Predicting Incident Heart Failure from Population-based Nationwide Electronic Health Records: Protocol for a Model Development and Validation Study

Heart failure (HF) is increasingly common and associated with excess morbidity, mortality and healthcare costs. New medications are now available which can alter the disease trajectory and reduce clinical events. However, many cases of HF remain undetected until presentation with more advanced symptoms, often requiring hospitalisation. Earlier identification and treatment of HF could reduce downstream healthcare impact, but predicting HF incidence is challenging due to the complexity and varying course of HF. The investigators will use routinely collected hospital-linked primary care data and focus on the use of artificial intelligence methods to develop and validate a prediction model for incident HF. Using clinical factors readily accessible in primary care, the investigators will provide a method for the identification of individuals in the community who are at risk of HF, as well as when incident HF will occur in those at risk, thus accelerating research assessing technologies for the improvement of risk prediction, and the targeting of high-risk individuals for preventive measures and screening.