Discovery and evaluation of patient pathways using ECDS

University of Birmingham requires access to NHS England data for the purpose of the following research project:

Discovery and evaluation of patient pathways using Emergency Care dataset (ECDS)

The following is a summary of the aims of the research project provided by University of Birmingham:

A&E performance across the NHS has been under severe strain for many years. Waits over five hours in emergency departments have been linked to increased mortality rates. Available bed capacity has halved, and each service in acute care adds to the average waiting time for patients. Under current analysis, the real term increase to NHS England’s budget over the course of this parliament will be negative. Consequently, an additional funding top up of £4 billion would be needed to match the original planed parliamentary budget. On top of budget constraints, pressure to match service demand, while delivering increased value for money, requires new and novel approaches to healthcare. Moving towards more “joined up” approaches, and reducing care fragmentation, is a focus of new research. Increasingly, larger datasets and more sophisticated analysis are needed to take advantage of data routinely collected in healthcare settings.

The project’s objective is to establish national descriptions and analysis of patient flows across emergency departments in England and will apply tools from the field of process mining to the Uncurated Low Latency Hospital Data Sets - Emergency Care dataset. Process mining is a data driven approach to describing complex processes and how separate subprocesses interact. Process mining will take recorded patient interactions in an emergency department and attempt to identify patient flows. The graphical picture is akin to a flow chart of how patients are treated, and which treatments are more common than others before departing an emergency department. The patient flow diagrams are designed to be interpreted and scrutinised by clinical and operational managers to verify their accuracy and suggest improvements to current practices.

This exploratory research project aims to:

1. Evaluate Uncurated Low Latency Hospital Data Sets - Emergency Care as a resource for applying the field or process mining to emergency care within NHS hospitals

2. Describe patient flows within NHS trust hospitals, and a graphical flow-chart like representation of these flows

3. Compare patient flows in terms of high-level patient outcomes, such as patient waiting times, discharge rates, inpatient admission rates

Although this will have an exploratory component, if, and which, cohorts are processed differently will be result used for future research. It is anticipated cohorts to significantly depend on age, gender, ethnicity and ICD10 coding. As an example, can pathways for patients who present with specific ICD10 codes be discovered and compare those processes across trusts to find better or worse patient outcomes. One motivation of this work is the desire to describe and compare individual NHS trusts and understand differences in trusts’ performance. The project will identify relevant cohorts from data analysis.

Patient flows will be created at NHS trust level, analysing patients who attended any type 1 department between the start of 2018 and the end of 2023. The analysis will also be conducted in each region of England, but always focused of the organisational units of NHS trusts. The project will then investigate differences between patient flows at trusts and their associated outcomes for patients. Differences in patient flows will be divided into a) structural differences and similarities between patient flow diagrams, b) performance differences, such as waiting times and admission rates, and c) differences in patient outcomes, such as emergency readmissions within 30 days of attendance.

The following NHS England Data will be accessed:

• Uncurated Low Latency Hospital Data Sets - Emergency Care – necessary to provide a whole description of a patient’s healthcare journey, which is required to study general emergency healthcare services.

The level of the Data will be

• Pseudonymised

The Data will be minimised as follows:

• Limited to data between Jan 2018 – latest available; this is to cover data before, during and after the COVID-19 pandemic so any changes in practice across this period can be studied.

University of Birmingham is the controller as the organisation responsible for ensuring that the Data will only be processed for the purpose described above.

As well as providing access to the SDE, NHS England will provide access to internal channels and policy groups, such as the urgency and emergence care transformation programme and elective care transformation programme. NHS England’s role is to help shape outputs and provide subject matter expertise in an advisory capacity only.

The lawful basis for processing personal data under the UK GDPR is:

Article 6(1)(e) - processing is necessary for the performance of a task carried out in the public interest or in the exercise of official authority vested in the controller;

The lawful basis for processing special category data under the UK GDPR is:

Article 9(2)(j) - 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 essence of the right to data protection and provide for suitable and specific measures to safeguard the fundamental rights and the interests of the data subject.

The public interest in this project is the study and identification of better ways to deliver healthcare. The project aims to discover new ways of delivering effective emergency care, with the potential result of reducing waiting times, improving long term outcomes, and making better use of resources such as staff levels, equipment and general expenditure.

The funding is provided by Health Data Research UK (HDRUK). The funding is for the PhD studentship and is not specifically limited to the project described. Funding is in place until the end of 2026 but will be extended if required.

The funder(s) will have no ability to suppress or otherwise limit the publication of findings.

Data will be accessed by:

• Substantive employees of the University of Birmingham.

• One PhD student enrolled with the University of Birmingham.

The individual has completed mandatory data protection and confidentiality training and is subject to the University of Birmingham’s policies on data protection and confidentiality. The individual accessing the data will do so under the supervision of a substantive employee of University of Birmingham. University of Birmingham would be responsible and liable for any work carried out by the individual. The PhD student would only work on the data for the purposes described in this Data Sharing Agreement (DSA).

The primary public and patient engagement channels used for this project are the OPTIMAL project patient advisory group (PAG) and mandatory public / patient interaction and engagement session held by HDR UK. The OPTIMAL PAG are a group of clinicians, healthcare administrators and academic healthcare researchers. The project has been presented at a PAG meeting (June 2023) for initial discussions about the general project theme and feedback on how to present to other audiences for the best communication. HDR UK PPIE are a group formed of the general public who have volunteered to review HDR UK PhD projects and give feedback. This feedback focuses on identifying aspects of a project which might have been overlook by involved academics, and helps to give a broader context for healthcare research.

Together, and through future engagement, these public/patient engagement groups will help refine the project’s scope to best deliver benefit for public healthcare, ensure rigorous ethical use of data is considered, and the context of the project is always viewed in a way which allows scrutiny from academics and non-technical parties.

No data will flow to NHS England for the purposes of this Data Sharing Agreement (DSA).

NHS England will grant access to the Uncurated Low Latency Hospital Data Sets - Emergency Care data via the Secure Data Environment (SDE). The SDE is a secure data and research analysis platform. It allows approved researchers with approved projects access to pseudonymised data and industry-leading analytics tools.

NHS England will provide access to the relevant records from the Uncurated Low Latency Hospital Data Sets - Emergency Care to the University of Birmingham. The Data will:

• Contain special categories of personal data but with no direct identifying data items. The Data will be pseudonymised and individuals cannot be reidentified through linkage with other data in the possession of the recipient.

SDE users can request exportation of aggregated analysis results (suppressed and summarised according to the NHSE SDE Disclosure Control rules) subject to review and approval by the NHS England SDE Output Checking team. The SDE Output Checking team will ensure that no output contains information which could be used either on its own or in conjunction with other data to breach an individual's privacy.

Users must identify themselves via a multi-factor authentication mechanism and are only able to access the datasets detailed within this DSA. The access and use of the system is fully auditable, and all users must comply with the use of the Data as specified in this DSA.

Users are only authorised to access the Data specified in this DSA and can utilise a variety of analytical tools available within the SDE platform. Users are not permitted to export record-level data from the SDE.

The Data will not be transferred to any other location.

The Data will be stored on servers at NHS England.

The Data will not be transferred to any other location.

The Data will be accessed by authorised personnel via remote access.

The Controller(s) must confirm and provide evidence upon audit by NHS England that access via any remote device complies with the data security obligations within this DSA and the Data Sharing Framework Contract.

For remote access:

- Remote access will only be from secure locations situated within the territory of use (as further restricted elsewhere within the DSA if so done) stated within this DSA;

- Access controls granting users the minimum level of access required are in place;

- Remote access is only via secure connections (e.g., VPNs or secure protocols) to protect data;

- Multifactor authentication (MFA) is required for remote access;

- Device security, including up-to-date software and operating systems, antivirus software, and enabled firewalls are utilised for the remote access;

- All remote access is undertaken within the scope of the organisation’s DSPT (or other security arrangements as per this DSA) and complies with the organisation’s remote access policy.

The above applies in addition to any condition set out elsewhere within the DSA (e.g. who may carry out processing, and for what purpose).

The Data will not leave England/Wales at any time.

Access is restricted to students at the University of Birmingham who have authorisation from the Principal Investigator.

All personnel accessing the Data have been appropriately trained in data protection and confidentiality.

The Data will not be linked with any other data.

There will be no requirement and no attempt to reidentify individuals when using the Data.

Analysts from the University of Birmingham will analyse the Data for the purposes described above.

The expected outputs of the processing will be:

> Submissions to peer reviewed journals such as Springer Link Process Science, Foundations and Trends in Systems and Control and Management Science. 2-3 journal submissions are expected.

> Presentations at appropriate conferences such as International Conference on Process Mining, Information Processing in Sensor Networks and Institute of Electrical and Electronics Engineers (IEEE) International Conference on Data Mining

> Production of new programming and theoretical framework tools which will be made available publicly. These tools can be used for the analysis and description of patient flows to provide recommendations for emergency care service redesign improvement and will be free of charge.

> Internal channels and policy groups, such as the urgency and emergence care transformation programme and elective care

> Press releases by the University of Birmingham, Health Data Research UK (HDR UK) and NHS England for appropriate results, for example, via formal web publications or technical blogs. This includes lay descriptions of the project and its results for use in public discourse

The outputs will not contain NHS England Data and will only contain aggregated information with small numbers suppressed as appropriate in line with the relevant disclosure rules for the dataset(s) from which the information was derived.

Production of outputs are expected to be by September 2027, with completed results before that date if available.

As a new and novel research project, benefits and their measurements will be subject to ongoing research input. The project outputs are anticipated to help evaluate new tools for secondary healthcare improvement. If successful, the new tools can help to understand patient flows within an emergency department, anticipate peak patient attendance times and case mix and potential new recommendations for changes in patient flows (e.g. diagnosis, treatments, investigations).

NHS trusts could realise organisational improvements, such as:

1. Resource management improvement (e.g. bed use, patient flow)

2. Improved efficiency (e.g. staff per patient)

3. Most effective use of staff levels

4. Data driven approaches to improving service delivery

5. More detailed cost benefit analysis of patient experience and outcomes

The wider health and social care system improvements would stem from better emergency care outcomes:

1. Greater hospital capacity for emergency care

2. Reduced expenditure on most costly interventions

3. Tangible and interpretable models which can be scrutinised by operational managers and clinical experts

4. Reduction of emergency bed use and readmissions

Notable benefits for arm's length bodies, policy makers and decision makers include:

1. The development of a data driven evidence base for analysing performance and recommending new best practice

2. Ability to scrutinise trusts practices and outcomes, particularly being able to recommend achievable transformations bey proposing a sequence of service changes

3. The development of event simulation models for process redesign, which would build evidence for policy changes and impacts of change

4. National health bodies, such as the Department of Health and Social Care, NHS England, NICE and Integrated Care Boards (ICB) could use this work for management of healthcare policies and recommendations for improving best practices

5. National and local healthcare leaders are expected to be able to understand better vs worse NHS trust performance, including accounting for geographical/ demographic differences between trusts

6. Service process models could help to develop new policy and guidance with a more nuanced and locally developed view

The use of the data could:

> help the system to better understand the health and care needs of populations.

> lead to the identification or improvement of treatments or interventions, or health and care system design to improve health and care outcomes or experience.

> advance understanding of regional and national trends in health and social care needs.

> advance understanding of the need for, or effectiveness of, preventative health and care measures for particular populations or conditions such as obesity and diabetes.

> inform planning health services and programmes, for example to improve equity of access, experience and outcomes.

> provide a mechanism for checking the quality of care. This could include identifying areas of good practice to learn from, or areas of poorer practice which need to be addressed.

> support knowledge creation or exploratory research (and the innovations and developments that might result from that exploratory work).

Patients are ever more reliant on efficient and effective healthcare. The dissemination of this data will help national and local organisation managers and clinicians deliver these outcomes. Potential benefits for patients are therefore expected to be recommendations for and implementation of service improvements. These improvements will help NHS trusts utilise current resources more efficiently and identify better best practice. Benefits for patients could include:

1. Lower waiting times

2. Better potential outcomes

3. Reduced unnecessary follow-up appointments

4. Improved bed capacity

The intention is that the new tools that are to be produced as part of this project could be used for the analysis and description of patient flows to provide recommendations for emergency care service redesign improvement. Such recommendations could form part of decision support tools for the management of hospital services: staff scheduling, patient demand management and official guideline conformance checking.

This project aims to inform new guidance at local and national levels, integrate operational knowledge from NHS England’s Performance Analysis team (UEC), and disseminate new recommendations to analysts, researchers, and policy makers.

Public interaction via established public/ patient engagement groups will be used to help promote and develop outputs. The University of Birmingham will provide access to existing channels, such as the OPTIMAL research project patient advisory group (PAG).

The project team will disseminate the findings of this exploration of best practices in emergency care delivery through patient advisory groups, arm's length bodies (NHS England) and healthcare research communities (University of Birmingham).

Access to data was only granted a few months ago so preliminary investigations are still ongoing.

Future benefits from previous application are anticipated to be:

As a new and novel research project, benefits and their measurements will be subject to ongoing research input. The project outputs are anticipated to help evaluate new tools for secondary healthcare improvement. If successful, the new tools can help to understand patient flows within an emergency department, anticipate peak patient attendance times and case mix and potential new recommendations for changes in patient flows (e.g. diagnosis, treatments, investigations).

NHS trusts could realise organisational improvements, such as:

1. Resource management improvement (e.g. bed use, patient flow)

2. Improved efficiency (e.g. staff per patient)

3. Most effective use of staff levels

4. Data driven approaches to improving service delivery

5. More detailed cost benefit analysis of patient experience and outcomes

The wider health and social care system improvements would stem from better emergency care outcomes:

1. Greater hospital capacity for emergency care

2. Reduced expenditure on most costly interventions

3. Tangible and interpretable models which can be scrutinised by operational managers and clinical experts

4. Reduction of emergency bed use and readmissions

Notable benefits for arm's length bodies, policy makers and decision makers include:

1. The development of a data driven evidence base for analysing performance and recommending new best practice

2. Ability to scrutinise trusts practices and outcomes, particularly being able to recommend achievable transformations bey proposing a sequence of service changes

3. The development of event simulation models for process redesign, which would build evidence for policy changes and impacts of change

4. National health bodies, such as the Department of Health and Social Care, NHS England, NICE and Integrated Care Boards (ICB) could use this work for management of healthcare policies and recommendations for improving best practices

5. National and local healthcare leaders are expected to be able to understand better vs worse NHS trust performance, including accounting for geographical/ demographic differences between trusts

6. Service process models could help to develop new policy and guidance with a more nuanced and locally developed view

The use of the data could:

> help the system to better understand the health and care needs of populations.

> lead to the identification or improvement of treatments or interventions, or health and care system design to improve health and care outcomes or experience.

> advance understanding of regional and national trends in health and social care needs.

> advance understanding of the need for, or effectiveness of, preventative health and care measures for particular populations or conditions such as obesity and diabetes.

> inform planning health services and programmes, for example to improve equity of access, experience and outcomes.

> provide a mechanism for checking the quality of care. This could include identifying areas of good practice to learn from, or areas of poorer practice which need to be addressed.

> support knowledge creation or exploratory research (and the innovations and developments that might result from that exploratory work).

Patients are ever more reliant on efficient and effective healthcare. The dissemination of this data will help national and local organisation managers and clinicians deliver these outcomes. Potential benefits for patients are therefore expected to be recommendations for and implementation of service improvements. These improvements will help NHS trusts utilise current resources more efficiently and identify better best practice. Benefits for patients could include:

1. Lower waiting times

2. Better potential outcomes

3. Reduced unnecessary follow-up appointments

4. Improved bed capacity

The intention is that the new tools that are to be produced as part of this project could be used for the analysis and description of patient flows to provide recommendations for emergency care service redesign improvement. Such recommendations could form part of decision support tools for the management of hospital services: staff scheduling, patient demand management and official guideline conformance checking.

This project aims to inform new guidance at local and national levels, integrate operational knowledge from NHS England’s Performance Analysis team (UEC), and disseminate new recommendations to analysts, researchers, and policy makers.

Public interaction via established public/ patient engagement groups will be used to help promote and develop outputs. The University of Birmingham will provide access to existing channels, such as the OPTIMAL research project patient advisory group (PAG).

The project team will disseminate the findings of this exploration of best practices in emergency care delivery through patient advisory groups, arm's length bodies (NHS England) and healthcare research communities (University of Birmingham).