NHS organisation are able to achieve themselves due to analytical capability and capacity constraints. Hospital Episode Statistic data has directly contributed to driving financial and performance improvements among CF's clients. CF has leveraged the Data to support the following organisations:

• NHS Devon ICB

• NHS Hampshire and Isle of White ICB

• Homerton Healthcare NHS Foundation Trust

• NHS Kent and Medway ICB

• Manchester University NHS Foundation Trust

• NHS Confed

• NHS England

• NHS North Central London ICB

• Nottingham University Hospitals NHS Trust

• Oldham Council

• NHS South-East London ICB

• NHS Sussex ICB

• University College London Hospitals NHS Trust

• Whittington Health NHS Trust

All four types of CF tools have been used in this period. Below are examples that have yielded benefits for the organisations and the populations that they serve.

CF Foresight Case Study: Manchester University NHS Foundation Trust

Due to the COVID-19 pandemic, the Trust has a significant backlog of patients waiting for treatment, with over 10,000 waiting over 65 weeks and average waits at 23 weeks. CF was commissioned in May 2023 to develop an elective recovery plan to return to 103% of 2019/20 activity levels and eliminate >65 week waits by March 2024.

The core of the approach to developing the elective recovery plan was to conduct a baseline assessment of activity, capacity, waiting workforce across the trust, at as granular a level of possible (site and specialty). HES data (APC and OP) was foundational to conducting this baseline assessment. This data allowed the development of insights that guided the elective recovery and site optimisation plan for both the under-utilized elective hub and the whole site. Examples of key insights developed using data received through DARS were:

• Specialties at MFT are widely distributed, with the average specialty operating across 5 of MFT's 10 sites.

• Activity has reduced across the Trust since 2019/20 but varies significantly by site and point of delivery with Manchester Royal Infirmary inpatient activity down by 16% and elective day case down by 28%.

• Non-elective length of stay increases at the Manchester Royal Infirmary can be explained in totality by changes in complexity unlike other sites.

• Orthopaedics, Paediatric surgery and Ophthalmology have the largest admitted waiting lists, each with over 2,500 people.

• Orthopaedics, ophthalmology, general surgery, ENT and Dental will each have 2,500 admitted clocks to stop by March 2024 to avoid any 65 week-wait breaches.

Insights developed have been used to generate a site optimisation plan for the Trafford Elective Hub. This includes consolidation of HVLC services currently delivered across MFT, to the elective hub which will result in a significant proportion of the longest waiting people (+65 weeks) being seen by March 2024.

CF Capacity Case Study: Southeast London ICS Mental Health Demand

CF were commissioned to leverage a data-driven approach to gain deeper insights. The program focused on analysing historical and current demand for mental health urgent and emergency care in the system. CF combined data analysis and active engagement with stakeholders. The HES APC and ECDS data sets were used to support key analyses and modelling:

• Current state assessment analysis (e.g., demand in acute mental health services, including inpatients, and emergency care)

• Historical demand to understand the demographics, locations and conditions for presenting and where possible, how this has changed with time.

• Length of time spent in A&E for mental health-related attendances compared to all attendances.

• Creating a capacity and demand model for inpatient admissions for older acute care and PICU (psychiatric intensive care) beds across both trusts.

CF conducted a detailed handover to best enable BI teams in SLaM and Oxleas to continue to use and update the model. The model resulted in a recommendation that the system increase its bedded capacity, owing to continually high occupancy levels with demand greater than capacity, and a high spend on out-of-area placement and private beds.

The program provided actionable recommendations through data analysis to improve access to non-emergency crisis services. Stakeholder alignment was achieved through 68 interviews with key stakeholders from various organizations. Critical data insights led to data-related improvements within the system. The demand and capacity model helped forecast future demand for mental health services, resulting in positive impacts on crisis care delivery and informed decision-making.

CF Benchmark Case Study: North Central London ICS ‘Start Well’ Programme

The Start Well Programme in North Central London (NCL) focuses on improving maternity, neonatal, children, and young people's services in an acute hospital setting, catering to a diverse population of around 1.5 million people across five boroughs. The program was initiated in response to calls for action following the publication of the NHS Long Term Plan and the Ockenden Report, as well as the need to learn from changes made during the pandemic. The aim was to urgently address health inequalities within the sector.

Data from HES APC was used in parallel with data from the model hospital and Secondary Usage Services (SUS) inpatient to analyse maternal and neonatal activity across NCL, creating a geographical breakdown of maternal, neonatal and children’s and young peoples’ services. Data analyses were supplemented with 60 clinician interviews to validate outputs and distil strengths and challenges. In addition, all trusts in London were analysed to generate a benchmark comparison between number of deliveries in NCL trusts as compared to peers.

The result of this phase of the Start Well Programme was a comprehensive case for change document that clearly outlined the opportunities for improvement in the NCL system compared to best practice, while acknowledging the strengths of the system. This output provides a basis for further phases of the programme to address the areas where improvements could be made.

The leadership development programme successfully aligned senior leaders from across the system on the importance of the change process and allowed clinical and operational leaders from different organisations to get to know one another. The senior leaders committed to engaging with the change process as the programme moves forward and vowed to bring their staff along with them.

CF Insights and Collaboration Engine (ICE) Case Study: Sussex Integrated Care System

CF were commissioned by NHS Sussex from June-August 2022 to co-develop a tailored version of CF's ICE to cover population health outcomes and health inequalities. The tool developed uses data from as tables of Hospital Episode Statistics (APC, ECDS, OP, CC, AE), as well as other sources, to derive metrics used for performance evaluation, goal setting and tracking.

Sussex ICS have a suite of performance reporting tools and dashboards and a strong performance reporting function, with each service area producing a weekly report that details performance for operational teams to respond to and adjust plans on a timely basis, but the new formation of the ICS meant they required a strategic oversight capability that functioned in tandem with existing teams to identify opportunity areas for improvement, set strategic goals at ICS, Place and local level with the aim to improving outcomes and tackle health inequalities by implementing targeted initiatives, and tracking the impact of the initiatives on outcomes over time.

CF worked closely alongside the Chief Medical Officer and Planning Performance & Intelligence (PPI) team throughout – taking a user-centric approach to development. Over 40 stakeholders were engaged through several interviews, 13 focus groups and over 6 user experience testing sessions.

• CF co-developed the suite of over 100 metrics that the NHS Sussex Executive Team needs to make decisions. The breadth of metrics included understanding the population context and wider determinants of health, through to health behaviours and lifestyle, availability and uptake of services and health outcomes. The tool allows a view of metrics by Core20 and across lower tier Local Authorities wherever possible.

• CF co-designed the user journey and tool interface and iterated it through user experience testing. We established data pipelines for new metrics to ensure metrics automatically updated at the necessary frequency and geographic granularity.

• CF developed as relevant peer groups weighted by multiple factors such as deprivation, rurality etc and a ‘no change’ synthetic counterfactual to estimate impact of initiatives.

• CF updated the reporting process and methodology so that executives have the right information at the right time. Including mapping the different possible users and governance for where information from the tool would be presented and designing user-friendly reporting templates.

Based on the ICE data presented and the local insights, Sussex identified four pressing priorities as CVD, Cancer, Falls & Respiratory Illnesses.

The strategic capability provided the information needed at an executive level for data- led decision making, using a dynamic user interface which will allow users to quickly understand the data and spend more time considering the solutions. This helped support Sussex ICS in their objectives; including improving outcomes in population health and healthcare, tackling inequalities, enhancing productivity and value for money and helping the NHS to support broader social and economic development.

Carnall Farrar Ltd (CF) is a management consultancy and data science company whose mission is to improve healthcare. CF works with several purchasers, providers, and systems across NHS organisations in England, including NHS Trusts, Foundation Trusts, Integrated Care Boards (ICBs), and Commissioning Support Units (CSUs). CF has strong relationships with the Department of Health and Social Care (DHSC), NHS England (NHSE), and the Office for Health Improvements and Disparities (within DHSC). These organisations commission CF to work on projects procured both through direct commissioning agreements, and competitive procurement processes as part of access to over six public sector specific frameworks.

CFs client base consists primarily of NHS organisations. As of September 2022, CF had active contracts with the following NHS clients:

• NHS North East and North Cumbria ICB

• South Tees Hospitals NHS Foundation Trust

• North Tees and Hartlepool Hospitals NHS Foundation Trust

• NHS Sussex Partnership Foundation Trust

• Liverpool University Hospitals NHS Foundation Trust

• Barts Health NHS Trust

• Northern Care Alliance NHS Foundation Trust

• NHS Hampshire Isle of Wight ICB

• NHS North Central London ICB

• NHSE Accelerated Access Collaborative

• NHSE Chief Data and Analytics Office

• NHS Humber and North Yorkshire ICB

• NHS North West London ICB

• NHS Surrey Heartlands ICB

• NHS Sussex ICB

CF has worked with over 30 health and social care systems in England to support health system strategy and strengthening, service transformation, financial sustainability, and integrated care delivery including:

- Providers of healthcare services

- Integrated Care Boards (ICBs)

- Commissioning Support Units (CSUs)

- Hospital Trusts

- Private secondary care providers

- Mental Health trusts

- Community Provider Trusts

- Pharmacies

- NHS England

- Office for Health Improvement and Disparities (formerly Public Health England)

CF has handled large volumes of data which has been obtained directly from NHS clients. CF has been successful in using this data to provide meaningful analytics which have positively impacted NHS organisations. However, the data available directly from each NHS organisation is aggregate data and does not include diagnostic (clinical) codes. The results, although useful, are limited.

CF obtain data from NHS England to expand the products currently on offer for NHS Clients. The record level data disseminated, although pseudonymised, is richer and more accurate than the data held by individual NHS organisations. Using the data under this Agreement, CF aims to provide more in-depth tools and products for NHS clients, therefore producing more accurate insight into the areas of the NHS requiring improvement and how these improvements can be made.

CF requires NHS England data in order provide additional benefits to NHS clients by expanding the capabilities of existing products and reducing costs to the NHS. Previously only three products have been produced using the data under this Agreement:

- CF Foresight

- CF Capacity

- CF Benchmarks

These products meet CFs ongoing objectives to improve patient flow (i.e., a patient’s entire journey from entering care to discharge), ensuring that patients receive high quality care at the right time and in the right place. They will also support determining the right size clinical services to meet future demand and provide insights into opportunities through benchmarking.

From 2022, CF is developing a new tool called the 'CF ICE (Integrated Care Explorer)' to support ICBs to develop and deliver their strategy, which will also utilise the data under this Agreement.

Further details about each of these tools are provided below:

1) CF Foresight:

Purpose:

This tool predicts demand and patient flow through a hospital over the short to medium term (1-4 months). Hospitals can look at upcoming demand compared to their current capacity, identifying potential pressure points. The tool can also test the impact of different potential interventions on demand and flow, informing data driven strategic decisions.

Case Study:

A basic version of the tool was initially tested by Northampton General Hospital NHS Trust. CF is working with NHS England’s Data and Analytical Product team to co-design the next version of the tool to provide a national overview of demand and flow. CF’s own tool was paused during the COVID-19 pandemic but is now in greater demand as systems attempt to catch up on their backlog of elective procedures. This was further developed with Kettering General Hospital NHS Foundation Trust and Northampton General Hospital NHS Trust in October and November 2021 to combine non-elective and elective pathways, specifically addressing their waitlist with increased activity, their activity with increased capacity, and their capacity capabilities with an increase in workforce availability. In 2022, CF have been leveraging this product to deliver system control centres in NHS Surrey ICB, NHS Humber and North Yorkshire ICB, and NHS North Central London ICB.

Data required:

A five-year extract of the following data sets:

- Hospital Episode Statistics (HES) Admitted Patient Care (APC)

- HES Outpatients (OP)

- HES Critical Care (CC)

- HES Accident and Emergency (A&E)

- Emergency Care Data Set (ECDS)

- Diagnostic Imaging Dataset (DIDs)

Why that data is required:

The tool incorporates machine learning model to predict future performance. The more years of data that are available for training, the better the accuracy of the model. Five years of data is considered sufficient to account for annual variation. The HES APC, CC, A&E, and ECDS data are required to train patient level models for predicting attendance, admission, four-hour breaches, and discharges within the hospital. The row level data is also required to model the specific interventions that trusts plan on using to improve performance. These interventions often require clinical coding to identify the impacted patients e.g., increasing discharge rates in frail elderly population within orthopaedics. CF requires the latest available datasets to ensure that NHS commissioners and providers, who will receive CF analytics products, can make effective decisions based on the most up-to-date information.

The DIDs data is required to predict pathways that relevant patients might take in various disease areas including cancer diagnosis and progression. It provides invaluable, detailed information to build on participants’ disease phenotypes (e.g., tumour size and spread in cancer). This data also adds to the understanding of patients’ histories on individual and cohort level and their relationship with genomic alterations, all of which are beneficial for the tool in predicting downstream pathways and outcomes that might impact on demand and patient flow through hospitals.

CF acknowledges that DIDs includes data from 217 NHS providers and covers data on diagnostic imaging tests on a large proportion of NHS patients in England. The DIDs reports on imaging activity, referral source, and timeliness, and approximately 44.0 million imaging tests were reported in England in the year to March 2022. DIDs captures information about referral source and patient type, details of the test (type of test and body site), demographic information such as GP registered practice, patient postcode, ethnicity, gender, and date of birth, plus items about waiting times for each diagnostic imaging event, from time of test request through to time of reporting. CF have therefore minimised the data requested as far as possible; CF have not requested all of the available fields from within the DIDs dataset, but only those fields necessary to carry out the analysis detailed in this Agreement are requested. Data is restricted to 5 historic years only.

2) CF Capacity:

Purpose:

This tool predicts in which year demand in an acute NHS organisation will exceed capacity based on demographic and non-demographic growth. It allows a system to model a variety of clinical configurations across sites, to maximise the operational effectiveness whilst minimising the negative impacts on patient safety, access, and hospital performance.

It is hoped that this tool, with the right bed-based capacity data, when combined with local data, will allow NHS and social care organisations to determine the necessary bed requirements. Given anticipated demand and associated operational assumptions, the capacity requirements by different type of beds based on requirements can be specified using this tool.

Case Study:

In 2019, CF used this tool in Guernsey to ensure that the new hospital will be correctly sized, for the Barking, Havering, and Redbridge University NHS Trust to reconfigure services to optimise current capacity across two sites and at Whipp’s Cross Hospital where CF assisted in the design of the hospital to ensure it met future capacity requirements.

Additionally, CF combined the features within the CF Foresight and Capacity tools at the start of the pandemic in 2020 to support system-wide modelling of demand and capacity in the five STPs of London, 32 LAs, and 9 community providers. CF used historical data from HES APC, A&E, and OP alongside COVID-19 sitreps, to develop browser-based software that enabled over 50 NHS users to:

• Allow NHS organisations to extend their current capacity through re-configuration and productivity improvements (CF Capacity)

• Allow NHS organisation to create the optimal configuration of capacity given the constraints of workforce and clinical effectiveness (CF Capacity)

• Predict future activity (CF Foresight)

• Quantify the impact of plans on future occupancy (CF Foresight)

• Develop plans to change activity over a selected period of time (CF Foresight)

• Track activity against baseline to assess real-time efficacy of the new plan (CF Foresight)

• Identify where and when demand will exceed capacity (new system level features)

• Provide forecasts on the likely demand for different discharge pathways to community and social care providers (new system level features)

Since the completion of this work in May 2020, the team have observed continued engagement with the tool. There were approximately 800 total interactions up until September 2020 at which point CF could no longer track users as this work was transferred into the NHSE foundry tooling. Using this tool, several key insights were uncovered:

An evolution of this model has been used for NHS Nottinghamshire CCG (2020), Hampshire Hospitals NHS Foundation Trust (2021), North West London ICB (2022), and North Central London ICB (2022). In these projects, HES and ECDS data was used to create deprivation heat maps to visualise the characteristics of the population and note if there were any pockets of areas with high deprivation/ high elderly population/ high proportion of black, Asian and minority ethnicity (BAME). This was linked to the corresponding patient flow to identify mismatched access to care and capacity constraints.

Data required:

A five-year extract of the following data sets:

- HES APC

- ECDS

- Diagnostic Imaging Dataset (DIDs)

Why that data is required:

This tool predicts up to 5 years into the future and relies on historical activity data to predict the trend and changes in activity over and above that expected from demographic changes. Five years of historic data is the minimum amount of data CF requires to capture longer term trends. Activity is categorised by point of delivery (outpatient, inpatient, emergency department), age, and healthcare resource group (HRG) code (where possible). This activity data is then mapped to capacity within the hospital. In order to capture the value from the capacity available, CF models scenarios that improve efficiency or reconfigure services. The outputs from the reconfiguration analysis will feed into a separate model, which predicts the effect of different service configurations on finance, workforce, estates, capital, and finance. This requires row level data including clinical codes. Access to mental health datasets should allow CF to analyse the acute patient pathways for mental health service users, and enable a better understanding of the clinical needs now and in the future.

3) CF Benchmarks:

Purpose:

To provide a set of automated reports that allow for a rapid diagnostic of ICBs)/places/local authorities. An automated set of reports that benchmarks ICBs across hospital demand, projected demand, life expectancy, deprivation, hospital performance, Quality and Outcomes Framework (QOF), expenditure, workforce, and populations segmentation. This product allows for a rapid diagnostic of a geographic area, freeing up time to focus on improvement rather than number analysis.

The report topics that are included are:

- Population Segmentation

- Drivers of the deficit

- Inpatient activity

- A&E performance

- Outpatient activity

Case Study:

CF has combined the HES data, the Secondary Use Services (SUS) data and the ECDS data into a single aggregated data pipeline with an internally facing browser interface for CF consultants to use on NHSE projects. This allowed both commissioners and providers to assess performance across the system and see trends in their key activity and quality metrics against their compare performance to peers as well as understand the scale of opportunity to improve performance. CF have used this tool to yield benefits in the following areas:

Hampshire and Isle of Wight ICB:

CF supported the elective recovery of Hampshire and Isle of Wight ICB in 2021. CF developed a demand and capacity model to support future planning and recovery. Additionally, CF created four speciality business cases and a medium-term plan, which were signed off and approved by the Planned Care Board, starting the process to establish specialty elective hubs and pathway changes across the system.

The work produced a series of deliverables that support the elective recovery of the ICB:

• Comprehensive demand and capacity model that allowed an understanding of the gaps in theatres and beds across the system and the future waiting list challenge for each trust

• Four specialty business cases, approved by the Planned Care Board, that set out clear next steps for the specialties and an approach to hub working that could tackle the longest waiters

• Holistic medium-term (1-3 years) plan that set out a clear ambition and necessary enablers that would allow the delivery of elective care across the ICB.

CF also supported the successful bid for the ICB to receive £10m in funding as an elective accelerator system and the submission of an elective recovery planning submission to NHS England.

Data required:

- HES APC

- ECDS

- HES A&E (for historical data)

- HES OP

- Community Services Dataset (CSDS)

- DIDs

- Mental Health datasets

Why that data is required:

CF will use these datasets to enable system financial leadership and regulators to understand the strategic financial challenge of a local area and benchmark against national peers. Mental health data is required to enable clients to monitor performance against internal targets and benchmark against national peers whilst the bridge file is required to support planning for mental health patients based on the benchmarked opportunities. The HES and Mental health data are required for benchmarking inpatient activity, outpatient activity, A&E performance, and populations segmentation. Five years of data is required as time-series analysis to assess trends in performance, expenditure, utilisation, demand, seasonal patterns in utilisation, and directional trends in performance.

The data is required at the patient level as CF’s benchmarking uses national data at the patient level to create explanatory models for each report. These explanatory models are required to compare the performance at the regional, local, site and specialty based on time of day and patient movements within the healthcare system e.g.. quantifying the differential impact across sites that the number of people in an emergency department has on the probability of a patient breaching the 4 hour target.

There is a desire to link patient level data with CSDS and DIDs, leaving it pseudonymised, to make it more actionable and to understand variations in slightly defined groups, which clearly consist of suppressed small numbers. For high-risk and high-cost patients, the ability to link data allows for a more pathway-centric view.

As a secondary uses data set, CSDS re-uses clinical and operational data for purposes other than direct patient care. CSDS sets out national definitions for the extraction of data about children and adults. These activities could take place in settings such as health centres, Sure Start centres, day care facilities, schools or community centres, mobile facilities, or a patient's own home. As such the scope of this dataset is far-reaching and includes a large proportion of the population of England, for example in September 2022 alone, there were 1,398,795 referrals received relating to 1,030,395 persons needing care. CF have therefore minimised the data requested from the CSDS dataset to the least amount required; data is minimised to 5 historic years only and the number of fields requested have been minimised so that only those necessary to perform the analysis detailed in this Agreement have been requested.

NEW TOOLS AND OBJECTIVES:

4) CF Integrated Care Explorer (ICE):

Purpose:

The ICE is a web-based analytics tool that provides ICBs with a holistic view of the relative current position on the integration of their services compared to other ICBs, across physical and mental health, community and hospital-based care, and health and social care. ICE supports the development of ICBs by helping them to understand their current position and support identifying focus areas to improve integration across different service areas.

The ICE incorporates the linkage of community data sets with acute data and mental health data. This tool uses aggregated HES data to provide a useful understanding of the place and interplay of providers needed to be able to chart patient journeys across community, mental health, and acute services with primary care to follow.

The aim is to adjust ICE to look at local authorities with Lower Layer Super Output Areas (LSOA) mapping. Given the fluidity of geographic boundaries across ICB places and neighbourhoods from an NHS and local authority perspective, there is a need to customise the geographic definition of a unit, which at various levels would not be consistent. To be able to cut the data at various desired levels consistently, very granular data will be needed, down to the record level by LSOA, so that it can be cut and re-aggregated into the view that would be most meaningful for CF's clients. The resulting display would be to aggregate data with a small number of suppressions. The analysis would require drilling down and reconstructing as well as building up from the lowest level. It is important that age banding, health conditions. and ethnicity be included along with indicators of public health such as indices of multiple deprivation (IMD) to fully normalise relevant comparisons.

Case Study:

CF released a free version of this tool in February 2022 to all 42 ICBs, which has been used by North Central London ICB, Staffordshire and Stoke on Trent, and Bristol, North Somerset, and Gloucestershire ICB, while the full paid version has been deployed to Sussex Health and Care ICB (https://ics.cfdata.io/) where it is being used to address inequalities in population outcomes and evaluate initiatives to improve population health.

Data required:

- HES APC

- ECDS

- CSDS

Why that data is required:

CF use HES APC data to create 24 selected integration metrics within physical and mental health, community and hospital-based care, health and social care chasms and ICB, locality breakdowns. CF are also working on implementing neighbourhood breakdown to provide better visibility in more granular level to ICBs.

The list of data required has been expanded slightly due to client requests to drill down into bits of data with more granularity. Based on feedback, there is a desire to expand upon the 24 selected integration metrics for further exploration and to allow for deeper analysis and the display of additional measures without patient-level linkage.

Lawful basis

The lawful bases for processing this data under UK GDPR is as follows:

• Article 6(1)(f) – it is necessary for the legitimate interests in being able to provide tools and services that will benefit healthcare organisations

• Article 9(2)(j) – it is necessary for reasons that are in the public interest in the area of public health. CF provides tools and services to public healthcare organisations that help them to monitor and improve the standards and quality of care that they offer. The processing is designed to benefit patients and society as a whole through facilitating better healthcare in the UK. Processing is necessary for archiving purposes in the public interest, scientific or historical research purposes or statistical purposes in accordance with Article 89(1) based on Union or Member State law which shall be proportionate to the aim pursued, respect the right to data protection and provide for suitable and specific measures to safeguard the fundamental rights and the interests of the data subject.

To determine the lawfulness of processing the data for these legitimate interests, CF has undertaken a Legitimate Interests Assessment (LIA) and determined that:

i. The processing is necessary for the purpose:

The processing of patient data is required to provide accurate analysis of patient pathways, outcomes and performance. Aggregate data does not allow the patient level predictions and evaluations required to perform the detailed analysis and modelling required for:

(1) CF Foresight: Predicting patient admission and discharge data, modelling patient level intervention

(2) CF Capacity: Mapping individual patients to activity groups, identifying opportunities within care pathways

(3) CF Benchmarking: Creating patient segmentation groups, modelling A&E performance, identifying financial opportunities for clinical pathways

(4) CF Integrated Care Explorer (ICE): Supporting Integrated Care Boards (ICBs), identifying focus areas to improve integration across different services, providing ICBs a tool for ongoing self-assessment

ii. The processing is proportionate to the purpose:

The processing of this data will relate solely to the improvement of the health and social care system in England and Wales through providing detailed recommendations and initiatives that aggregate data cannot provide due to the unconnected nature of the data-sets.

The negative impact on individual patients is minimal and CF predicts that patients will benefit from the enhanced service provided by the tools and analysis this data processing produces. This data processing will not identify individuals and the output of this processing will not lead to data-sets that can be used to identify individuals.

iii. The purpose cannot be achieved by processing the data in another more obvious or less intrusive way:

The correlations between behaviours at the level of the individual patient are lost when using aggregate data. These correlations are crucial for capturing the true impact of initiatives and identifying the underlying causes for health system under-performance. Summary statistics mask these relationships and can lead to biased analysis especially when modelling system performance across multiple points of delivery.

iv. The interests of the individual data subjects do not override the legitimate interest:

CF has considered that the data is health data, including data about children or other vulnerable people, which the data subjects are likely to consider particularly private and that some individuals would feel uncomfortable about the processing of their health data outside of the NHS. However, the data sets are pseudonymised and therefore, the possible impacts of the processing will be minimal as CF is not able to de-pseudonymise the data nor will CF attempt to identify patients using any means. CF has put in place policy safeguards to ensure the security and privacy of patient records and limit the impact on patients to positive enhancements of care.

CF believes that the above provides sufficient legitimate interests for lawful processing of the data requested under this Agreement.

CF is the sole Controller for the purposes of this Agreement and CF will be directly processing the data. Amazon Web Services (AWS) is a Processor for CF. Data processing and storage will take place within CF's secure cloud platform which is based on an AWS UK environment. The servers that store and process the data under this Agreement will be within UK sovereignty (London). The data under this Agreement will be solely used for the purposes stated above and only substantive employees of CF will have access to this data. No employee of AWS will access this data.

Benefits to the Health and Social Care System:

CF will support access of the data to NHS clients, enabling more effective use of the data, validation of data through feedback and, crucially, supporting more effective integration of data. The analytical products that CF builds will help NHS clients to make better decisions. A crucial component of the analytical work with NHS clients is to ensure a legacy of embedded analytical capability. CF aims to improve the flow of data across the NHS, closing the gap between action and feedback. This will help reduce data latency and improve data quality, two key components to effective use of data to create a health system that learns from every patient.

The data held under this Agreement will only be used to provide services to NHS organisations within England and Wales. For CF’s non-NHS clients, only publicly available data is used, and the data is stored in a different physical location within CF's data warehouse. The data held under this Agreement will only be used for CF’s NHS Clients and will not be shared between NHS and non-NHS projects/organisations.

CF is a commercial organisation. However, the data are not used for commercial purposes such as sales targeting or commercial insurance.

CF is committed to improving healthcare in the UK and is commissioned by a number of different purchasers and providers of healthcare from NHS organisations to solve pre-defined structural, organisational, or operational issues. Part of the service CF offers is the ability to perform detailed analysis using healthcare data to provide insights into the drivers of key problems to enable evidence-based decision making for NHS leadership.

CF will use the data supplied by NHS England to enhance the analytical services CF provide to NHS clients, by developing several additional analytical outputs as described in the purpose statements.

Commercial arrangements are put in place between CF and the client organisation. Only CF primary users will have access to NHS England data. Tools created for NHS customers will only contain aggregated data (with small numbers suppressed).

CF works on multiple projects at any one time for several different national, regional, and local organisations across the NHS. Therefore, it is not possible to provide full details of all outputs, as these are highly specific to the requirements for each client. CF will only share aggregated analysis with its NHS clients in presentations, reports, or cloud-based visualisation tools, in full compliance with the small numbers guidance. In general, all outputs can be grouped into one of several categories detailed below:

• CF provides detailed reports to clients, which contain data in table format containing aggregated, non-patient identifiable data with small numbers suppressed in line with the HES Analysis Guide. These reports may also contain visualisations created using data based on aggregated, non-patient identifiable results of quantitative analysis.

• CF presents the aggregated, non-patient identifiable results with small numbers suppressed, in the form of tables and visualisations, at meetings with NHS client stakeholders.

• CF provides interactive visualisations to NHS clients in the form of cloud-based tools; the software tools that CF builds will allow some analysis to be done on aggregated data (with small numbers suppressed), in house by the providers/commissioners. CF will not allow the providers and commissioners to directly access the patient level data.

• Benchmarking applies across all services. National benchmarks will be derived from the national data. The outputs from queries against these data will be transferred to visualisation software for communication to CF clients.

All outputs will only contain results in highly aggregated format and as statistical summaries and measures of association. Small numbers will be suppressed. Record level information will not be released to any third party. Examples of the specific tool outputs are set out below:

1) CF Foresight

Output: A browser-based tool that enables providers and commissioners to view predictions of waitlists, future attendances, admissions, discharges, and occupancy as well as model the impact of interventions to improve performance and patient flow.

Timelines: A tailored version of this tool has been developed to support system control centres that were required by ICBs by December 2022, and is currently in use by Surrey Heartlands ICB. This tool is also currently being used to support Manchester University NHS Foundation Trust with forecasting and planning the productivity increase required to recover of elective services such that there are no 65+ week waiters and MFT reaches 103% of 19/20 activity levels by March 2024.

2) CF Capacity

Output: A Python (visualisation software) and Excel based tool which visualises and models the impact of reconfiguration and efficiency improvements.

Timelines: The basic Excel version has been used since 2020 and during 2022 CF have developed an additional automated python-based mapping tool that automates the approach. This has been trialled at two clients during 2022 and is currently live at one. In April – May 2023, CF used a version of CF Capacity to create a capacity and demand model for Mental Health services in SEL. The model resulted in a recommendation that the system increase its bedded capacity and the model was handed over to BI teams in SLaM and Oxleas to continue to use and update.

3) CF Benchmark

Output: A browser based interactive explorer of the population segments, health system performance and financial performance, and an automated PowerPoint presentation.

Timelines: This tool is used internally by CF staff members to provide insights and benchmarking to all of CF's NHS clients. This tool was most recently used, May 2023, to support NCL ICS with creating a baseline understanding of the geographical distribution of maternal and neonatal activity.

4) CF Insight and Collaboration Engine (ICE)

Output: A web-based analytics tool that provides a holistic view of the relative current performance and position on the integration of ICB services.

Timelines: The full version of this tool is used by NHS Sussex ICB, NHS Sussex ICB and NHS Greater Manchester ICB. A limited free version has been used by North Central London ICB, NHS Staffordshire and Stoke-on-Trent ICB, and Bristol, North Somerset and Gloucestershire ICB, helping them to understand their current position, supporting focus areas to improve integration and evaluating the impact of initiatives to improve population health outcomes and reduce inequalities.

All outputs will only contain results in highly aggregated format and as statistical summaries and measures of association. Small numbers will be suppressed in line with the HES Analysis Guide. Record level information will not be released to any third party.

Between the period June 2022 and June 2023, CF has played a vital role in supporting numerous NHS organisations, leveraging data provided by the DARS to uncover deep insight beyond that of which the NHS organisation are able to achieve themselves due to analytical capability and capacity constraints. Hospital Episode Statistic data has directly contributed to driving financial and performance improvements among CF's clients. CF has leveraged DARS to support the following organisations:

• NHS Devon ICB

• NHS Hampshire and Isle of White ICB

• Homerton Healthcare NHS Foundation Trust

• NHS Kent and Medway ICB

• Manchester University NHS Foundation Trust

• NHS Confed

• NHS England

• NHS North Central London ICB

• Nottingham University Hospitals NHS Trust

• Oldham Council

• NHS South-East London ICB

• Sussex ICB

• University College London Hospitals NHS Trust

• Whittington Health NHS Trust

All four types of CF tools have been used in this period. Below are examples that have yielded benefits for the organisations and the populations that they serve.

CF Foresight Case Study: Manchester University NHS Foundation Trust

Due to the COVID-19 pandemic, the Trust has a significant backlog of patients waiting for treatment, with over 10,000 waiting over 65 weeks and average waits at 23 weeks. CF was commissioned in May 2023 to develop an elective recovery plan to return to 103% of 2019/20 activity levels and eliminate >65 week waits by March 2024.

The core of the approach to developing the elective recovery plan was to conduct a baseline assessment of activity, capacity, waiting workforce across the trust, at as granular a level of possible (site and specialty). HES data (APC and OP) was foundational to conducting this baseline assessment. This data allowed the development of insights that guided the elective recovery and site optimisation plan for both the under-utilized elective hub and the whole site. Examples of key insights developed using data received through DARS were:

• Specialties at MFT are widely distributed, with the average specialty operating across 5 of MFT's 10 sites.

• Activity has reduced across the Trust since 2019/20 but varies significantly by site and point of delivery with Manchester Royal Infirmary inpatient activity down by 16% and elective day case down by 28%.

• Non-elective length of stay increases at the Manchester Royal Infirmary can be explained in totality by changes in complexity unlike other sites.

• Orthopaedics, Paediatric surgery and Ophthalmology have the largest admitted waiting lists, each with over 2,500 people.

• Orthopaedics, ophthalmology, general surgery, ENT and Dental will each have 2,500 admitted clocks to stop by March 2024 to avoid any 65 week-wait breaches.

Insights developed have been used to generate a site optimisation plan for the Trafford Elective Hub. This includes consolidation of HVLC services currently delivered across MFT, to the elective hub which will result in a significant proportion of the longest waiting people (+65 weeks) being seen by March 2024.

CF Capacity Case Study: Southeast London ICS Mental Health Demand

CF were commissioned to leverage a data-driven approach to gain deeper insights. The program focused on analysing historical and current demand for mental health urgent and emergency care in the system. CF combined data analysis and active engagement with stakeholders. The HES APC and ECDS data sets were used to support key analyses and modelling:

• Current state assessment analysis (e.g., demand in acute mental health services, including inpatients, and emergency care)

• Historical demand to understand who is presenting, where, presenting with and where possible, how this has changed with time.

• Length of time spent in A&E for mental health-related attendances compared to all attendances.

• Creating a capacity and demand model for inpatient admissions for older acute care and PICU (psychiatric intensive care) beds across both trusts.

CF conducted a detailed handover to best enable BI teams in SLaM and Oxleas to continue to use and update the model. The model resulted in a recommendation that the system increase its bedded capacity, owing to continually high occupancy levels with demand greater than capacity, and a high spend on out-of-area placement and private beds.

The program provided actionable recommendations through data analysis to improve access to non-emergency crisis services. Stakeholder alignment was achieved through 68 interviews with key stakeholders from various organizations. Critical data insights led to data-related improvements within the system. The demand and capacity model helped forecast future demand for mental health services, resulting in positive impacts on crisis care delivery and informed decision-making.

CF Benchmark Case Study: North Central London ICS ‘Start Well’ Programme

The Start Well Programme in North Central London (NCL) focuses on improving maternity, neonatal, children, and young people's services in an acute hospital setting, catering to a diverse population of around 1.5 million people across five boroughs. The program was initiated in response to calls for action following the publication of the NHS Long Term Plan and the Ockenden Report, as well as the need to learn from changes made during the pandemic. The aim was to urgently address health inequalities within the sector.

Data from HES APC was used in parallel with data from the model hospital and Secondary Usage Services (SUS) inpatient to analyse maternal and neonatal activity across NCL, creating a geographical breakdown of maternal, neonatal and children’s and young peoples’ services. Data analyses were supplemented with 60 clinician interviews to validate outputs and distil strengths and challenges. In addition, all trusts in London were analysed to generate a benchmark comparison between number of deliveries in NCL trusts as compared to peers.

The result of this phase of the Start Well Programme was a comprehensive case for change document that clearly outlined the opportunities for improvement in the NCL system compared to best practice, while acknowledging the strengths of the system. This output provides a basis for further phases of the programme to address the areas where improvements could be made.

The leadership development programme successfully aligned senior leaders from across the system on the importance of the change process and allowed clinical and operational leaders from different organisations to get to know one another. The senior leaders committed to engaging with the change process as the programme moves forward and vowed to bring their staff along with them.

CF Insight and Collaboration Engine (ICE) Case Study: Sussex Integrated Care System

CF were commissioned by NHS Sussex from June-August 2022 to co-develop a tailored version of CF's ICE to cover population health outcomes and health inequalities. The tool developed uses data from as tables of Hospital Episode Statistics (APC, ECDS, OP, CC, AE), as well as other sources, to derive metrics used for performance evaluation, goal setting and tracking.

Sussex ICS have a suite of performance reporting tools and dashboards and a strong performance reporting function, with each service area producing a weekly report that details performance for operational teams to respond to and adjust plans on a timely basis, but the new formation of the ICS meant they required a strategic oversight capability that functioned in tandem with existing teams to identify opportunity areas for improvement, set strategic goals at ICS, Place and local level with the aim to improving outcomes and tackle health inequalities by implementing targeted initiatives, and tracking the impact of the initiatives on outcomes over time.

CF worked closely alongside the Chief Medical Officer and Planning Performance & Intelligence (PPI) team throughout – taking a user-centric approach to development. Over 40 stakeholders were engaged through several interviews, 13 focus groups and over 6 user experience testing sessions.

• CF co-developed of the suite over 100 metrics that the NHS Sussex Executive Team needs to make decisions. The breadth of metrics included understanding the population context and wider determinants of health, through to health behaviours and lifestyle, availability and uptake of services and health outcomes. The tool allows a view of metrics by Core20 and across lower tier Local Authorities wherever possible.

• CF co-designed the user journey and tool interface and iterated it through user experience testing. We established data pipelines for new metrics to ensure metrics automatically updated at the necessary frequency and geographic granularity.

• CF developed as relevant peer groups weighted by multiple factors such as deprivation, rurality etc and a ‘no change’ synthetic counterfactual to estimate impact of initiatives.

• CF updated the reporting process and methodology so that executives have the right information at the right time. Including mapping the different possible users and governance fora where information from the tool would be presented and designing user-friendly reporting templates.

Based on the ICE data presented and the local insights, Sussex identified four pressing priorities as CVD, Cancer, Falls & Respiratory Illnesses.

The strategic capability provided the information needed at an executive level for data- led decision making, using a dynamic user interface which will allow users to quickly understand the data and spend more time considering the solutions. This helped support Sussex ICS in their objectives; including improving outcomes in population health and healthcare, tackling inequalities, enhancing productivity and value for money and helping the NHS to support broader social and economic development.

Carnall Farrar Ltd (CF) is a management consultancy and data science company whose mission is to improve healthcare. CF works with several purchasers, providers, and systems across NHS organisations in England, including NHS Trusts, Foundation Trusts, Clinical Commissioning Groups (CCGs) and Commissioning Support Units (CSUs). CF has strong relationships with the Department of Health and Social Care (DHSC), NHS England (NHSE) and the Office for Health Improvements and Disparities (within DHSC). These organisations commission CF to work on projects procured both through direct commissioning agreements, and competitive procurement processes as part of access to over six public sector specific frameworks.

CF’s client base consists primarily of NHS organisations. As of September 2022, CF had active contracts with the following NHS clients:

• NHS North East and North Cumbria Integrated Care Board (ICB)

• South Tees Hospitals NHS Foundation Trust

• North Tees and Hartlepool Hospitals NHS Foundation Trust

• NHS Sussex Partnership Foundation Trust

• Liverpool University Hospitals NHS Foundation Trust

• Barts Health NHS Trust

• Northern Care Alliance NHS Foundation Trust

• NHS Hampshire Isle of Wight ICB

• NHS North Central London ICB

• NHSE Accelerated Access Collaborative

• NHSE Chief Data and Analytics Office

• NHS Humber and North Yorkshire ICB

• NHS North West London ICB

• NHS Surrey Heartlands ICB

• NHS Sussex ICB

Over the past three years, CF has worked with over 30 health and social care systems in England, to support health system strategy and strengthening, service transformation, financial sustainability, and integrated care delivery including:

- Providers of healthcare services

- Clinical Commissioning Groups

- Integrated Care Boards (ICBs)

- Commissioning Support Units (CSUs)

- Hospital Trusts

- Private secondary care providers

- Mental Health trusts

- Community Provider Trusts

- Pharmacies

- NHS England

- Office for Health Improvement and Disparities (formerly Public Health England)

Over the past five years CF has handled large volumes of data which has been obtained directly from NHS clients. CF has been successful in using this data to provide meaningful analytics which have positively impacted NHS organisations. However, the data available directly from each NHS organisation is aggregate data and does not include diagnostic (clinical) codes. The results, although useful, are limited.

Additionally, under this Agreement, Carnall Farrar obtains data from NHS Digital to expand the products currently on offer for NHS Clients. The record level data disseminated under this Agreement, although pseudonymised, is richer and more accurate than the data held by individual NHS organisations. Using the data under this Agreement, CF aim to provide more in-depth tools and products for NHS clients, therefore producing more accurate insight into the areas of the NHS requiring improvement and how these improvements can be made.

CF requires NHS Digital data in order provide additional benefits to NHS clients by expanding the capabilities of existing products and reducing costs to the NHS. Previously only three products have been produced using the data under this Agreement:

- CF Foresight

- CF Capacity

- CF Benchmarks

These products meet CF's ongoing objectives to improve patient flow, right size clinical services to meet future demand and provide insights into opportunities through benchmarking.

From 2022, CF is developing a new tool called the 'CF ICE (Integrated Care Explorer)' to support integrated care boards develop and deliver their strategy, which will also utilise the data under this Agreement.

Further details about each of these tools are provided below:

1) CF Foresight:

Purpose:

This tool predicts demand and patient flow through a hospital over the short to medium term (1-4 months). Hospitals can identify “pinch” points in upcoming demand compared to their current capacity and model the impact of a variety of interventions on demand and flow.

Case Study:

A basic version of the tool was alpha tested by Northampton General Hospital NHS Trust. CF is working with NHS England’s Data and Analytical Product team, to co-design the next version of the tool to provide a national overview of demand and flow. CF’s own tool was paused during the COVID-19 pandemic but is now in greater demand as systems attempt to catch up on their elective backlog. This was further developed with Kettering General Hospital NHS Foundation Trust and Northampton General Hospital NHS Trust in October and November 2021 to combine non-elective and elective pathways, specifically addressing their waitlist with increased activity, their activity with increased capacity, and their capacity capabilities with an increase in workforce availability. In 2022 CF have been leveraging this product to deliver system control centres in NHS Surrey ICB, NHS Humber and North Yorkshire ICB and NHS North Central London ICB.

Data required:

A five-year extract of the following data sets:

- Hospital Episode Statistics (HES) Admitted Patient Care (APC)

- HES Out Patients (OP)

- HES Critical Care (CC)

- HES Accident and Emergency (A&E)

- Emergency Care Dataset (ECDS)

- Diagnostic Imaging Dataset (DIDs)

Why that data is required?

The tool incorporates machine learning model to predict future performance. The more years of data that are available for training the better the accuracy of the model. Five years of data is considered sufficient to account for annual variation. The HES APC, CC, A&E and the ECDS data are required to train patient level models for predicting attendance, admission, four-hour breaches, and discharges within the hospital. The row level data is also required to model the specific interventions that trusts plan on using to improve performance. These interventions often require clinical coding to identify the impacted patients e.g., increasing discharge rates in frail elderly population within orthopaedics. CF requires the latest available datasets to ensure that NHS commissioners and providers, who will receive CF analytics products, can make effective decisions based on the most up-to-date information.

In addition to the HES and ECDS data previously mentioned, the diagnostic imaging dataset (DIDs) is required to predict pathways that relevant patients might take in various disease areas including cancer diagnosis and progression. It provides invaluable, detailed information to build on participants’ disease phenotypes (e.g., tumour size and spread in cancer). This data also adds to the understanding of patients’ histories on individual and cohort level and their relationship with genomic alterations, all of which are beneficial for the tool in predicting downstream pathways and outcomes that might impact on demand and patient flow through hospitals.

CF acknowledges that DIDs includes data from 217 NHS providers and covers data on diagnostic imaging tests on a large proportion of NHS patients in England. The DIDs reports on imaging activity, referral source and timeliness and approximately 44.0 million imaging tests were reported in England in the year to March 2022. DIDs captures information about referral source and patient type, details of the test (type of test and body site), demographic information such as GP registered practice, patient postcode, ethnicity, gender and date of birth, plus items about waiting times for each diagnostic imaging event, from time of test request through to time of reporting. CF have therefore minimised the data requested as far as possible; CF have not requested all of the available fields from within the DIDs dataset, but only those fields necessary to carry out the analysis detailed in this Agreement are requested. Data is restricted to 5 historic years only.

2) CF Capacity:

Purpose:

This tool predicts in which year demand in an acute NHS organisation will exceed capacity based on demographic and non-demographic growth. It allows a system to model a variety of clinical configurations across sites, to maximise the operational effectiveness whilst minimising the negative impacts on patient safety, access, and hospital performance.

It is hoped this tool, with the right bed-based capacity data, when combined with local data, will allow NHS and social care organisations to determine the necessary bed requirements. Given anticipated demand and associated operational assumptions, the capacity requirements by different type of beds based on requirements can be specified using this tool.

Case Study:

In 2019 CF used this tool in Guernsey to ensure that the new hospital will be correctly sized, for the Barking, Havering and Redbridge University NHS Trust to reconfigure services to optimise current capacity across two sites and at Whipp’s Cross Hospital where CF assisted in the design of the hospital to ensure it met future capacity requirements.

Additionally, CF combined the features within the CF Foresight and Capacity tools at the start of the pandemic in 2020 to support system-wide modelling of demand and capacity in the five STPs of London, 32 LAs and 9 community providers. Carnall Farrar used historical data from HES APC, A&E and OP alongside COVID-19 sitreps, to develop browser-based software that enabled over 50 NHS users to:

• Allow NHS organisations to extend their current capacity through re-configuration and productivity improvements (CF Capacity)

• Allow NHS organisation to create the optimal configuration of capacity given the constraints of workforce and clinical effectiveness (CF Capacity).

• Predict future activity (CF Foresight)

• Quantify the impact of plans on future occupancy (CF Foresight)

• Develop plans to change activity over a selected period of time (CF Foresight)

• Track activity against baseline to assess real-time efficacy of the new plan. (CF Foresight)

• Identify where and when demand will exceed capacity (new system level features)

• Provide forecasts on the likely demand for different discharge pathways to community and social care providers (new system level features)

Since the completion of this work in May 2020, the team have observed continued engagement with the tool. There were approximately 800 total interactions up until September 2020 at which point CF could no longer track users as this work was transferred into the NHSE foundry tooling. Using this tool, several key insights were uncovered:

An evolution of this model has been used for NHS Nottinghamshire CCG (2020), Hampshire Hospitals NHS Foundation Trust (2021), North West London ICB (2022) and North Central London ICB (2022). In these projects HES and ECDS data was used to create deprivation heat maps to visualise the characteristics of the population and note if there were any pockets of areas with high deprivation/ high elderly population/ high proportion of black, Asian and minority ethnicity (BAME). This was linked to the corresponding patient flow to identify mismatched access to care and capacity constraints.

Data required:

A five-year extract of the following data sets:

- HES APC

- ECDS

- Diagnostic Imaging Dataset (DIDs)

Why that data is required?

This tool predicts up to 5 years into the future and relies on historical activity data to predict the trend and changes in activity over and above that expected from demographic changes. Five years of historic data is the minimum amount of data CF requires to capture longer term trends. Activity is categorised by point of delivery (outpatient, inpatient, emergency department), age, and healthcare resource group (HRG) code (where possible). This activity data is then mapped to capacity within the hospital. In order to capture the value from the capacity available, CF model scenarios that improve efficiency or reconfigure services. The outputs from the reconfiguration analysis will feed into a separate model, which predicts the effect of different service configurations on finance, workforce, estates, capital, and finance. This requires row level data including clinical codes. Access to mental health datasets should allow CF to analyse the acute patient pathways for mental health service users, and enable a better understanding of the clinical needs now and in the future.

3) CF Benchmarks:

Purpose:

To provide a set of automated reports that allow for a rapid diagnostic of Integrated Care Boards (ICBs)/CCGs/places/local authorities. An automated set of reports that benchmarks CCGs across hospital demand, projected demand, life expectancy, deprivation, hospital performance, Quality and Outcomes Framework (QOF), expenditure, workforce, and populations segmentation. This product allows for a rapid diagnostic of a geographic area, freeing up time to focus on improvement rather than number analysis.

The report topics that are included are:

- Population Segmentation

- Drivers of the deficit

- Inpatient activity

- A&E performance

- Outpatient activity

Case Study:

CF has combined the HES data, the Secondary Users Services (SUS) data and the ECDS data into a single aggregated data pipeline with an internally facing browser interface for CF consultants to use on NHSE projects. This allowed both commissioners and providers to assess performance across the system and see trends in their key activity and quality metrics against their compare performance to peers as well as understand the scale of opportunity to improve performance. Over the past year CF have used this tool to yield benefits in the following areas:

Hampshire and Isle of Wight ICB:

CF supported the elective recovery of Hampshire and Isle of Wight ICB in 2021. CF developed a demand and capacity model to support future planning and recovery. Additionally, CF created four speciality business cases and a medium-term plan, which were signed off and approved by the Planned Care Board, starting the process to establish specialty elective hubs and pathway changes across the system.

The work produced a series of deliverables that support the elective recovery of the ICB:

• Comprehensive demand and capacity model that allowed an understanding of the gaps in theatres and beds across the system and the future waiting list challenge for each trust

• Four specialty business cases, approved by the Planned Care Board, that set out clear next steps for the specialties and an approach to hub working that could tackle the longest waiters

• Holistic medium-term (1-3 years) plan that set out a clear ambition and necessary enablers that would allow the delivery of elective care across the ICB.

CF also supported the successful bid for the ICB to receive £10m in funding as an elective accelerator system and the submission of an elective recovery planning submission to NHS England.

Data required:

- HES APC

- ECDS

- HES A&E (for historical data)

- HES OP

- Community Services Dataset (CSDS)

- DIDs

- Mental Health datasets

Why that data is required?

CF will use these datasets to enable system financial leadership and regulators to understand the strategic financial challenge of a local area and benchmark against national peers. Mental health data is required to enable clients to monitor performance against internal targets and benchmark against national peers whilst the bridge file is required to support planning for mental health patients based on the benchmarked opportunities. The HES and Mental health data are required for benchmarking inpatient activity, outpatient activity, A&E performance, and populations segmentation. Five years of data is required as time-series analysis to assess trends in performance, expenditure, utilisation, demand, seasonal patterns in utilisation as well as directional trends in performance.

The data is required at the patient level as CF’s benchmarking uses national data at the patient level to create explanatory models for each report. These explanatory models are required to compare the performance at the regional, local, site and specialty based on time of day and patient movements within the healthcare system e.g. Quantifying the differential impact across sites that the number of people in an emergency department has on the probability of a patient breaching the 4 hour target.

There is a desire to link patient level data with CSDS and DIDs, leaving it pseudonymised, to make it more actionable and to understand variations in slightly defined groups, which clearly consist of suppressed small numbers. For high-risk and high-cost patients, the ability to link data allows for a more pathway-centric view.

As a secondary uses data set, Community Services Data Set (CSDS) re-uses clinical and operational data for purposes other than direct patient care. CSDS sets out national definitions for the extraction of data about children and adults. These activities could take place in settings such as health centres, Sure Start centres, day care facilities, schools or community centres, mobile facilities, or a patient's own home. As such the scope of this dataset is far-reaching and includes a large proportion of the population of England, for example in September 2022 alone, there were 1,398,795 referrals received relating to 1,030,395 persons needing care. CF have therefore minimised the data requested from the CSDS dataset to the least amount required; data is minimised to 5 historic years only and the number of fields requested have been minimised so that only those necessary to perform the analysis detailed in this Agreement have been requested.

NEW TOOLS AND OBJECTIVES:

4) CF Integrated Care Explorer (ICE):

Purpose:

The Integrated Care Explorer (ICE) is a web-based analytics tool that provides ICBs a holistic view of the relative current position on the integration of their services compared to other ICBs, across physical and mental health, community and hospital-based care, and health and social care. ICE supports the development of ICBs by helping them to understand their current position and support identifying focus areas to improve integration across different service areas.

The ICE incorporates the linkage of community data sets with acute data and mental health data. This tool uses aggregated HES data to provide a useful understanding of the place and interplay of providers needed to be able to chart patient journeys across community, mental health, and acute services with primary care to follow.

The aim is to adjust ICE to look at local authorities with Lower Layer Super Output Areas (LSOA) mapping. Given the fluidity of geographic boundaries across ICB places and neighbourhoods from an NHS and local authority perspective, there is a need to customise the geographic definition of a unit, which at various levels would not be consistent. To be able to cut the data at various desired levels consistently, very granular data will be needed, down to the record level by LSOA, so that it can be cut and re-aggregated into the view that would be most meaningful for our clients. The resulting display would be to aggregate data with a small number of suppressions. The analysis would require drilling down and reconstructing as well as building up from the lowest level. It is important that age banding and health conditions as well as ethnicity be included along with indicators of public health such as indices of multiple deprivation (IMD) to fully normalise relevant comparisons.

Case Study:

CF released a free version of this tool in February 2022 to all 42 integrated care boards, which has been used by North Central London ICB, Staffordshire and Stoke on Trent, and Bristol, North Somerset, and Gloucestershire ICB, while the full paid version has been deployed to Sussex Health and Care ICB. (https://ics.cfdata.io/) where it is being used to address inequalities in population outcomes and evaluate initiatives to improve population health.

Data required:

- HES APC

- ECDS

- CSDS

Why that data is required?

CF use HES APC data to create twenty-four selected integration metrics within physical and mental health, community and hospital-based care, health and social care chasms and ICB, locality breakdowns. CF are also working on implementing neighbourhood breakdown to provide better visibility in more granular level to ICBs.

The list of data required has been expanded slightly due to client requests to drill down into bits of data with more granularity. Based on feedback, there is a desire to expand upon the twenty-four selected integration metrics for further exploration and to allow for deeper analysis and the display of additional measures without patient-level linkage.

Lawful basis

The lawful bases for processing this data under UK GDPR is as follows:

• Article 6(1)(f) – it is necessary for the legitimate interests in being able to provide tools and services that will benefit healthcare organisations

• Article 9(2)(j) – it is necessary for reasons that are in the public interest in the area of public health. CF provides tools and services to public healthcare organisations that help them to monitor and improve the standards and quality of care that they offer. The processing is designed to benefit patients' and society as a whole, through facilitating better healthcare in the UK. Processing is necessary for archiving purposes in the public interest, scientific or historical research purposes or statistical purposes in accordance with Article 89(1) based on Union or Member State law which shall be proportionate to the aim pursued, respect the right to data protection and provide for suitable and specific measures to safeguard the fundamental rights and the interests of the data subject.

To determine the lawfulness of processing the data for these legitimate interests, Carnall Farrar has undertaken a Legitimate Interests Assessment (LIA) and determined that:

i. The processing is necessary for the purpose:

The processing of patient data is required to provide accurate analysis of patient pathways, outcomes and performance. Aggregate data does not allow the patient level predictions and evaluations required to perform the detailed analysis and modelling required for:

CF Foresight (1): Predicting patient admission and discharge data, modelling patient level intervention

CF Capacity (2): Mapping individual patients to activity groups, identifying opportunities within care pathways

CF Benchmarking (3): Creating patient segmentation groups, modelling A&E performance, identifying financial opportunities for clinical pathways

CF Integrated Care Explorer (ICE) (4): Supporting Integrated Care Boards (ICBs), identifying focus areas to improve integration across different services, providing ICBs a tool for ongoing self-assessment

ii. The processing is proportionate to the purpose:

The processing of this data will relate solely to the improvement of the health and social care system in England and Wales through providing detailed recommendations and initiatives that aggregate data cannot provide due to the unconnected nature of the data-sets.

The negative impact on individual patients is minimal and CF predicts that patients will benefit from the enhanced service provided by the tools and analysis this data processing produces. This data processing will not identify individuals and the output of this processing will not lead to data-sets that can be used to identify individuals.

iii. The purpose cannot be achieved by processing the data in another more obvious or less intrusive way:

The correlations between behaviours at the level of the individual patient are lost when using aggregate data. These correlations are crucial for capturing the true impact of initiatives and identifying the underlying causes for health system under-performance. Summary statistics mask these relationships and can lead to biased analysis especially when modelling system performance across multiple points of delivery.

iv. The interests of the individual data subjects do not override the legitimate interest:

Carnall Farrar has considered that the data is health data, including data about children or other vulnerable people, which the data subjects are likely to consider particularly private and that some individuals would feel uncomfortable about the processing of their health data outside of the NHS. However, the data sets are pseudonymised and therefore, the possible impacts of the processing will be minimal as Carnall Farrar is not able to de-pseudonymise the data nor will Carnall Farrar attempt to identify patients using any means. Carnall Farrar has put in place policy safeguards to ensure the security and privacy of patient records and limit the impact on patients to positive enhancements of care.

Carnall Farrar believes that the above provides sufficient legitimate interests for lawful processing of the data requested under this Agreement.

Carnall Farrar is the sole Data Controller for the purposes of this Agreement and Carnall Farrar will be directly processing the data. Amazon Web Services (AWS) is a Data Processor for Carnall Farrar. Data processing and storage will take place within Carnall Farrar's secure cloud platform which is based on an AWS UK environment. The servers that store and process the data under this Agreement will be within UK sovereignty (London). The data under this Agreement will be solely used for the purposes stated above and only substantive employees of Carnall Farrar will have access to this data. No employee of AWS will access this data.

Benefits to the Health and Social Care System:

CF will support access of the data to NHS clients, enabling more effective use of the data, validation of data through feedback and, crucially, supporting more effective integration of data. The analytical products that CF builds will help NHS clients to make better decisions. A crucial component of the analytical work with NHS clients is to ensure a legacy of embedded analytical capability. CF aims to improve the flow of data across the NHS, closing the gap between action and feedback. This will help reduce data latency and improve data quality, two key components to effective use of data to create a health system that learns from every patient.

The data disseminated under this Agreement will only be used to provide services to NHS organisations within England and Wales. For CF’s non-NHS clients, only publicly available data is used, and the data is stored in a different physical location within CF's data warehouse. The data provided under this Agreement will only be used for CF’s NHS Clients and will not be shared between NHS and non-NHS projects/organisations.

Carnall Farrar (CF) is a commercial organisation. However, the data are not used for commercial purposes such as sales targeting or commercial insurance.

CF is committed to improving healthcare in the UK and is commissioned by a number of different purchasers and providers of healthcare from NHS organisations to solve pre-defined structural, organisational, or operational issues. Part of the service CF offers is the ability to perform detailed analysis using healthcare data to provide insights into the drivers of key problems to enable evidence-based decision making for NHS leadership.

CF will use the data supplied by NHS Digital to enhance the analytical services CF provide to NHS clients, by developing several additional analytical outputs as described in the purpose statements.

Commercial arrangements are put in place between CF and the client organisation. Only CF primary users will have access to NHS Digital data. Tools created for NHS customers will only contain aggregated data (with small numbers suppressed).

CF works on multiple projects at any one time for several different national, regional, and local organisations across the NHS. Therefore, it is not possible to provide full details of all outputs, as these are highly specific to the requirements for each client. CF will only share aggregated analysis with its NHS clients in presentations, reports, or cloud-based visualisation tools, in full compliance with the small numbers guidance. In general, all outputs can be grouped into one of several categories detailed below:

• CF provides detailed reports to clients, which contain data in table format containing aggregated, non-patient identifiable data with small numbers suppressed in line with the HES Analysis Guide;

• These reports may also contain visualisations created using data based on aggregated, non-patient identifiable results of quantitative analysis;

• CF presents the aggregated, non-patient identifiable results with small numbers suppressed, in the form of tables and visualisations, at meetings with NHS client stakeholders;

• CF provides interactive visualisations to NHS clients in the form of cloud-based tools; the software tools that CF builds will allow some analysis to be done on aggregated data (with small numbers suppressed), in house by the providers/commissioners. CF will not allow the providers and commissioners to directly access the patient level data.

• Benchmarking applies across all services. National benchmarks will be derived from the national data. The outputs from queries against these data will be transferred to visualisation software for communication to CF clients.

All outputs will only contain results in highly aggregated format and as statistical summaries and measures of association. Small numbers will be suppressed. Record level information will not be released to any third party.

Examples of the specific tool outputs are set out below:

1) CF Foresight

Output: A browser-based tool that enables providers and commissioners to view predictions of waitlists, future attendances, admissions, discharges, and occupancy as well as model the impact of interventions to improve performance and patient flow.

Timelines: The second version of this tool has been in usage since September 2021. The latest version of this tool is being modified to support system control centres required from the 1st of December 2022 in every ICB. This is being piloted at 3 Integrated Care Boards and expected to be fully functional by January 2023.

2) CF Capacity

Output: A Python (visualisation software) and Excel based tool which visualises and models the impact of reconfiguration and efficiency improvements.

Timelines: The basic Excel version has been used since 2020 and during 2022 CF have developed an additional automated python-based mapping tool that automates the approach. This has been trialled at two clients during 2022 and is currently live at one.

3) CF Benchmark

Population segmentation

Output: A browser based interactive explorer of the population segments and an automated PowerPoint presentation.

Timelines: This tool is used internally by CF staff members to provide insights and benchmarking to all of CF's NHS clients.

4) CF Integrated Care Explorer (ICE)

Output: A web-based analytics tool that provides a holistic view of the relative current position on the integration of ICB services.

Timelines: The full version of this tool is used by Sussex Health and Care ICB, and a limited free version has been used by North Central London ICB, Staffordshire and Stoke on Trent, and Bristol, North Somerset and Gloucestershire ICB, helping them to understand their current position and support identifying focus areas to improve integration across different services.

All outputs will only contain results in highly aggregated format and as statistical summaries and measures of association. Small numbers will be suppressed in line with the HES Analysis Guide. Record level information will not be released to any third party.

Below are some examples of where outputs produced using the data under this agreement has yielded benefits for health and social care:

In response to COVID-19, Carnall Farrar pivoted the CF Foresight + CF Capacity tools described above to support the NHS in their response to the pandemic. Carnall Farrar combined the features of the tools at the start of the pandemic to support system-wide modelling of demand and capacity in the five STPs of London, 32 Local Authorities and 9 community providers.

Since the completion of this work in May 2020, the CF team have observed continued engagement with the tool. Particular interest has been for community users in understanding how different COVID-19 acute admissions scenarios impact community demand over time. Using this tool, a number of key insights were uncovered:

• Each of the five London STPs were able to model the different COVID-19 scenarios to understand the number of acute beds, deaths and discharges they could expect over the next 4-18 months enabling better planning of resources and improved management of clinic spaces for patients within these areas.

The demand and capacity modelling highlighted the critical challenge in the elective pathway and led to prioritisation of action in this area. Integration between acute and community models allowed the user to understand the burden of acute discharges on community demand over time. This work was awarded the “Best Healthcare Analytics Project for the NHS” in the HSJ partnership awards 2021.

CF Capacity:

Nottingham and Nottinghamshire ICB:

The HES and ECDS data was used to create deprivation heat maps to visualise the characteristics of the population and note if there were any pockets of areas with high deprivation/ high elderly population/ high proportion of black, Asian and minority ethnic (BAME). This was linked to the corresponding activity rates in hospital to identify mismatched access to care.

This helped to inform the impact assessment of moving hospital services between sites on at-risk groups to ensure there was equitable access to services across the area.

CF Benchmark - Inpatient Activity, A&E performance, and Outpatient Activity:

Carnall Farrar combined the HES data, the SUS data and the ECDS data into a single aggregated data pipeline with an internally facing browser interface for CF consultants to use on NHSE projects. This allowed both commissioners and providers to assess performance across the system and see trends in their key activity and quality metrics against their compare performance to peers as well as understand the scale of opportunity to improve performance. Over the last year Carnall Farrar have used this tool to yield benefits in the following area:

Hampshire and Isle of Wight ICB:

CF supported the elective recovery of Hampshire and Isle of Wight ICB post-COVID. CF developed a demand and capacity model to support future planning and recovery. Additionally, CF created four speciality business cases and a medium-term (1-3 years) plan, which were signed off and approved by the Planned Care Board, starting the process to establish specialty elective hubs and pathway changes across the system.

The work produced a series of deliverables that support the elective recovery of the ICB:

• Comprehensive demand and capacity model that allowed an understanding of the gaps in theatres and beds across the system and the future waiting list challenge for each trust

• Four specialty business cases, approved by the Planned Care Board, that set out clear next steps for the specialties and an approach to hub working that could tackle the longest waiters

• Holistic medium-term plan that set out a clear ambition and necessary enablers that would allow the delivery of elective care across the ICB.

CF also supported the successful bid for the ICB to receive £10m in funding as an elective accelerator system and the submission of an elective recovery planning submission to NHS England.

Carnall Farrar Ltd (CF) is a management consultancy and analytics company whose mission is to improve healthcare. CF works with a number of purchasers and providers across NHS organisations in England, Wales and Scotland, including NHS Trusts, Foundation Trusts, Clinical Commissioning Groups and Commissioning Support Units. CF has strong relationships with the Department of Health, NHS England, NHS Improvement and Public Health England. These organisations commission CF to work on projects procured both through direct commissioning agreements, and competitive procurement processes as part of access to over six public sector specific frameworks.

CF’s client base consists primarily of NHS organisations. As of October 2021, CF had active contracts with the following NHS clients:

• Barking, Havering and Redbridge University NHS Trust

• Lancashire and South Cumbria NHS STP

• Bedford, Luton and Milton Keynes NHS ICS

• Harrogate and District NHS Foundation Trust

• Central London Community Healthcare NHS Trust

• Frimley Health and Care ICS

• Hampshire and Isle of Wight ICS

• Nottingham and Nottinghamshire ICS

• North Central London STP

Over the past few years, CF has worked with over 15 health and social care systems in England, to support health system strategy and strengthening, service transformation, financial sustainability, and integrated care delivery. Over the past five years CF has handled large volumes of data which has been obtained directly from NHS clients. CF has been successful in using this data to provide meaningful analytics which have positively impacted NHS organisations. Unfortunately, the data available directly from each NHS organisation is aggregate data and does not include diagnostic (clinical) codes. The results, although useful, are limited.

Carnall Farrar is requesting data from NHS Digital to expand the products currently on offer for NHS Clients. The record level data disseminated under this Agreement, although pseudonymised, is richer and more accurate than the data held by individual NHS organisations. Using the data under this Agreement, CF will provide more in-depth tools and products for NHS clients, therefore producing more accurate insight into the areas of the NHS requiring improvement and how these improvements can be made.

CF is requesting NHS Digital data in order provide additional benefits to NHS clients by expanding the capabilities of existing products and reducing costs to the NHS. The three products that the data under this Agreement will be used for are:

- CF Foresight

- CF Capacity

- CF Benchmarks

1) CF Foresight:

Purpose:

This tool predicts demand and patient flow through a hospital over the short to medium term (1-4 months). Hospitals can identify “pinch” points in upcoming demand compared to their current capacity and model the impact of a variety of interventions on demand and flow.

Current users:

A basic version of the tool is currently used by Northampton General Hospital NHS Trust to model the impact of increasing discharge rates within the Trust. CF also works with NHS Improvement and NHS England’s Data and Analytical Product team, to co-design the next version of the tool in order to provide a national overview of demand and flow.

Data required:

A five year extract of the following data sets:

- Mental Health Services Data Set

- Mental Health Minimum Data Set

- HES APC

- HES CC

- HES A&E

- ECDS

Why that data is required?

The tool incorporates machine learning model to predict future performance. The more years of data that are available for training the better the accuracy of the model. Five years of data is considered sufficient to account for annual variation. The HES APC, CC A&E and the ECDS data are required to train patient level models for predicting attendance, admission, four-hour breaches and discharges within the hospital. The Mental Health Services Data Set and the Mental Health Minimum Data Set are required to model the impact of mental health on A&E performance over time. The row level data is also required to model the specific interventions that trusts plan on using to improve performance. These interventions often require clinical coding to identify the impacted patients e.g. increasing discharge rates in frail elderly population within orthopaedics. CF requires the latest available data-sets to ensure that NHS commissioners and providers, who will receive CF analytics products, can make effective decisions based on the most up-to-date information.

2) CF Capacity:

Purpose:

This tool predicts in which year demand in an acute NHS organisation will exceed capacity based on demographic and non-demographic growth. It allows a system to model a variety of clinical configurations across sites, to maximise the operational effectiveness whilst minimising the negative impacts on patient safety, access and hospital performance.

Current users:

In 2019 CF used this tool on three projects; in Guernsey to ensure that the new hospital will be correctly sized, for the Barking, Havering and Redbridge University NHS Trust to reconfigure services to optimise current capacity across two sites and at Whipp’s Cross Hospital where CF assisted in the design of the hospital to ensure it met future capacity requirements.

Data required:

A five-year extract of the following data sets:

- Mental Health Services Data Set

- Mental Health Minimum Data Set

- HES APC

- HES CC

- HES A&E

- ECDS

Why that data is required?

This tool predicts up to 20 years into the future and relies on historical activity data to predict the trend and changes in activity over and above that expected from demographic changes. Five years of historic data is the minimum amount of data CF requires to capture longer term trends. Activity is categorised by point of delivery (outpatient, inpatient, emergency department), age, and HRG code (where possible). This activity data is then mapped to capacity within the hospital. In order to capture the value from the capacity available, CF model scenarios that improve efficiency or reconfigure services. The outputs from the reconfiguration analysis will feed into a separate model, which predicts the effect of different service configurations on finance, workforce, estates, capital and finance. This requires row level data including clinical codes. Access to mental health data-sets will allow CF to analyse the acute patient pathways for mental health service users, and enable a better understanding of the clinical needs now and in the future.

3) CF Benchmarks :

Purpose:

To provide a set of automated reports that allow for a rapid diagnostic of an NHS organisation. An automated set of reports that benchmarks CCGs across hospital demand, projected demand, life expectancy, deprivation, hospital performance, QOF, expenditure, workforce and populations segmentation. This product allows for a rapid diagnostic of a geographic area, freeing up time to focus on improvement rather than number analysis.

The report topics that are included are:

- Population Segmentation

- Mental Health Toolkit

- Drivers of the deficit

- Inpatient activity

- A&E performance

- Outpatient activity

Current users:

In 2019 CF employed an alpha version of this product across 6 NHS organisations:

- Lancashire and South Cumbria NHS STP

- Bedford, Luton and Milton Keynes NHS ICS

- Harrogate and District NHS Foundation Trust

- Barking, Havering and Redbridge University NHS Trust

- Newham CCG

- Tower Hamlets CCG

Data required:

- SUS PbR Spells

- SUS PbR Episodes

- SUS PbR A&E

- SUS PbR OP

- Mental Health Services Data Set

- Mental Health Minimum Data Set

- HES APC

- HES CC

- HES A&E

- HES OP

Why that data is required?

Payment by Results (PbR) is required for the drivers of the deficit analysis. CF will use these datasets to enable system financial leadership and regulators to understand the strategic financial challenge of a local area and benchmark against national peers. Mental health data is required to enable clients to monitor performance against internal targets and benchmark against national peers whilst the bridge file is required to support planning for mental health patients based on the benchmarked opportunities. The HES and Mental health data are required for benchmarking inpatient activity, outpatient activity, A&E performance and populations segmentation. Five years of data is required as time-series analysis to assess trends in performance, expenditure, utilisation, demand, seasonal patterns in utilisation as well as directional trends in performance.

The data is required at the patient level as CF’s benchmarking uses national data at the patient level to create explanatory models for each report. These explanatory models are required to compare the performance at the regional, local, site and specialty based on time of day and patient movements within the healthcare system e.g. Quantifying the differential impact across sites that the number of people in an ED department has on the probability of a patient breaching the 4 hour target.

Lawful basis

The lawful bases for processing this data under GDPR is as follows:

• Article 6(1)(f) – it is necessary for the legitimate interests in being able to provide tools and services that will benefit healthcare organisations

• Article 9(2)(j) – it is necessary for reasons that are in the public interest in the area of public health. CF provides tools and services to public healthcare organisations that help them to monitor and improve the standards and quality of care that they offer. The processing is designed to benefit patients' and society as a whole, through facilitating better healthcare in the UK.

To determine the lawfulness of processing the data for these legitimate interests, Carnall Farrar has undertaken a Legitimate Interests Assessment (LIA) and determined that:

i. The processing is necessary for the purpose:

The processing of patient data is required to provide accurate analysis of patient pathways, outcomes and performance. Aggregate data does not allow the patient level predictions and evaluations required to perform the detailed analysis and modelling required for:

CF Foresight (1) : Predicting patient admission and discharge data, modelling patient level intervention

CF Capacity (2) : Mapping individual patients to activity groups, identifying opportunities within care pathways

CF Benchmarking (3) : Creating patient segmentation groups, modelling A&E performance, identifying financial opportunities for clinical pathways

ii. The processing is proportionate to the purpose:

The processing of this data will relate solely to the improvement of the health and social care system in England and Wales through providing detailed recommendations and initiatives that aggregate data cannot provide due to the unconnected nature of the data-sets.

The negative impact on individual patients is minimal and CF predicts that patients will benefit from the enhanced service provided by the tools and analysis this data processing produces. This data processing will not identify individuals and the output of this processing will not lead to data-sets that can be used to identify individuals.

iii. The purpose cannot be achieved by processing the data in another more obvious or less intrusive way:

The correlations between behaviours at the level of the individual patient are lost when using aggregate data. These correlations are crucial for capturing the true impact of initiatives and identifying the underlying causes for health system under-performance. Summary statistics mask these relationships and can lead to biased analysis especially when modelling system performance across multiple points of delivery.

iv. The interests of the individual data subjects do not override the legitimate interest:

Carnall Farrar has considered that the data is health data, including data about children or other vulnerable people, which the data subjects are likely to consider particularly private and that some individuals would feel uncomfortable about the processing of their health data outside of the NHS. However, the data sets are pseudonymised and therefore, the possible impacts of the processing will be minimal as Carnall Farrar is not able to de-pseudonymise the data nor will Carnall Farrar attempt to identify patients using any means. Carnall Farrar has put in place policy safeguards to ensure the security and privacy of patient records and limit the impact on patients to positive enhancements of care.

Carnall Farrar believes that the above provides sufficient legitimate interests for lawful processing of the data requested under this Agreement. Carnall Farrar has determined that there is unlikely to be any moral or ethical issue arising from the processing of this data as the data requested is pseudonymised.

Carnall Farrar is the sole Data Controller for the purposes of this Agreement and Carnall Farrar will be directly processing the data. Amazon Web Services (AWS) is a Data Processor for Carnall Farrar. Data processing and storage will take place within Carnall Farrar's secure cloud platform which is based on an AWS UK environment. The servers that store and process the data under this Agreement will be within UK sovereignty (London). The data under this Agreement will be solely used for the purposes stated above and only substantive employees of Carnall Farrar will have access to this data. No employee of AWS will access this data.

Benefits to the Health and Social Care System:

CF will support access of the data to NHS clients, enabling more effective use of the data, validation of data through feedback and, crucially, supporting more effective integration of data. The analytical products that CF builds will help NHS clients to make better decisions. A crucial component of the analytical work with NHS clients is to ensure a legacy of embedded analytical capability. CF aims to improve the flow of data across the NHS, closing the gap between action and feedback. This will help reduce data latency and improve data quality, two key components to effective use of data to create a health system that learns from every patient.

The data disseminated under this Agreement will only be used to provide services to NHS organisations within England and Wales. CF does not currently work with any non-NHS organisations however, previously CF has worked with non-NHS organisations such as charities (Healthy living UK), think tanks (IPPR) and life sciences projects. For CF’s non-NHS clients, only publicly available data is used, and the data is stored in a different physical location within CF's data warehouse. The data provided under this Agreement will only be used for CF’s NHS Clients and will not be shared between NHS and non-NHS projects/organisations.

CF works on multiple projects at any one time for a number of different national, regional and local organisations across the NHS. Therefore, it is not possible to provide full details of all outputs, as these are highly specific to the requirements for each client. CF will only share aggregated analysis with its NHS clients in presentations, reports or cloud-based visualisation tools, in full compliance with the small numbers guidance. In general, all outputs can be grouped into one of several categories detailed below:

• CF provides detailed reports to clients, which contain data in table format containing aggregated, non-patient identifiable data with small numbers suppressed in line with the HES Analysis Guide;

• These reports may also contain visualisations created using data based on aggregated, non-patient identifiable results of quantitative analysis;

• CF presents the aggregated, non-patient identifiable results with small numbers suppressed, in the form of tables and visualisations, at meetings with NHS client stakeholders;

• CF provides interactive visualisations to NHS clients in the form of cloud-based tools; the software tools that CF builds will allow some analysis to be done on aggregated data (with small numbers suppressed), in house by the providers/commissioners. CF will not allow the providers and commissioners to directly access the patient level data.

• Benchmarking applies across all services. National benchmarks will be derived from the national data. The outputs from queries against these data will be transferred to excel, R, Python or visualisation software for communication to CF clients.

All outputs will only contain results in highly aggregated format and as statistical summaries and measures of association. Small numbers will be suppressed. Record level information will not be released to any third party.

Examples of the specific tool outputs are set out below:

1) CF Foresight

Output : A browser based tool that enables providers and commissioners to view predictions of future attendances, admissions, discharges and occupancy as well as model the impact of interventions to improve performance

Timelines: An alpha version of this product has been available for the past year and CF are co-designing a new version with Northampton and NHS England and NHS Improvement for release in Spring 2020.

2) CF Capacity

Output : An Excel based tool which visualises and models the impact of reconfiguration and efficiency improvements.

Timelines: CF has this tool deployed at two sites currently and are releasing the advanced version of the tool in Spring 2020.

3) CF Benchmark

Population segmentation

Output: A browser based interactive explorer of the population segments

Timelines: v1 is available now but only for one geographic area (Kent and Medway)

All other reports:

Output:

An automated PowerPoint presentation accessed via the browser

Timelines:

An aggregated version has been used for the past year.

All outputs will only contain results in highly aggregated format and as statistical summaries and measures of association. Small numbers will be suppressed in line with the HES Analysis Guide. Record level information will not be released to any third party.

CF Foresight + CF Capacity:

In response to COVID-19, Carnall Farrar provided the tools described above to support the NHS in their response to the pandemic using the data obtained through NHS Digital. Carnall Farrar combined the features within the CF Foresight and Capacity tools at the start of the pandemic to support system-wide modelling of demand and capacity in the five STPs of London, 32 LAs and 9 community providers. Carnall Farrar used historical data from HES APC, A&E and OP alongside COVID-19 situation reports, to develop browser based software that enabled over 50 NHS users to:

• Allow NHS organisations to extend their current capacity through re-configuration and productivity improvements (CF Capacity)

• Allow NHS organisation to create the optimal configuration of capacity given the constraints of workforce and clinical effectiveness (CF Capacity).

• Predict future activity (CF Foresight)

• Quantify the impact of plans on future occupancy (CF Foresight)

• Develop plans to change activity over a selected period of time (CF Foresight)

• Track activity against baseline to assess real-time efficacy of the new plan. (CF Foresight)

• Identify where and when demand will exceed capacity (new system level features)

• Provide forecasts on the likely demand for different discharge pathways to community and social care providers (new system level features)

Since the completion of this work in May 2020, the team have observed continued engagement with the tool. There have been 22 unique power users across the five London STPs and ~800 total interactions up until September 2020. Particular interest has been for community users in understanding how different COVID-19 acute admissions scenarios impact community demand over time. Using this tool, a number of key insights were uncovered:

• Each of the five London STPs were able to model the different COVID-19 scenarios to understand the number of acute beds, deaths and discharges they could expect over the next 4-18 months

• The majority of scenarios indicated that acute ICU capacity would not be exceeded. These outputs were shared and discussed in a workshop in early April to key leadership across NHS London, facilitated by NHS Regional Director for London and the Regional Medical Director NHS England & NHS Improvement (London).

• The demand and capacity modelling highlighted the critical challenge in the elective pathway and led to prioritisation of action in this area.

• Integration between acute and community models allowed the user to understand the burden of acute discharges on community demand over time

This work was awarded the “Best Healthcare Analytics Project for the NHS” in the HSJ partnership awards 2021.

CF Capacity:

Nottingham and Nottinghamshire ICS

The HES and ECDS data was used to create deprivation heat maps to visualise the characteristics of the population and note if there were any pockets of areas with high deprivation/ high elderly population/ high proportion of BAME. This was linked to the corresponding activity rates in hospital to identify mismatched access to care.

This helped to inform the impact assessment of moving hospital services between sites on at-risk groups to ensure there was equitable access to services across the area.

Nottingham has a complex health and deprivation profile, and this has caused areas where there is a mismatch in access to care. CF carried out advanced analysis of data from HES and ECDS to identify and map areas with high deprivation, older populations, and high proportions of BAME communities. This was compared to corresponding hospital activity rates to gain insights into relationships with access to care.

The integrated impact assessment (IIA) directly affected the decision making for the reconfiguration of services. The IIA allowed for an assessment of the population impacted. and mapped the split of the population by characteristic and LSOA. This allowed for an understanding of the overall impact of the reconfiguration on these populations in terms health outcomes and travel time and provided insight into the impact on chronic disease under different reconfiguration scenarios. Examples of this are mapping the time taken to reach a maternity ward depending on location, and time taken for stroke travel times by transport time/method.

Examples of the direct benefits yielded from this work are:

- An on-site shuttle bus to transport patients and staff for those deprived areas that were disproportionately impacted by the reconfiguration

- More free parking for patients and staff

- The hyper-acute stroke service being co-located with other emergency specialties such as neurosurgery and mechanical thrombectomy.

CF Benchmark - Inpatient Activity, A&E performance and Outpatient Activity:

Carnall Farrar combined the HES data, the SUS data and the ECDS data into a single aggregated data pipeline with a internally facing browser interface for CF consultants to use on NHSE projects. This allowed both commissioners and providers to assess performance across the system and see trends in their key activity and quality metrics against their compare performance to peers as well as understand the scale of opportunity to improve performance. Over the last year Carnall Farrar have used this tool in to yield benefits in the following area:

Hampshire and Isle of Wight ICS

Carnall Farrar supported the elective recovery of Hampshire and Isle of Wight ICS post-COVID. Carnall Farrar developed a demand and capacity model to support future planning and recovery. Additionally, Carnall Farrar created four speciality business cases and a medium-term plan, which were signed off and approved by the Planned Care Board, starting the process to establish specialty elective hubs and pathway changes across the system.

The work produced a series of deliverables that support the elective recovery of the ICS:

• Comprehensive demand and capacity model that allowed an understanding of the gaps in theatres and beds across the system and the future waiting list challenge for each trust

• Four specialty business cases, approved by the Planned Care Board, that set out clear next steps for the specialties and an approach to hub working that could tackle the longest waiters

• Holistic medium-term plan that set out a clear ambition and necessary enablers that would allow the delivery of elective care across the ICS

Carnall Farrar also supported the successful bid for the ICS to receive £10m in funding as an elective accelerator system and the submission of an elective recovery planning submission to NHS England.

Frimley Health and Care ICS

Carnall Farrar supported the creation of plans for the ICS and leverage the CF Benchmarking tool to quantify and analyse patient flow between and within the ICS to assess the coherence of the planning footprint and ensure that resource was appropriately distributed.

Carnall Farrar Ltd (CF) is a management consultancy and analytics company whose mission is to improve healthcare. CF works with a number of purchasers and providers across NHS organisations in England, Wales and Scotland, including NHS Trusts, Foundation Trusts, Clinical Commissioning Groups and Commissioning Support Units. CF has strong relationships with the Department of Health, NHS England, NHS Improvement and Public Health England. These organisations commission CF to work on projects procured both through direct commissioning agreements, and competitive procurement processes as part of access to over six public sector specific frameworks.

CF’s client base consists primarily of NHS organisations. As of October 2021, CF had active contracts with the following NHS clients:

• Barking, Havering and Redbridge University NHS Trust

• Lancashire and South Cumbria NHS STP

• Bedford, Luton and Milton Keynes NHS ICS

• Harrogate and District NHS Foundation Trust

• Central London Community Healthcare NHS Trust

• Frimley Health and Care ICS

• Hampshire and Isle of Wight ICS

• Nottingham and Nottinghamshire ICS

• North Central London STP

Over the past few years, CF has worked with over 15 health and social care systems in England, to support health system strategy and strengthening, service transformation, financial sustainability, and integrated care delivery. Over the past five years CF has handled large volumes of data which has been obtained directly from NHS clients. CF has been successful in using this data to provide meaningful analytics which have positively impacted NHS organisations. Unfortunately, the data available directly from each NHS organisation is aggregate data and does not include diagnostic (clinical) codes. The results, although useful, are limited.

Carnall Farrar is requesting data from NHS Digital to expand the products currently on offer for NHS Clients. The record level data disseminated under this Agreement, although pseudonymised, is richer and more accurate than the data held by individual NHS organisations. Using the data under this Agreement, CF will provide more in-depth tools and products for NHS clients, therefore producing more accurate insight into the areas of the NHS requiring improvement and how these improvements can be made.

CF is requesting NHS Digital data in order provide additional benefits to NHS clients by expanding the capabilities of existing products and reducing costs to the NHS. The three products that the data under this Agreement will be used for are:

- CF Foresight

- CF Capacity

- CF Benchmarks

1) CF Foresight:

Purpose:

This tool predicts demand and patient flow through a hospital over the short to medium term (1-4 months). Hospitals can identify “pinch” points in upcoming demand compared to their current capacity and model the impact of a variety of interventions on demand and flow.

Current users:

A basic version of the tool is currently used by Northampton General Hospital NHS Trust to model the impact of increasing discharge rates within the Trust. CF also works with NHS Improvement and NHS England’s Data and Analytical Product team, to co-design the next version of the tool in order to provide a national overview of demand and flow.

Data required:

A five year extract of the following data sets:

- Mental Health Services Data Set

- Mental Health Minimum Data Set

- HES APC

- HES CC

- HES A&E

- ECDS

Why that data is required?

The tool incorporates machine learning model to predict future performance. The more years of data that are available for training the better the accuracy of the model. Five years of data is considered sufficient to account for annual variation. The HES APC, CC A&E and the ECDS data are required to train patient level models for predicting attendance, admission, four-hour breaches and discharges within the hospital. The Mental Health Services Data Set and the Mental Health Minimum Data Set are required to model the impact of mental health on A&E performance over time. The row level data is also required to model the specific interventions that trusts plan on using to improve performance. These interventions often require clinical coding to identify the impacted patients e.g. increasing discharge rates in frail elderly population within orthopaedics. CF requires the latest available data-sets to ensure that NHS commissioners and providers, who will receive CF analytics products, can make effective decisions based on the most up-to-date information.

2) CF Capacity:

Purpose:

This tool predicts in which year demand in an acute NHS organisation will exceed capacity based on demographic and non-demographic growth. It allows a system to model a variety of clinical configurations across sites, to maximise the operational effectiveness whilst minimising the negative impacts on patient safety, access and hospital performance.

Current users:

In 2019 CF used this tool on three projects; in Guernsey to ensure that the new hospital will be correctly sized, for the Barking, Havering and Redbridge University NHS Trust to reconfigure services to optimise current capacity across two sites and at Whipp’s Cross Hospital where CF assisted in the design of the hospital to ensure it met future capacity requirements.

Data required:

A five-year extract of the following data sets:

- Mental Health Services Data Set

- Mental Health Minimum Data Set

- HES APC

- HES CC

- HES A&E

- ECDS

Why that data is required?

This tool predicts up to 20 years into the future and relies on historical activity data to predict the trend and changes in activity over and above that expected from demographic changes. Five years of historic data is the minimum amount of data CF requires to capture longer term trends. Activity is categorised by point of delivery (outpatient, inpatient, emergency department), age, and HRG code (where possible). This activity data is then mapped to capacity within the hospital. In order to capture the value from the capacity available, CF model scenarios that improve efficiency or reconfigure services. The outputs from the reconfiguration analysis will feed into a separate model, which predicts the effect of different service configurations on finance, workforce, estates, capital and finance. This requires row level data including clinical codes. Access to mental health data-sets will allow CF to analyse the acute patient pathways for mental health service users, and enable a better understanding of the clinical needs now and in the future.

3) CF Benchmarks :

Purpose:

To provide a set of automated reports that allow for a rapid diagnostic of an NHS organisation. An automated set of reports that benchmarks CCGs across hospital demand, projected demand, life expectancy, deprivation, hospital performance, QOF, expenditure, workforce and populations segmentation. This product allows for a rapid diagnostic of a geographic area, freeing up time to focus on improvement rather than number analysis.

The report topics that are included are:

- Population Segmentation

- Mental Health Toolkit

- Drivers of the deficit

- Inpatient activity

- A&E performance

- Outpatient activity

Current users:

In 2019 CF employed an alpha version of this product across 6 NHS organisations:

- Lancashire and South Cumbria NHS STP

- Bedford, Luton and Milton Keynes NHS ICS

- Harrogate and District NHS Foundation Trust

- Barking, Havering and Redbridge University NHS Trust

- Newham CCG

- Tower Hamlets CCG

Data required:

- SUS PbR Spells

- SUS PbR Episodes

- SUS PbR A&E

- SUS PbR OP

- Mental Health Services Data Set

- Mental Health Minimum Data Set

- HES APC

- HES CC

- HES A&E

- HES OP

Why that data is required?

Payment by Results (PbR) is required for the drivers of the deficit analysis. CF will use these datasets to enable system financial leadership and regulators to understand the strategic financial challenge of a local area and benchmark against national peers. Mental health data is required to enable clients to monitor performance against internal targets and benchmark against national peers whilst the bridge file is required to support planning for mental health patients based on the benchmarked opportunities. The HES and Mental health data are required for benchmarking inpatient activity, outpatient activity, A&E performance and populations segmentation. Five years of data is required as time-series analysis to assess trends in performance, expenditure, utilisation, demand, seasonal patterns in utilisation as well as directional trends in performance.

The data is required at the patient level as CF’s benchmarking uses national data at the patient level to create explanatory models for each report. These explanatory models are required to compare the performance at the regional, local, site and specialty based on time of day and patient movements within the healthcare system e.g. Quantifying the differential impact across sites that the number of people in an ED department has on the probability of a patient breaching the 4 hour target.

Lawful basis

The lawful bases for processing this data under GDPR is as follows:

• Article 6(1)(f) – it is necessary for the legitimate interests in being able to provide tools and services that will benefit healthcare organisations

• Article 9(2)(j) – it is necessary for reasons that are in the public interest in the area of public health. CF provides tools and services to public healthcare organisations that help them to monitor and improve the standards and quality of care that they offer. The processing is designed to benefit patients' and society as a whole, through facilitating better healthcare in the UK.

To determine the lawfulness of processing the data for these legitimate interests, Carnall Farrar has undertaken a Legitimate Interests Assessment (LIA) and determined that:

i. The processing is necessary for the purpose:

The processing of patient data is required to provide accurate analysis of patient pathways, outcomes and performance. Aggregate data does not allow the patient level predictions and evaluations required to perform the detailed analysis and modelling required for:

CF Foresight (1) : Predicting patient admission and discharge data, modelling patient level intervention

CF Capacity (2) : Mapping individual patients to activity groups, identifying opportunities within care pathways

CF Benchmarking (3) : Creating patient segmentation groups, modelling A&E performance, identifying financial opportunities for clinical pathways

ii. The processing is proportionate to the purpose:

The processing of this data will relate solely to the improvement of the health and social care system in England and Wales through providing detailed recommendations and initiatives that aggregate data cannot provide due to the unconnected nature of the data-sets.

The negative impact on individual patients is minimal and CF predicts that patients will benefit from the enhanced service provided by the tools and analysis this data processing produces. This data processing will not identify individuals and the output of this processing will not lead to data-sets that can be used to identify individuals.

iii. The purpose cannot be achieved by processing the data in another more obvious or less intrusive way:

The correlations between behaviours at the level of the individual patient are lost when using aggregate data. These correlations are crucial for capturing the true impact of initiatives and identifying the underlying causes for health system under-performance. Summary statistics mask these relationships and can lead to biased analysis especially when modelling system performance across multiple points of delivery.

iv. The interests of the individual data subjects do not override the legitimate interest:

Carnall Farrar has considered that the data is health data, including data about children or other vulnerable people, which the data subjects are likely to consider particularly private and that some individuals would feel uncomfortable about the processing of their health data outside of the NHS. However, the data sets are pseudonymised and therefore, the possible impacts of the processing will be minimal as Carnall Farrar is not able to de-pseudonymise the data nor will Carnall Farrar attempt to identify patients using any means. Carnall Farrar has put in place policy safeguards to ensure the security and privacy of patient records and limit the impact on patients to positive enhancements of care.

Carnall Farrar believes that the above provides sufficient legitimate interests for lawful processing of the data requested under this Agreement. Carnall Farrar has determined that there is unlikely to be any moral or ethical issue arising from the processing of this data as the data requested is pseudonymised.

Carnall Farrar is the sole Data Controller for the purposes of this Agreement and Carnall Farrar will be directly processing the data. Amazon Web Services (AWS) is a Data Processor for Carnall Farrar. Data processing and storage will take place within Carnall Farrar's secure cloud platform which is based on an AWS UK environment. The servers that store and process the data under this Agreement will be within UK sovereignty (London). The data under this Agreement will be solely used for the purposes stated above and only substantive employees of Carnall Farrar will have access to this data. No employee of AWS will access this data.

Benefits to the Health and Social Care System:

CF will support access of the data to NHS clients, enabling more effective use of the data, validation of data through feedback and, crucially, supporting more effective integration of data. The analytical products that CF builds will help NHS clients to make better decisions. A crucial component of the analytical work with NHS clients is to ensure a legacy of embedded analytical capability. CF aims to improve the flow of data across the NHS, closing the gap between action and feedback. This will help reduce data latency and improve data quality, two key components to effective use of data to create a health system that learns from every patient.

The data disseminated under this Agreement will only be used to provide services to NHS organisations within England and Wales. CF does not currently work with any non-NHS organisations however, previously CF has worked with non-NHS organisations such as charities (Healthy living UK), think tanks (IPPR) and life sciences projects. For CF’s non-NHS clients, only publicly available data is used, and the data is stored in a different physical location within CF's data warehouse. The data provided under this Agreement will only be used for CF’s NHS Clients and will not be shared between NHS and non-NHS projects/organisations.

CF works on multiple projects at any one time for a number of different national, regional and local organisations across the NHS. Therefore, it is not possible to provide full details of all outputs, as these are highly specific to the requirements for each client. CF will only share aggregated analysis with its NHS clients in presentations, reports or cloud-based visualisation tools, in full compliance with the small numbers guidance. In general, all outputs can be grouped into one of several categories detailed below:

• CF provides detailed reports to clients, which contain data in table format containing aggregated, non-patient identifiable data with small numbers suppressed in line with the HES Analysis Guide;

• These reports may also contain visualisations created using data based on aggregated, non-patient identifiable results of quantitative analysis;

• CF presents the aggregated, non-patient identifiable results with small numbers suppressed, in the form of tables and visualisations, at meetings with NHS client stakeholders;

• CF provides interactive visualisations to NHS clients in the form of cloud-based tools; the software tools that CF builds will allow some analysis to be done on aggregated data (with small numbers suppressed), in house by the providers/commissioners. CF will not allow the providers and commissioners to directly access the patient level data.

• Benchmarking applies across all services. National benchmarks will be derived from the national data. The outputs from queries against these data will be transferred to excel, R, Python or visualisation software for communication to CF clients.

All outputs will only contain results in highly aggregated format and as statistical summaries and measures of association. Small numbers will be suppressed. Record level information will not be released to any third party.

Examples of the specific tool outputs are set out below:

1) CF Foresight

Output : A browser based tool that enables providers and commissioners to view predictions of future attendances, admissions, discharges and occupancy as well as model the impact of interventions to improve performance

Timelines: An alpha version of this product has been available for the past year and CF are co-designing a new version with Northampton and NHS England and NHS Improvement for release in Spring 2020.

2) CF Capacity

Output : An Excel based tool which visualises and models the impact of reconfiguration and efficiency improvements.

Timelines: CF has this tool deployed at two sites currently and are releasing the advanced version of the tool in Spring 2020.

3) CF Benchmark

Population segmentation

Output: A browser based interactive explorer of the population segments

Timelines: v1 is available now but only for one geographic area (Kent and Medway)

All other reports:

Output:

An automated PowerPoint presentation accessed via the browser

Timelines:

An aggregated version has been used for the past year.

All outputs will only contain results in highly aggregated format and as statistical summaries and measures of association. Small numbers will be suppressed in line with the HES Analysis Guide. Record level information will not be released to any third party.

CF Foresight + CF Capacity:

In response to COVID-19, Carnall Farrar provided the tools described above to support the NHS in their response to the pandemic using the data obtained through NHS Digital. Carnall Farrar combined the features within the CF Foresight and Capacity tools at the start of the pandemic to support system-wide modelling of demand and capacity in the five STPs of London, 32 LAs and 9 community providers. Carnall Farrar used historical data from HES APC, A&E and OP alongside COVID-19 situation reports, to develop browser based software that enabled over 50 NHS users to:

• Allow NHS organisations to extend their current capacity through re-configuration and productivity improvements (CF Capacity)

• Allow NHS organisation to create the optimal configuration of capacity given the constraints of workforce and clinical effectiveness (CF Capacity).

• Predict future activity (CF Foresight)

• Quantify the impact of plans on future occupancy (CF Foresight)

• Develop plans to change activity over a selected period of time (CF Foresight)

• Track activity against baseline to assess real-time efficacy of the new plan. (CF Foresight)

• Identify where and when demand will exceed capacity (new system level features)

• Provide forecasts on the likely demand for different discharge pathways to community and social care providers (new system level features)

Since the completion of this work in May 2020, the team have observed continued engagement with the tool. There have been 22 unique power users across the five London STPs and ~800 total interactions up until September 2020. Particular interest has been for community users in understanding how different COVID-19 acute admissions scenarios impact community demand over time. Using this tool, a number of key insights were uncovered:

• Each of the five London STPs were able to model the different COVID-19 scenarios to understand the number of acute beds, deaths and discharges they could expect over the next 4-18 months

• The majority of scenarios indicated that acute ICU capacity would not be exceeded. These outputs were shared and discussed in a workshop in early April to key leadership across NHS London, facilitated by NHS Regional Director for London and the Regional Medical Director NHS England & NHS Improvement (London).

• The demand and capacity modelling highlighted the critical challenge in the elective pathway and led to prioritisation of action in this area.

• Integration between acute and community models allowed the user to understand the burden of acute discharges on community demand over time

This work was awarded the “Best Healthcare Analytics Project for the NHS” in the HSJ partnership awards 2021.

CF Capacity:

Nottingham and Nottinghamshire ICS

The HES and ECDS data was used to create deprivation heat maps to visualise the characteristics of the population and note if there were any pockets of areas with high deprivation/ high elderly population/ high proportion of BAME. This was linked to the corresponding activity rates in hospital to identify mismatched access to care.

This helped to inform the impact assessment of moving hospital services between sites on at-risk groups to ensure there was equitable access to services across the area.

Nottingham has a complex health and deprivation profile, and this has caused areas where there is a mismatch in access to care. CF carried out advanced analysis of data from HES and ECDS to identify and map areas with high deprivation, older populations, and high proportions of BAME communities. This was compared to corresponding hospital activity rates to gain insights into relationships with access to care.

The integrated impact assessment (IIA) directly affected the decision making for the reconfiguration of services. The IIA allowed for an assessment of the population impacted. and mapped the split of the population by characteristic and LSOA. This allowed for an understanding of the overall impact of the reconfiguration on these populations in terms health outcomes and travel time and provided insight into the impact on chronic disease under different reconfiguration scenarios. Examples of this are mapping the time taken to reach a maternity ward depending on location, and time taken for stroke travel times by transport time/method.

Examples of the direct benefits yielded from this work are:

- An on-site shuttle bus to transport patients and staff for those deprived areas that were disproportionately impacted by the reconfiguration

- More free parking for patients and staff

- The hyper-acute stroke service being co-located with other emergency specialties such as neurosurgery and mechanical thrombectomy.

CF Benchmark - Inpatient Activity, A&E performance and Outpatient Activity:

Carnall Farrar combined the HES data, the SUS data and the ECDS data into a single aggregated data pipeline with a internally facing browser interface for CF consultants to use on NHSE projects. This allowed both commissioners and providers to assess performance across the system and see trends in their key activity and quality metrics against their compare performance to peers as well as understand the scale of opportunity to improve performance. Over the last year Carnall Farrar have used this tool in to yield benefits in the following area:

Hampshire and Isle of Wight ICS

Carnall Farrar supported the elective recovery of Hampshire and Isle of Wight ICS post-COVID. Carnall Farrar developed a demand and capacity model to support future planning and recovery. Additionally, Carnall Farrar created four speciality business cases and a medium-term plan, which were signed off and approved by the Planned Care Board, starting the process to establish specialty elective hubs and pathway changes across the system.

The work produced a series of deliverables that support the elective recovery of the ICS:

• Comprehensive demand and capacity model that allowed an understanding of the gaps in theatres and beds across the system and the future waiting list challenge for each trust

• Four specialty business cases, approved by the Planned Care Board, that set out clear next steps for the specialties and an approach to hub working that could tackle the longest waiters

• Holistic medium-term plan that set out a clear ambition and necessary enablers that would allow the delivery of elective care across the ICS

Carnall Farrar also supported the successful bid for the ICS to receive £10m in funding as an elective accelerator system and the submission of an elective recovery planning submission to NHS England.

Frimley Health and Care ICS

Carnall Farrar supported the creation of plans for the ICS and leverage the CF Benchmarking tool to quantify and analyse patient flow between and within the ICS to assess the coherence of the planning footprint and ensure that resource was appropriately distributed.

Carnall Farrar Ltd (CF) is a management consultancy and analytics company whose mission is to improve healthcare. CF works with a number of purchasers and providers across NHS organisations in England, Wales and Scotland, including NHS Trusts, Foundation Trusts, Clinical Commissioning Groups and Commissioning Support Units. CF has strong relationships with the Department of Health, NHS England, NHS Improvement and Public Health England. These organisations commission CF to work on projects procured both through direct commissioning agreements, and competitive procurement processes as part of access to over six public sector specific frameworks.

CF’s client base consists primarily of NHS organisations. As of February 2020, CF had active contracts with the following NHS clients:

• Barking, Havering and Redbridge University NHS Trust

• Lancashire and South Cumbria NHS STP

• Bedford, Luton and Milton Keynes NHS ICS

• Harrogate and District NHS Foundation Trust

• Central London Community Healthcare NHS Trust

Over the past few years, CF has worked with over 15 health and social care systems in England, to support health system strategy and strengthening, service transformation, financial sustainability, and integrated care delivery. Over the past five years CF has handled large volumes of data which has been obtained directly from NHS clients. CF has been successful in using this data to provide meaningful analytics which have positively impacted NHS organisations. Unfortunately, the data available directly from each NHS organisation is aggregate data and does not include diagnostic (clinical) codes. The results, although useful, are limited.

Carnall Farrar is requesting data from NHS Digital to expand the products currently on offer for NHS Clients. The record level data disseminated under this Agreement, although pseudonymised, is richer and more accurate than the data held by individual NHS organisations. Using the data under this Agreement, CF will provide more in-depth tools and products for NHS clients, therefore producing more accurate insight into the areas of the NHS requiring improvement and how these improvements can be made.

CF is requesting NHS Digital data in order provide additional benefits to NHS clients by expanding the capabilities of existing products and reducing costs to the NHS. The three products that the data under this Agreement will be used for are:

- CF Foresight

- CF Capacity

- CF Benchmarks

1) CF Foresight:

Purpose:

This tool predicts demand and patient flow through a hospital over the short to medium term (1-4 months). Hospitals can identify “pinch” points in upcoming demand compared to their current capacity and model the impact of a variety of interventions on demand and flow.

Current users:

A basic version of the tool is currently used by Northampton General Hospital NHS Trust to model the impact of increasing discharge rates within the Trust. CF also works with NHS Improvement and NHS England’s Data and Analytical Product team, to co-design the next version of the tool in order to provide a national overview of demand and flow.

Data required:

A five year extract of the following data sets:

- Mental Health Services Data Set

- Mental Health Minimum Data Set

- HES APC

- HES CC

- HES A&E

- ECDS

Why that data is required?

The tool incorporates machine learning model to predict future performance. The more years of data that are available for training the better the accuracy of the model. Five years of data is considered sufficient to account for annual variation. The HES APC, CC A&E and the ECDS data are required to train patient level models for predicting attendance, admission, four-hour breaches and discharges within the hospital. The Mental Health Services Data Set and the Mental Health Minimum Data Set are required to model the impact of mental health on A&E performance over time. The row level data is also required to model the specific interventions that trusts plan on using to improve performance. These interventions often require clinical coding to identify the impacted patients e.g. increasing discharge rates in frail elderly population within orthopaedics. CF requires the latest available data-sets to ensure that NHS commissioners and providers, who will receive CF analytics products, can make effective decisions based on the most up-to-date information.

2) CF Capacity:

Purpose:

This tool predicts in which year demand in an acute NHS organisation will exceed capacity based on demographic and non-demographic growth. It allows a system to model a variety of clinical configurations across sites, to maximise the operational effectiveness whilst minimising the negative impacts on patient safety, access and hospital performance.

Current users:

In 2019 CF used this tool on three projects; in Guernsey to ensure that the new hospital will be correctly sized, for the Barking, Havering and Redbridge University NHS Trust to reconfigure services to optimise current capacity across two sites and at Whipp’s Cross Hospital where CF assisted in the design of the hospital to ensure it met future capacity requirements.

Data required:

A five-year extract of the following data sets:

- Mental Health Services Data Set

- Mental Health Minimum Data Set

- HES APC

- HES CC

- HES A&E

- ECDS

Why that data is required?

This tool predicts up to 20 years into the future and relies on historical activity data to predict the trend and changes in activity over and above that expected from demographic changes. Five years of historic data is the minimum amount of data CF requires to capture longer term trends. Activity is categorised by point of delivery (outpatient, inpatient, emergency department), age, and HRG code (where possible). This activity data is then mapped to capacity within the hospital. In order to capture the value from the capacity available, CF model scenarios that improve efficiency or reconfigure services. The outputs from the reconfiguration analysis will feed into a separate model, which predicts the effect of different service configurations on finance, workforce, estates, capital and finance. This requires row level data including clinical codes. Access to mental health data-sets will allow CF to analyse the acute patient pathways for mental health service users, and enable a better understanding of the clinical needs now and in the future.

3) CF Benchmarks :

Purpose:

To provide a set of automated reports that allow for a rapid diagnostic of an NHS organisation. An automated set of reports that benchmarks CCGs across hospital demand, projected demand, life expectancy, deprivation, hospital performance, QOF, expenditure, workforce and populations segmentation. This product allows for a rapid diagnostic of a geographic area, freeing up time to focus on improvement rather than number analysis.

The report topics that are included are:

- Population Segmentation

- Mental Health Toolkit

- Drivers of the deficit

- Inpatient activity

- A&E performance

- Outpatient activity

Current users:

In 2019 CF employed an alpha version of this product across 6 NHS organisations:

- Lancashire and South Cumbria NHS STP

- Bedford, Luton and Milton Keynes NHS ICS

- Harrogate and District NHS Foundation Trust

- Barking, Havering and Redbridge University NHS Trust

- Newham CCG

- Tower Hamlets CCG

Data required:

- SUS PbR Spells

- SUS PbR Episodes

- SUS PbR A&E

- SUS PbR OP

- Mental Health Services Data Set

- Mental Health Minimum Data Set

- HES APC

- HES CC

- HES A&E

- HES OP

Why that data is required?

Payment by Results (PbR) is required for the drivers of the deficit analysis. CF will use these datasets to enable system financial leadership and regulators to understand the strategic financial challenge of a local area and benchmark against national peers. Mental health data is required to enable clients to monitor performance against internal targets and benchmark against national peers whilst the bridge file is required to support planning for mental health patients based on the benchmarked opportunities. The HES and Mental health data are required for benchmarking inpatient activity, outpatient activity, A&E performance and populations segmentation. Five years of data is required as time-series analysis to assess trends in performance, expenditure, utilisation, demand, seasonal patterns in utilisation as well as directional trends in performance.

The data is required at the patient level as CF’s benchmarking uses national data at the patient level to create explanatory models for each report. These explanatory models are required to compare the performance at the regional, local, site and specialty based on time of day and patient movements within the healthcare system e.g. Quantifying the differential impact across sites that the number of people in an ED department has on the probability of a patient breaching the 4 hour target.

Lawful basis

The lawful bases for processing this data under GDPR is as follows:

• Article 6(1)(f) – it is necessary for the legitimate interests in being able to provide tools and services that will benefit healthcare organisations

• Article 9(2)(j) – it is necessary for reasons that are in the public interest in the area of public health. CF provides tools and services to public healthcare organisations that help them to monitor and improve the standards and quality of care that they offer. The processing is designed to benefit patients' and society as a whole, through facilitating better healthcare in the UK.

To determine the lawfulness of processing the data for these legitimate interests, Carnall Farrar has undertaken a Legitimate Interests Assessment (LIA) and determined that:

i. The processing is necessary for the purpose:

The processing of patient data is required to provide accurate analysis of patient pathways, outcomes and performance. Aggregate data does not allow the patient level predictions and evaluations required to perform the detailed analysis and modelling required for:

CF Foresight (1) : Predicting patient admission and discharge data, modelling patient level intervention

CF Capacity (2) : Mapping individual patients to activity groups, identifying opportunities within care pathways

CF Benchmarking (3) : Creating patient segmentation groups, modelling A&E performance, identifying financial opportunities for clinical pathways

ii. The processing is proportionate to the purpose:

The processing of this data will relate solely to the improvement of the health and social care system in England and Wales through providing detailed recommendations and initiatives that aggregate data cannot provide due to the unconnected nature of the data-sets.

The negative impact on individual patients is minimal and CF predicts that patients will benefit from the enhanced service provided by the tools and analysis this data processing produces. This data processing will not identify individuals and the output of this processing will not lead to data-sets that can be used to identify individuals.

iii. The purpose cannot be achieved by processing the data in another more obvious or less intrusive way:

The correlations between behaviours at the level of the individual patient are lost when using aggregate data. These correlations are crucial for capturing the true impact of initiatives and identifying the underlying causes for health system under-performance. Summary statistics mask these relationships and can lead to biased analysis especially when modelling system performance across multiple points of delivery.

iv. The interests of the individual data subjects do not override the legitimate interest:

Carnall Farrar has considered that the data is health data, including data about children or other vulnerable people, which the data subjects are likely to consider particularly private and that some individuals would feel uncomfortable about the processing of their health data outside of the NHS. However, the data sets are pseudonymised and therefore, the possible impacts of the processing will be minimal as Carnall Farrar is not able to de-pseudonymise the data nor will Carnall Farrar attempt to identify patients using any means. Carnall Farrar has put in place policy safeguards to ensure the security and privacy of patient records and limit the impact on patients to positive enhancements of care.

Carnall Farrar believes that the above provides sufficient legitimate interests for lawful processing of the data requested under this Agreement. Carnall Farrar has determined that there is unlikely to be any moral or ethical issue arising from the processing of this data as the data requested is pseudonymised.

Carnall Farrar is the sole Data Controller for the purposes of this Agreement and Carnall Farrar will be directly processing the data. Amazon Web Services (AWS) is a Data Processor for Carnall Farrar. Data processing and storage will take place within Carnall Farrar's secure cloud platform which is based on an AWS UK environment. The servers that store and process the data under this Agreement will be within UK sovereignty (London). The data under this Agreement will be solely used for the purposes stated above and only substantive employees of Carnall Farrar will have access to this data. No employee of AWS will access this data.

Benefits to the Health and Social Care System:

CF will support access of the data to NHS clients, enabling more effective use of the data, validation of data through feedback and, crucially, supporting more effective integration of data. The analytical products that CF builds will help NHS clients to make better decisions. A crucial component of the analytical work with NHS clients is to ensure a legacy of embedded analytical capability. CF aims to improve the flow of data across the NHS, closing the gap between action and feedback. This will help reduce data latency and improve data quality, two key components to effective use of data to create a health system that learns from every patient.

The data disseminated under this Agreement will only be used to provide services to NHS organisations within England and Wales. CF does not currently work with any non-NHS organisations however, previously CF has worked with non-NHS organisations such as charities (Healthy living UK), think tanks (IPPR) and life sciences projects. For CF’s non-NHS clients, only publicly available data is used, and the data is stored in a different physical location within CF's data warehouse. The data provided under this Agreement will only be used for CF’s NHS Clients and will not be shared between NHS and non-NHS projects/organisations.

CF works on multiple projects at any one time for a number of different national, regional and local organisations across the NHS. Therefore, it is not possible to provide full details of all outputs, as these are highly specific to the requirements for each client. CF will only share aggregated analysis with its NHS clients in presentations, reports or cloud-based visualisation tools, in full compliance with the small numbers guidance. In general, all outputs can be grouped into one of several categories detailed below:

• CF provides detailed reports to clients, which contain data in table format containing aggregated, non-patient identifiable data with small numbers suppressed in line with the HES Analysis Guide;

• These reports may also contain visualisations created using data based on aggregated, non-patient identifiable results of quantitative analysis;

• CF presents the aggregated, non-patient identifiable results with small numbers suppressed, in the form of tables and visualisations, at meetings with NHS client stakeholders;

• CF provides interactive visualisations to NHS clients in the form of cloud-based tools; the software tools that CF builds will allow some analysis to be done on aggregated data (with small numbers suppressed), in house by the providers/commissioners. CF will not allow the providers and commissioners to directly access the patient level data.

• Benchmarking applies across all services. National benchmarks will be derived from the national data. The outputs from queries against these data will be transferred to excel, R, Python or visualisation software for communication to CF clients.

All outputs will only contain results in highly aggregated format and as statistical summaries and measures of association. Small numbers will be suppressed. Record level information will not be released to any third party.

Examples of the specific tool outputs are set out below:

1) CF Foresight

Output : A browser based tool that enables providers and commissioners to view predictions of future attendances, admissions, discharges and occupancy as well as model the impact of interventions to improve performance

Timelines: An alpha version of this product has been available for the past year and we are co-designing a new version with Northampton and NHS England and NHS Improvement for release in Spring 2020.

2) CF Capacity

Output : An Excel based tool which visualises and models the impact of reconfiguration and efficiency improvements.

Timelines: CF has this tool deployed at two sites currently and are releasing the advanced version of the tool in Spring 2020.

3) CF Benchmark

Population segmentation

Output: A browser based interactive explorer of the population segments

Timelines: v1 is available now but only for one geographic area (Kent and Medway)

All other reports:

Output:

An automated PowerPoint presentation accessed via the browser

Timelines:

An aggregated version has been used for the past year.

All outputs will only contain results in highly aggregated format and as statistical summaries and measures of association. Small numbers will be suppressed in line with the HES Analysis Guide. Record level information will not be released to any third party.

Carnall Farrar Ltd (CF) is a management consultancy and analytics company whose mission is to improve healthcare. CF works with a number of purchasers and providers across NHS organisations in England, Wales and Scotland, including NHS Trusts, Foundation Trusts, Clinical Commissioning Groups and Commissioning Support Units. CF has strong relationships with the Department of Health, NHS England, NHS Improvement and Public Health England. These organisations commission CF to work on projects procured both through direct commissioning agreements, and competitive procurement processes as part of access to over six public sector specific frameworks.

CF’s client base consists primarily of NHS organisations. As of February 2020, CF had active contracts with the following NHS clients:

• Barking, Havering and Redbridge University NHS Trust

• Lancashire and South Cumbria NHS STP

• Bedford, Luton and Milton Keynes NHS ICS

• Harrogate and District NHS Foundation Trust

• Central London Community Healthcare NHS Trust

Over the past few years, CF has worked with over 15 health and social care systems in England, to support health system strategy and strengthening, service transformation, financial sustainability, and integrated care delivery. Over the past five years CF has handled large volumes of data which has been obtained directly from NHS clients. CF has been successful in using this data to provide meaningful analytics which have positively impacted NHS organisations. Unfortunately, the data available directly from each NHS organisation is aggregate data and does not include diagnostic (clinical) codes. The results, although useful, are limited.

Carnall Farrar is requesting data from NHS Digital to expand the products currently on offer for NHS Clients. The record level data disseminated under this Agreement, although pseudonymised, is richer and more accurate than the data held by individual NHS organisations. Using the data under this Agreement, CF will provide more in-depth tools and products for NHS clients, therefore producing more accurate insight into the areas of the NHS requiring improvement and how these improvements can be made.

CF is requesting NHS Digital data in order provide additional benefits to NHS clients by expanding the capabilities of existing products and reducing costs to the NHS. The three products that the data under this Agreement will be used for are:

- CF Foresight

- CF Capacity

- CF Benchmarks

1) CF Foresight:

Purpose:

This tool predicts demand and patient flow through a hospital over the short to medium term (1-4 months). Hospitals can identify “pinch” points in upcoming demand compared to their current capacity and model the impact of a variety of interventions on demand and flow.

Current users:

A basic version of the tool is currently used by Northampton General Hospital NHS Trust to model the impact of increasing discharge rates within the Trust. CF also works with NHS Improvement and NHS England’s Data and Analytical Product team, to co-design the next version of the tool in order to provide a national overview of demand and flow.

Data required:

A five year extract of the following data sets:

- Mental Health Services Data Set

- Mental Health Minimum Data Set

- HES APC

- HES CC

- HES A&E

- ECDS

Why that data is required?

The tool incorporates machine learning model to predict future performance. The more years of data that are available for training the better the accuracy of the model. Five years of data is considered sufficient to account for annual variation. The HES APC, CC A&E and the ECDS data are required to train patient level models for predicting attendance, admission, four-hour breaches and discharges within the hospital. The Mental Health Services Data Set and the Mental Health Minimum Data Set are required to model the impact of mental health on A&E performance over time. The row level data is also required to model the specific interventions that trusts plan on using to improve performance. These interventions often require clinical coding to identify the impacted patients e.g. increasing discharge rates in frail elderly population within orthopaedics. CF requires the latest available data-sets to ensure that NHS commissioners and providers, who will receive CF analytics products, can make effective decisions based on the most up-to-date information.

2) CF Capacity:

Purpose:

This tool predicts in which year demand in an acute NHS organisation will exceed capacity based on demographic and non-demographic growth. It allows a system to model a variety of clinical configurations across sites, to maximise the operational effectiveness whilst minimising the negative impacts on patient safety, access and hospital performance.

Current users:

In 2019 CF used this tool on three projects; in Guernsey to ensure that the new hospital will be correctly sized, for the Barking, Havering and Redbridge University NHS Trust to reconfigure services to optimise current capacity across two sites and at Whipp’s Cross Hospital where CF assisted in the design of the hospital to ensure it met future capacity requirements.

Data required:

A five-year extract of the following data sets:

- Mental Health Services Data Set

- Mental Health Minimum Data Set

- HES APC

- HES CC

- HES A&E

- ECDS

Why that data is required?

This tool predicts up to 20 years into the future and relies on historical activity data to predict the trend and changes in activity over and above that expected from demographic changes. Five years of historic data is the minimum amount of data CF requires to capture longer term trends. Activity is categorised by point of delivery (outpatient, inpatient, emergency department), age, and HRG code (where possible). This activity data is then mapped to capacity within the hospital. In order to capture the value from the capacity available, CF model scenarios that improve efficiency or reconfigure services. The outputs from the reconfiguration analysis will feed into a separate model, which predicts the effect of different service configurations on finance, workforce, estates, capital and finance. This requires row level data including clinical codes. Access to mental health data-sets will allow CF to analyse the acute patient pathways for mental health service users, and enable a better understanding of the clinical needs now and in the future.

3) CF Benchmarks :

Purpose:

To provide a set of automated reports that allow for a rapid diagnostic of an NHS organisation. An automated set of reports that benchmarks CCGs across hospital demand, projected demand, life expectancy, deprivation, hospital performance, QOF, expenditure, workforce and populations segmentation. This product allows for a rapid diagnostic of a geographic area, freeing up time to focus on improvement rather than number analysis.

The report topics that are included are:

- Population Segmentation

- Mental Health Toolkit

- Drivers of the deficit

- Inpatient activity

- A&E performance

- Outpatient activity

Current users:

In 2019 CF employed an alpha version of this product across 6 NHS organisations:

- Lancashire and South Cumbria NHS STP

- Bedford, Luton and Milton Keynes NHS ICS

- Harrogate and District NHS Foundation Trust

- Barking, Havering and Redbridge University NHS Trust

- Newham CCG

- Tower Hamlets CCG

Data required:

- SUS PbR Spells

- SUS PbR Episodes

- SUS PbR A&E

- SUS PbR OP

- Mental Health Services Data Set

- Mental Health Minimum Data Set

- HES APC

- HES CC

- HES A&E

- HES OP

Why that data is required?

Payment by Results (PbR) is required for the drivers of the deficit analysis. CF will use these datasets to enable system financial leadership and regulators to understand the strategic financial challenge of a local area and benchmark against national peers. Mental health data is required to enable clients to monitor performance against internal targets and benchmark against national peers whilst the bridge file is required to support planning for mental health patients based on the benchmarked opportunities. The HES and Mental health data are required for benchmarking inpatient activity, outpatient activity, A&E performance and populations segmentation. Five years of data is required as time-series analysis to assess trends in performance, expenditure, utilisation, demand, seasonal patterns in utilisation as well as directional trends in performance.

The data is required at the patient level as CF’s benchmarking uses national data at the patient level to create explanatory models for each report. These explanatory models are required to compare the performance at the regional, local, site and specialty based on time of day and patient movements within the healthcare system e.g. Quantifying the differential impact across sites that the number of people in an ED department has on the probability of a patient breaching the 4 hour target.

Lawful basis

The lawful bases for processing this data under GDPR is as follows:

• Article 6(1)(f) – it is necessary for the legitimate interests in being able to provide tools and services that will benefit healthcare organisations

• Article 9(2)(j) – it is necessary for reasons that are in the public interest in the area of public health. CF provides tools and services to public healthcare organisations that help them to monitor and improve the standards and quality of care that they offer. The processing is designed to benefit patients' and society as a whole, through facilitating better healthcare in the UK.

To determine the lawfulness of processing the data for these legitimate interests, Carnall Farrar has undertaken a Legitimate Interests Assessment (LIA) and determined that:

i. The processing is necessary for the purpose:

The processing of patient data is required to provide accurate analysis of patient pathways, outcomes and performance. Aggregate data does not allow the patient level predictions and evaluations required to perform the detailed analysis and modelling required for:

CF Foresight (1) : Predicting patient admission and discharge data, modelling patient level intervention

CF Capacity (2) : Mapping individual patients to activity groups, identifying opportunities within care pathways

CF Benchmarking (3) : Creating patient segmentation groups, modelling A&E performance, identifying financial opportunities for clinical pathways

ii. The processing is proportionate to the purpose:

The processing of this data will relate solely to the improvement of the health and social care system in England and Wales through providing detailed recommendations and initiatives that aggregate data cannot provide due to the unconnected nature of the data-sets.

The negative impact on individual patients is minimal and CF predicts that patients will benefit from the enhanced service provided by the tools and analysis this data processing produces. This data processing will not identify individuals and the output of this processing will not lead to data-sets that can be used to identify individuals.

iii. The purpose cannot be achieved by processing the data in another more obvious or less intrusive way:

The correlations between behaviours at the level of the individual patient are lost when using aggregate data. These correlations are crucial for capturing the true impact of initiatives and identifying the underlying causes for health system under-performance. Summary statistics mask these relationships and can lead to biased analysis especially when modelling system performance across multiple points of delivery.

iv. The interests of the individual data subjects do not override the legitimate interest:

Carnall Farrar has considered that the data is health data, including data about children or other vulnerable people, which the data subjects are likely to consider particularly private and that some individuals would feel uncomfortable about the processing of their health data outside of the NHS. However, the data sets are pseudonymised and therefore, the possible impacts of the processing will be minimal as Carnall Farrar is not able to de-pseudonymise the data nor will Carnall Farrar attempt to identify patients using any means. Carnall Farrar has put in place policy safeguards to ensure the security and privacy of patient records and limit the impact on patients to positive enhancements of care.

Carnall Farrar believes that the above provides sufficient legitimate interests for lawful processing of the data requested under this Agreement. Carnall Farrar has determined that there is unlikely to be any moral or ethical issue arising from the processing of this data as the data requested is pseudonymised.

Carnall Farrar is the sole Data Controller for the purposes of this Agreement and Carnall Farrar will be directly processing the data. Amazon Web Services (AWS) is a Data Processor for Carnall Farrar. Data processing and storage will take place within Carnall Farrar's secure cloud platform which is based on an AWS UK environment. The servers that store and process the data under this Agreement will be within UK sovereignty (London). The data under this Agreement will be solely used for the purposes stated above and only substantive employees of Carnall Farrar will have access to this data. No employee of AWS will access this data.

Benefits to the Health and Social Care System:

CF will support access of the data to NHS clients, enabling more effective use of the data, validation of data through feedback and, crucially, supporting more effective integration of data. The analytical products that CF builds will help NHS clients to make better decisions. A crucial component of the analytical work with NHS clients is to ensure a legacy of embedded analytical capability. CF aims to improve the flow of data across the NHS, closing the gap between action and feedback. This will help reduce data latency and improve data quality, two key components to effective use of data to create a health system that learns from every patient.

The data disseminated under this Agreement will only be used to provide services to NHS organisations within England and Wales. CF does not currently work with any non-NHS organisations however, previously CF has worked with non-NHS organisations such as charities (Healthy living UK), think tanks (IPPR) and life sciences projects. For CF’s non-NHS clients, only publicly available data is used, and the data is stored in a different physical location within CF's data warehouse. The data provided under this Agreement will only be used for CF’s NHS Clients and will not be shared between NHS and non-NHS projects/organisations.

CF works on multiple projects at any one time for a number of different national, regional and local organisations across the NHS. Therefore, it is not possible to provide full details of all outputs, as these are highly specific to the requirements for each client. CF will only share aggregated analysis with its NHS clients in presentations, reports or cloud-based visualisation tools, in full compliance with the small numbers guidance. In general, all outputs can be grouped into one of several categories detailed below:

• CF provides detailed reports to clients, which contain data in table format containing aggregated, non-patient identifiable data with small numbers suppressed in line with the HES Analysis Guide;

• These reports may also contain visualisations created using data based on aggregated, non-patient identifiable results of quantitative analysis;

• CF presents the aggregated, non-patient identifiable results with small numbers suppressed, in the form of tables and visualisations, at meetings with NHS client stakeholders;

• CF provides interactive visualisations to NHS clients in the form of cloud-based tools; the software tools that CF builds will allow some analysis to be done on aggregated data (with small numbers suppressed), in house by the providers/commissioners. CF will not allow the providers and commissioners to directly access the patient level data.

• Benchmarking applies across all services. National benchmarks will be derived from the national data. The outputs from queries against these data will be transferred to excel, R, Python or visualisation software for communication to CF clients.

All outputs will only contain results in highly aggregated format and as statistical summaries and measures of association. Small numbers will be suppressed. Record level information will not be released to any third party.

Examples of the specific tool outputs are set out below:

1) CF Foresight

Output : A browser based tool that enables providers and commissioners to view predictions of future attendances, admissions, discharges and occupancy as well as model the impact of interventions to improve performance

Timelines: An alpha version of this product has been available for the past year and we are co-designing a new version with Northampton and NHS England and NHS Improvement for release in Spring 2020.

2) CF Capacity

Output : An Excel based tool which visualises and models the impact of reconfiguration and efficiency improvements.

Timelines: CF has this tool deployed at two sites currently and are releasing the advanced version of the tool in Spring 2020.

3) CF Benchmark

Population segmentation

Output: A browser based interactive explorer of the population segments

Timelines: v1 is available now but only for one geographic area (Kent and Medway)

All other reports:

Output:

An automated PowerPoint presentation accessed via the browser

Timelines:

An aggregated version has been used for the past year.

All outputs will only contain results in highly aggregated format and as statistical summaries and measures of association. Small numbers will be suppressed in line with the HES Analysis Guide. Record level information will not be released to any third party.

Carnall Farrar Ltd (CF) is a management consultancy and analytics company whose mission is to improve healthcare. CF works with a number of purchasers and providers across NHS organisations in England, Wales and Scotland, including NHS Trusts, Foundation Trusts, Clinical Commissioning Groups and Commissioning Support Units. CF has strong relationships with the Department of Health, NHS England, NHS Improvement and Public Health England. These organisations commission CF to work on projects procured both through direct commissioning agreements, and competitive procurement processes as part of access to over six public sector specific frameworks.

CF’s client base consists primarily of NHS organisations. As of February 2020, CF had active contracts with the following NHS clients:

• Barking, Havering and Redbridge University NHS Trust

• Lancashire and South Cumbria NHS STP

• Bedford, Luton and Milton Keynes NHS ICS

• Harrogate and District NHS Foundation Trust

• Central London Community Healthcare NHS Trust

Over the past few years, CF has worked with over 15 health and social care systems in England, to support health system strategy and strengthening, service transformation, financial sustainability, and integrated care delivery. Over the past five years CF has handled large volumes of data which has been obtained directly from NHS clients. CF has been successful in using this data to provide meaningful analytics which have positively impacted NHS organisations. Unfortunately, the data available directly from each NHS organisation is aggregate data and does not include diagnostic (clinical) codes. The results, although useful, are limited.

Carnall Farrar is requesting data from NHS Digital to expand the products currently on offer for NHS Clients. The record level data disseminated under this Agreement, although pseudonymised, is richer and more accurate than the data held by individual NHS organisations. Using the data under this Agreement, CF will provide more in-depth tools and products for NHS clients, therefore producing more accurate insight into the areas of the NHS requiring improvement and how these improvements can be made.

CF is requesting NHS Digital data in order provide additional benefits to NHS clients by expanding the capabilities of existing products and reducing costs to the NHS. The three products that the data under this Agreement will be used for are:

- CF Foresight

- CF Capacity

- CF Benchmarks

1) CF Foresight:

Purpose:

This tool predicts demand and patient flow through a hospital over the short to medium term (1-4 months). Hospitals can identify “pinch” points in upcoming demand compared to their current capacity and model the impact of a variety of interventions on demand and flow.

Current users:

A basic version of the tool is currently used by Northampton General Hospital NHS Trust to model the impact of increasing discharge rates within the Trust. CF also works with NHS Improvement and NHS England’s Data and Analytical Product team, to co-design the next version of the tool in order to provide a national overview of demand and flow.

Data required:

A five year extract of the following data sets:

- Mental Health Services Data Set

- Mental Health Minimum Data Set

- HES APC

- HES CC

- HES A&E

- ECDS

Why that data is required?

The tool incorporates machine learning model to predict future performance. The more years of data that are available for training the better the accuracy of the model. Five years of data is considered sufficient to account for annual variation. The HES APC, CC A&E and the ECDS data are required to train patient level models for predicting attendance, admission, four-hour breaches and discharges within the hospital. The Mental Health Services Data Set and the Mental Health Minimum Data Set are required to model the impact of mental health on A&E performance over time. The row level data is also required to model the specific interventions that trusts plan on using to improve performance. These interventions often require clinical coding to identify the impacted patients e.g. increasing discharge rates in frail elderly population within orthopaedics. CF requires the latest available data-sets to ensure that NHS commissioners and providers, who will receive CF analytics products, can make effective decisions based on the most up-to-date information.

2) CF Capacity:

Purpose:

This tool predicts in which year demand in an acute NHS organisation will exceed capacity based on demographic and non-demographic growth. It allows a system to model a variety of clinical configurations across sites, to maximise the operational effectiveness whilst minimising the negative impacts on patient safety, access and hospital performance.

Current users:

In 2019 CF used this tool on three projects; in Guernsey to ensure that the new hospital will be correctly sized, for the Barking, Havering and Redbridge University NHS Trust to reconfigure services to optimise current capacity across two sites and at Whipp’s Cross Hospital where CF assisted in the design of the hospital to ensure it met future capacity requirements.

Data required:

A five-year extract of the following data sets:

- Mental Health Services Data Set

- Mental Health Minimum Data Set

- HES APC

- HES CC

- HES A&E

- ECDS

Why that data is required?

This tool predicts up to 20 years into the future and relies on historical activity data to predict the trend and changes in activity over and above that expected from demographic changes. Five years of historic data is the minimum amount of data CF requires to capture longer term trends. Activity is categorised by point of delivery (outpatient, inpatient, emergency department), age, and HRG code (where possible). This activity data is then mapped to capacity within the hospital. In order to capture the value from the capacity available, CF model scenarios that improve efficiency or reconfigure services. The outputs from the reconfiguration analysis will feed into a separate model, which predicts the effect of different service configurations on finance, workforce, estates, capital and finance. This requires row level data including clinical codes. Access to mental health data-sets will allow CF to analyse the acute patient pathways for mental health service users, and enable a better understanding of the clinical needs now and in the future.

3) CF Benchmarks :

Purpose:

To provide a set of automated reports that allow for a rapid diagnostic of an NHS organisation. An automated set of reports that benchmarks CCGs across hospital demand, projected demand, life expectancy, deprivation, hospital performance, QOF, expenditure, workforce and populations segmentation. This product allows for a rapid diagnostic of a geographic area, freeing up time to focus on improvement rather than number analysis.

The report topics that are included are:

- Population Segmentation

- Mental Health Toolkit

- Drivers of the deficit

- Inpatient activity

- A&E performance

- Outpatient activity

Current users:

In 2019 CF employed an alpha version of this product across 6 NHS organisations:

- Lancashire and South Cumbria NHS STP

- Bedford, Luton and Milton Keynes NHS ICS

- Harrogate and District NHS Foundation Trust

- Barking, Havering and Redbridge University NHS Trust

- Newham CCG

- Tower Hamlets CCG

Data required:

- SUS PbR Spells

- SUS PbR Episodes

- SUS PbR A&E

- SUS PbR OP

- Mental Health Services Data Set

- Mental Health Minimum Data Set

- HES APC

- HES CC

- HES A&E

- HES OP

Why that data is required?

Payment by Results (PbR) is required for the drivers of the deficit analysis. CF will use these datasets to enable system financial leadership and regulators to understand the strategic financial challenge of a local area and benchmark against national peers. Mental health data is required to enable clients to monitor performance against internal targets and benchmark against national peers whilst the bridge file is required to support planning for mental health patients based on the benchmarked opportunities. The HES and Mental health data are required for benchmarking inpatient activity, outpatient activity, A&E performance and populations segmentation. Five years of data is required as time-series analysis to assess trends in performance, expenditure, utilisation, demand, seasonal patterns in utilisation as well as directional trends in performance.

The data is required at the patient level as CF’s benchmarking uses national data at the patient level to create explanatory models for each report. These explanatory models are required to compare the performance at the regional, local, site and specialty based on time of day and patient movements within the healthcare system e.g. Quantifying the differential impact across sites that the number of people in an ED department has on the probability of a patient breaching the 4 hour target.

Lawful basis

The lawful bases for processing this data under GDPR is as follows:

• Article 6(1)(f) – it is necessary for the legitimate interests in being able to provide tools and services that will benefit healthcare organisations

• Article 9(2)(j) – it is necessary for reasons that are in the public interest in the area of public health. CF provides tools and services to public healthcare organisations that help them to monitor and improve the standards and quality of care that they offer. The processing is designed to benefit patients' and society as a whole, through facilitating better healthcare in the UK.

To determine the lawfulness of processing the data for these legitimate interests, Carnall Farrar has undertaken a Legitimate Interests Assessment (LIA) and determined that:

i. The processing is necessary for the purpose:

The processing of patient data is required to provide accurate analysis of patient pathways, outcomes and performance. Aggregate data does not allow the patient level predictions and evaluations required to perform the detailed analysis and modelling required for:

CF Foresight (1) : Predicting patient admission and discharge data, modelling patient level intervention

CF Capacity (2) : Mapping individual patients to activity groups, identifying opportunities within care pathways

CF Benchmarking (3) : Creating patient segmentation groups, modelling A&E performance, identifying financial opportunities for clinical pathways

ii. The processing is proportionate to the purpose:

The processing of this data will relate solely to the improvement of the health and social care system in England and Wales through providing detailed recommendations and initiatives that aggregate data cannot provide due to the unconnected nature of the data-sets.

The negative impact on individual patients is minimal and CF predicts that patients will benefit from the enhanced service provided by the tools and analysis this data processing produces. This data processing will not identify individuals and the output of this processing will not lead to data-sets that can be used to identify individuals.

iii. The purpose cannot be achieved by processing the data in another more obvious or less intrusive way:

The correlations between behaviours at the level of the individual patient are lost when using aggregate data. These correlations are crucial for capturing the true impact of initiatives and identifying the underlying causes for health system under-performance. Summary statistics mask these relationships and can lead to biased analysis especially when modelling system performance across multiple points of delivery.

iv. The interests of the individual data subjects do not override the legitimate interest:

Carnall Farrar has considered that the data is health data, including data about children or other vulnerable people, which the data subjects are likely to consider particularly private and that some individuals would feel uncomfortable about the processing of their health data outside of the NHS. However, the data sets are pseudonymised and therefore, the possible impacts of the processing will be minimal as Carnall Farrar is not able to de-pseudonymise the data nor will Carnall Farrar attempt to identify patients using any means. Carnall Farrar has put in place policy safeguards to ensure the security and privacy of patient records and limit the impact on patients to positive enhancements of care.

Carnall Farrar believes that the above provides sufficient legitimate interests for lawful processing of the data requested under this Agreement. Carnall Farrar has determined that there is unlikely to be any moral or ethical issue arising from the processing of this data as the data requested is pseudonymised.

Carnall Farrar is the sole Data Controller for the purposes of this Agreement and Carnall Farrar will be directly processing the data. Amazon Web Services (AWS) is a Data Processor for Carnall Farrar. Data processing and storage will take place within Carnall Farrar's secure cloud platform which is based on an AWS UK environment. The servers that store and process the data under this Agreement will be within UK sovereignty (London). The data under this Agreement will be solely used for the purposes stated above and only substantive employees of Carnall Farrar will have access to this data. No employee of AWS will access this data.

Benefits to the Health and Social Care System:

CF will support access of the data to NHS clients, enabling more effective use of the data, validation of data through feedback and, crucially, supporting more effective integration of data. The analytical products that CF builds will help NHS clients to make better decisions. A crucial component of the analytical work with NHS clients is to ensure a legacy of embedded analytical capability. CF aims to improve the flow of data across the NHS, closing the gap between action and feedback. This will help reduce data latency and improve data quality, two key components to effective use of data to create a health system that learns from every patient.

The data disseminated under this Agreement will only be used to provide services to NHS organisations within England and Wales. CF does not currently work with any non-NHS organisations however, previously CF has worked with non-NHS organisations such as charities (Healthy living UK), think tanks (IPPR) and life sciences projects. For CF’s non-NHS clients, only publicly available data is used, and the data is stored in a different physical location within CF's data warehouse. The data provided under this Agreement will only be used for CF’s NHS Clients and will not be shared between NHS and non-NHS projects/organisations.

CF works on multiple projects at any one time for a number of different national, regional and local organisations across the NHS. Therefore, it is not possible to provide full details of all outputs, as these are highly specific to the requirements for each client. CF will only share aggregated analysis with its NHS clients in presentations, reports or cloud-based visualisation tools, in full compliance with the small numbers guidance. In general, all outputs can be grouped into one of several categories detailed below:

• CF provides detailed reports to clients, which contain data in table format containing aggregated, non-patient identifiable data with small numbers suppressed in line with the HES Analysis Guide;

• These reports may also contain visualisations created using data based on aggregated, non-patient identifiable results of quantitative analysis;

• CF presents the aggregated, non-patient identifiable results with small numbers suppressed, in the form of tables and visualisations, at meetings with NHS client stakeholders;

• CF provides interactive visualisations to NHS clients in the form of cloud-based tools; the software tools that CF builds will allow some analysis to be done on aggregated data (with small numbers suppressed), in house by the providers/commissioners. CF will not allow the providers and commissioners to directly access the patient level data.

• Benchmarking applies across all services. National benchmarks will be derived from the national data. The outputs from queries against these data will be transferred to excel, R, Python or visualisation software for communication to CF clients.

All outputs will only contain results in highly aggregated format and as statistical summaries and measures of association. Small numbers will be suppressed. Record level information will not be released to any third party.

Examples of the specific tool outputs are set out below:

1) CF Foresight

Output : A browser based tool that enables providers and commissioners to view predictions of future attendances, admissions, discharges and occupancy as well as model the impact of interventions to improve performance

Timelines: An alpha version of this product has been available for the past year and we are co-designing a new version with Northampton and NHS England and NHS Improvement for release in Spring 2020.

2) CF Capacity

Output : An Excel based tool which visualises and models the impact of reconfiguration and efficiency improvements.

Timelines: CF has this tool deployed at two sites currently and are releasing the advanced version of the tool in Spring 2020.

3) CF Benchmark

Population segmentation

Output: A browser based interactive explorer of the population segments

Timelines: v1 is available now but only for one geographic area (Kent and Medway)

All other reports:

Output:

An automated PowerPoint presentation accessed via the browser

Timelines:

An aggregated version has been used for the past year.

All outputs will only contain results in highly aggregated format and as statistical summaries and measures of association. Small numbers will be suppressed in line with the HES Analysis Guide. Record level information will not be released to any third party.

Yielded Benefits is not a requirement for new applications.