NHS Digital Data Release Register - reformatted
Milton Keynes University Hospital NHS Foundation Trust projects
10 data files in total were disseminated unsafely (information about files used safely is missing for TRE/"system access" projects).
FINESSE database outcome study - NHS England Linkage project — DARS-NIC-662451-S5L8J
Type of data: information not disclosed for TRE projects
Opt outs honoured: Anonymised - ICO Code Compliant, Yes (Section 251 NHS Act 2006)
Legal basis: Health and Social Care Act 2012 s261(2)(a); National Health Service Act 2006 - s251 - 'Control of patient information'.
Purposes: No (NHS Trust)
Sensitive: Sensitive, and Non-Sensitive
When:DSA runs 2023-10-10 — 2025-10-09 2024.02 — 2024.04.
Access method: One-Off
Data-controller type: MILTON KEYNES UNIVERSITY HOSPITAL NHS FOUNDATION TRUST
Sublicensing allowed: No
Datasets:
- Civil Registrations of Death
- Hospital Episode Statistics Admitted Patient Care (HES APC)
Objectives:
Milton Keynes University Hospital NHS Foundation Trust (MKUH NHS FT) requires access to NHS England data for the purpose of developing the "Artificial Intelligence Stress Echo (FINESSE)" project database.
The following is a summary of the aims of the research project provided by MKUH NHS FT:
Stress echocardiography (SE) using a pharmacological agent (dobutamine) is a bedside test which patients tolerate well and is accurate. It shows any problems with the motion of the heart wall when resting and during exercise (which is imitated by dobutamine administration). Currently published research using SE have been incorporating all types of SE and has an average follow up of 2.5 years with a maximum follow up of 5 years.
The aim of the project is to develop a predictive model for chest pain sufferers based on their clinical characteristics, risk factor profiles, and the outcome of their SE, which was part of the patients standard care investigations. The required and collected information is known as major cardiovascular events (MACE) and includes all cause death and non-fatal heart attack over the intermediate and long term.
The proposed project is part of a larger longitudinal research study started in 2019, which looked at all-cause mortality without addressing the major cardiovascular events (MACE) in a 2,667 cohort of dobutamine SE patients. Data was collected between 1995-2012 for this study. This current proposal for a 15-year follow-up of the same cohort will provide more robust outcome data and give greater validity to the research and the prediction model is expected to be more accurate.
Additionally, the Research Group (RG) will utilise machine learning (ML) to develop an objective model that may be able to partially automate the diagnosis. Improving diagnostic accuracy will potentially reduce diagnostic or treatment costs. The model will be developed based on clinical variables (cardiovascular risk factors, co-morbidities, prescribed medications, and patients' demographics and anthropometrics (human body measurements)) in addition with the SE results (blood supply problem detection to the heart muscle, with measuring the motion problems induced by it, also known as wall motion score index). Developing an accurate predictive model for MACE is expected to lead to better and more accurate multi-facetted diagnosis and a reduced need for diagnostic procedures such as coronary angiography therefore reducing pressure on the NHS.
The data for the algorithm used at this stage is for research purposes only and will not be used for clinical purposes or decision making or affect any patient treatments or investigations.
The following NHS England data will be accessed:
> Hospital Episode Statistics (HES): Admitted Patient Care (APC) necessary to provide information on diagnostic and treatment or operation procedure information, hospital admission with non-fatal myocardial infarction unplanned revascularisation surgery or stent procedures (>6 months after SE), stroke events, event dates.
> Civil Registrations of Death necessary to provide information on date and cause of death, which is required to complete analysis.
The level of the data will be:
> Pseudonymised
The data will be minimised as follows:
> Limited to a study cohort identified by Milton Keynes University Hospital NHS Foundation Trust the cohort includes 2,667 patients aged 18 years and above, who underwent SE for chest pain assessment, whose identifiers are held on the FINESSE Stress Echocardiography research database. All SE for the cohort were performed at Milton Keynes University Hospital (MKUH) by a single Cardiologist over a 15-year period (between October 2002 - 2017).
> Limited to data between October 2002 latest available. For each individual patient, HES data will only be provided from the date of their Stress Echocardiography surgery and until up to 15 years after their surgery. For each individual patient, deaths data will only be processed from the date of their Stress Echocardiography surgery and until up to 15 years after their surgery. This means some patients will be followed up for the maximum 15 years, and others for only ~5 years. The data requested spans over a 21-year period to capture follow-up for patients whose SE was conducted more recently.
> Limited to conditions relevant to the study identified by specific ICD-10 and OPCS-4 codes
> Limited to England and Wales. The geographical spread of data required is patients who have undergone SE registered at Milton Keynes University Hospital, but over the 15-year followup period, these patients may have moved from the region or may have died. NHS England data is required as it is unfeasible to trace all data subjects due to the time elapsed since some of the patients underwent their SE and the study design does not incorporate direct contact with patients or service users specifically.
MKUH NHS FT is the data controller as the organisation responsible for ensuring that the data will only be processed for the purpose described above.
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 data processing is in the public interest because the data will be used to develop an algorithm to develop a cardiovascular outcomes prediction model which is expected to benefit patients who may have a heart condition.
The funding is provided by MKUH NHS FT. The funding is for the department and is not specifically limited to the study described.
Open University is a processor acting under the instructions of MKUH NHS FT. Open Universitys role is limited to analysis of data for predictive modelling and data analysis. MKUH NHS FT use Cloud based processing. Microsoft UK provide Cloud Services for MKUH NHS FT and are therefore listed as a processor.
There was some patient and public involvement (PPI) conducted prior to the study where a meeting was held with patient representatives to discuss the FINESSE project background, current status, protocol, further plans and collaboration. Participants fed back that there was an understanding of the necessity of the linkage to NHS England with no concerns raised and it was acknowledged that the study could give better guidance into people at risk, giving confidence in improving diagnosis. Communication to the public will continue by notification of the research that has been done and the outcomes of that research. This will be conducted on an annual basis.
Data will be accessed by a PhD student of the University Of Leicester who holds an honorary contract with MKUH NHS FT. The individual will act as an agent of MKUH NHS FT at all times under supervision from employees of MKUH NHS FT. Aside from this individual, access is restricted to employees or agents of MKUH NHS FT and Open University who have authorisation from the Principal Investigator.
Expected Benefits:
The findings of this research study are expected to provide the following benefits:
1. The algorithm will not be used at this stage for clinical purpose or decision-making. However, if the algorithm proves to be a useful tool for this use, the algorithm may ultimately be used for communicating research and development of predictive models to aid clinical decision making on patient pathways (diagnosis and treatment) will be of interest to clinicians, health economists, patient groups and the general public.
2. Clinicians are expected to be able to better predict and utilise diagnostic resources which could increase capacity within Trusts to diagnose and treat patients.
3. The benefits of processing for this project are expected to expand the dataset and therefore the modelling and prediction model will be more accurate.
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 the need for, or effectiveness of, preventative health and care measures for cardiovascular diseases.
> Inform planning health services and programmes, for example to improve equity of access, experience and outcomes.
Providing a targeted and personalised approach to medicine and communicating the results could help patients to have better understanding of their condition and increased choice of their treatments.
The prediction models are hoped to allow for more accurately patient outcomes due to coronary artery disease and is expected to help reduce the use of invasive diagnostic and therapeutic procedures such as percutaneous coronary intervention. This will give clinicians and patients more choice. The clinician may decide using the prediction model developed on the base of probability to treat the patient more conservatively therefore reducing patient interventions, freeing up NHS diagnostic time and clinician time and reducing cost which can be utilised elsewhere within the NHS.
Outputs:
The expected outputs of the processing will be:
> A report of findings to Milton Keynes University Hospital Research and Development committee at the end of the study
> Submissions to peer reviewed journals; (online and paper) e.g., journal of Cardiology. At least 2 submissions are expected.
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.
The outputs will be communicated to relevant recipients through the following dissemination channels:
> Journals
> Conference talks; e.g., European Society of Cardiology (ESC), American College of Cardiology (ACC), American Heart Association (AHA) and British Cardiovascular Society (BCS)
> Communication of results to local research networks and Academic Health Science Networks
> Forum for discussion with other healthcare professionals
> Posters displayed at presentations / meetings with other researchers
> Public promotion of the research to patient representative groups; e.g., NIHR Patient Group representatives and Trust Patient Representatives
> Education Outreach; via local hospital newsletters, MKUH members forum talks and patient groups
> Communications department at MKUH internal and external communications
> Social Media: LinkedIn
The research findings will be communicated using a targeted approach for the scientific community to ensure that the findings are communicated in a transparent and contextual manner.
Communication will be tailored for individuals such as patients and patient groups to explain the context of the findings in relation to individual conditions and plain language principles are applied.
The target dates to produce the outputs are:
(1) Interim analysis expected: February 2024
Dissemination via Abstract publication, internal publication via R&D committee.
(2) Final analysis expected: June 2024
Dissemination via Peer reviewed publication, internal and external dissemination via R&D committee, Academic Health Science Network (AHSN), Patient groups as appropriate.
Processing:
Milton Keynes University Hospital NHS Foundation Trust (MKUH NHS FT) will transfer data to NHS England. The data will consist of identifying details (specifically NHS Number, Date of Birth and a unique research ID) for the cohort to be linked with NHS England data. The identifiers held by MKUH NHS FT will be securely destroyed after the cohort identifying details have been sent to NHS England.
NHS England data will provide the relevant records from the HES APC and Civil Registrations of Death datasets to MKUH NHS FT. The data will contain no direct identifying data items but will contain a unique person ID which can be used to link the data with other record level data already held by the recipient.
MKUH NHS FT will securely transfer the pseudonymised data to the Open University for subsequent stages of the research study which uses predictive modelling and data analysis. After analysis the data will be returned to MKUH NHS FT.
The data will be stored on servers at the Open University.
MKUH NHS FT stores Data on the Cloud provided by Microsoft Limited.
The Data will be accessed onsite at the premises of MKUH NHS FT and Open University.
The Data will also be accessed by authorised personnel of MKUH MHS FT via remote access of the Data held on the servers at MKUH NHS FT.
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;
- Personnel are both prohibited and technically prevented from downloading or copying NHSE data to local devices;
- 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 organisations DSPT (or other security arrangements as per this agreement) and complies with the organisations 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).
Remote processing will be from secure locations within England/Wales. The data will not leave England/Wales at any time.
Access is restricted to employees or agents of MKUH NHS FT and Open University.
All personnel accessing the Data have been appropriately trained in data protection and confidentiality.
The NHS England Data will be linked to the main database using only the unique research ID. The data will not be linked with any other data.
The current research database contains the following data;
> Patient Identifiable Data (Name, Date of Birth, Hospital ID) these identifiers will be destroyed after submission of the cohort, but before receipt of the NHS England Data
> Baseline demographic data (Gender, Age, Cardiovascular risk factors, past medical history)
> Details of stress Echo findings (wall motion score index at rest and during peak stress)
> Some Outcome data after SE - further investigation, re-admission with chest pain and intervention such as cardiac stenting procedure or bypass surgery.
Upon receipt of the NHS England Data, all patient identifiable data will be removed from the database. Only this pseudonymised database will be used for subsequent stages of the study. Date of death will be converted to month and year of death only. All analyses will use the pseudonymised dataset. There will be no requirement and no attempt to reidentify individuals when using the pseudonymised dataset.
Researchers from the clinical research group at MKUH NHS FT will analyse the data for the purposes described above.
Analysts from the Open University will use the pseudonymised data to conduct predictive modelling and data analysis.