Prediction of incident heart failure using machine learning techniques in men and women with- and without a history of myocardial infarction.
Rationale: Assessment of risk of future heart failure leaves room for improvement. The potential role of a wider set of blood biomarkers than is currently being used for risk prediction, should be clarified. Moreover, sex differences need to be taken into account when assessing risk of heart failure. Finally, heart failure has many causes of which myocardial infarction is a major contributor. In persons with previous myocardial infarction, different risk prediction models are needed.
Aims: We aim to perform sophisticated data analyses on UK biobank participant data to construct prediction models for heart failure. Special attention will be paid to the role of a wide set of blood biomarkers. Sex differences will be taken into account. Separate models will be constructed for persons with and without a history of myocardial infarction.
Project duration: The expected project duration is 36 months.
Public health impact: Heart failure poses a heavy burden on our healthcare system and this burden will increase in the future due to the aging of the population. To lower this burden, accurate prediction of heart failure is warranted. This project is expected to improve prediction of heart failure. Herewith, it carries potential to enable timely and appropriate treatment in an early stage.