Investigation into predictors of diagnosis in PAH patients
Research type
Research Study
Full title
Investigation into predictors of diagnosis in PAH patients
IRAS ID
207449
Contact name
Rito Bergemann
Contact email
Duration of Study in the UK
2 years, 0 months, 1 days
Research summary
Literature documents the difficulties with Pulmonary Arterial Hypertension (PAH) diagnosis which involves many different types of clinical tests, and the lengthy time it can take to diagnose the condition from the advent of a patient’s first symptoms. GSK commissioned IMS Health to carry out a retrospective analysis of idiopathic PAH (i.e. PAH with an unknown cause) diagnostic pathways based on NHS Hospital Episode Statistics, whose findings gave cause to believe that there is value in pursuing further analysis. This study aims to build a data environment for analysis in order to; describe the PAH patient population in England, understand the natural history of disease and look for opportunities for improving predictive analytical methods to flag patients for diagnosis earlier.
The study design is a non-interventional retrospective database analysis of a PAH patient cohort based on data from the Pulmonary Vascular Disease Unit at Sheffield Teaching Hospitals NHS Foundation Trust (STHFT) and Hospital Episodes and Statistics (HES) data from the Health and Social Care Information Centre (HSCIC).
This research will be conducted as a joint collaboration between the STHFT, University of Sheffield (UoS), GSK and IMS. The study is expected to be completed within ~15 months, pending research governance and regulatory approvals. The project will be executed by IMS Health and overseen by an analytical committee comprising leading academics in pulmonary hypertension research, and industry employees. Ethics and research governance arrangements will be addressed by suitable approvals and will be guided by STHFT. Dissemination of results will be guided by the analytical committee and if an effective predictive algorithm (i.e. a more effective way of diagnosing patients with the condition) is produced, then efforts will be made to implement this to the benefit of patients and healthcare services.
Summary of results
People affected by pulmonary hypertension (high blood pressure in the lungs) are often diagnosed late when the disease is advanced and less likely to respond to treatment. During the patient journey there are often multiple visits to the doctor and multiple investigations performed with missed opportunities to make the diagnosis. Using artificial intelligence approaches we have shown for the first time that by examining people’s health care behaviour that patients at risk of pulmonary hypertension could potentially be diagnosed earlier.REC name
East Midlands - Derby Research Ethics Committee
REC reference
16/EM/0286
Date of REC Opinion
29 Jul 2016
REC opinion
Further Information Favourable Opinion