The BHF-Turing Cardiovascular Data Science Awards (Second Call): Post myocardial infarction disease trajectories: process mining of 145 million hospitalised events (joint funding with The Alan Turing Institute)

Although cardiovascular disease remains the global leading cause of death, in recent decades, survival following myocardial infarction (MI) has improved dramatically.

Increased MI survivorship is associated with an increased risk of recurrent events and the development of other diseases.

To date, data about post MI disease risks have been limited to small numbers of a priori defined conditions or have used unsophisticated methods which do not take important sequential and temporal information into account.

Therefore, we aim to use hypothesis-free, data-driven methods, to investigate the full spectrum of post-MI disease trajectories using large scale nationwide hospital data.

To handle the breadth and depth of such national data, combined with the complexity of assessing not only all possible hospital diagnosis, but also the sequences in which they occur, we will investigate the application of process mining techniques.

Characterising the incidence and nature of post-MI disease trajectories across all hospitalisations without restriction to a pre-determined list of outcomes will provide a new understanding of disease progression and lead to the discovery novel disease pathways.

This could, identify areas in which either consolidation or development of new pharmacotherapies are required, and identify opportunities for the interruption or prevention of the adverse post-MI pathways.