Healthcare regulators and organisations in the UK and the US have partnered to build artificial intelligence (AI) and machine learning (ML) models which can predict heart disease.

The Veterans Cardiac Health and AI Model Predictions (V-CHAMPs) Challenge uses synthetic datasets based on real US veteran health records.

Organisations taking part in the research include the FDA Digital Health Center of Excellence, precisionFDA (part of the FDA’s Office of Digital Transformation) and the Medicines and Healthcare products Regulatory Agency (MHRA).

The research will explore a range of outcomes following heart failure including hospital readmission rates and mortality.

The results will enable health systems in the US and UK to improve their understanding of cardiovascular risks as well as increasing understanding of synthetic data and AI/ML models and how they could be used to explore similar topics in the future, said the MHRA.

In the US, cardiovascular diseases such as heart failure, heart attacks, strokes, and peripheral artery disease are the leading cause of hospitalisation for veterans and a major cause of disability.

Paul Campbell, interim head of software at the MHRA, said: “This is a unique chance for any developer or team to get involved, challenge themselves against other experts across the globe, all while contributing towards a worthy goal.

“Having access to hi-fidelity synthetic datasets will be a game-changer in this space, offering an opportunity for participants to test the potential of synthetic data to its limits.”

Share Story: