Background: Well-created synthetic data establishes a governance risk-free environment for health care algorithm development and experimentation. This includes the evaluation of new treatment models, care management systems, clinical decision support, and more. Synthetic data is of particular use in rare diseases, where real data may be in short supply, or to replicate disease in less common patient demographics (such as certain ethnicities or co-morbid combinations).
Familial hypertrophic cardiomyopathy (HCM) is a rare genetic condition characterized by thickening (hypertrophy) of the cardiac muscle, usually of the interventricular septum. Many affected individuals have no symptoms. Other people may experience chest pain; breathlessness and fainting. Arrhythmias can be life threatening and HCM is associated with an increased risk of sudden death. Some affected individuals develop potentially fatal heart failure, which may require heart transplantation. Approximately 130,000 people have HCM in the UK, but there is a significant burden of undiagnosed disease and diagnostic delay. Inheritance is autosomal dominant, with the most commonly involved genes being MYH7, MYBPC3, TNNT2, and TNNI3.
PIONEER geography: The West Midlands (WM) has a population of 5.9 million and includes a diverse ethnic and socio-economic mix. There is a higher than average percentage of minority ethnic groups and rare diseases including HCM, with a regional specialist HCM service.
Electronic Health Records (EHR): University Hospitals Birmingham NHS Foundation Trust (UHB) is one of the largest NHS Trusts in England, providing direct acute services and specialist care across four hospital sites, with 2.2 million patient episodes per year, 2750 beds and 100 ITU beds. UHB runs a fully electronic healthcare record (EHR) (PICS; Birmingham Systems), a shared primary and secondary care record (Your Care Connected) and a patient portal “My Health”.
Scope: This synthetic dataset reflects the diversity of the WM and the granularity of the HCM service. It replicates longitudinal data including the care journey prior to diagnosis. It includes ECHO provocation, CPEX, ECG including evidence of pre-excitation, as well as symptoms, family history, genetic testing and HCM phenotype. Outcomes and procedures are included.
Available supplementary data: Synthetic Ambulance data. Real HCM patient data, including from secondary and ambulance settings – forming a synthetic algorithm “build” and real “test” datasets.
Available supplementary support: Analytics, Model build, validation and refinement; A.I.; Data partner support for ETL (extract, transform and load) process, Clinical expertise, Patient and end-user access, Purchaser access, Regulatory requirements, Data-driven trials, “fast screen” services.