Artificial intelligence-assisted automated heart failure detection and classification from electronic health records.

Aims: Electronic health records (EHR) linked to Digital Imaging and Communications in Medicine (DICOM), biological specimens, and deep learning (DL) algorithms could potentially improve patient care through automated case detection and surveillance. We hypothesized that by applying keyword searches to routinely stored EHR, in conjunction with AI-powered automated reading of DICOM echocardiography images and analysing biomarkers from routinely stored plasma samples, we were able to identify heart failure (HF) patients.

Methods And Results: We used EHR data between 1993 and 2021 from Tayside and Fife (~20% of the Scottish population).

Use of Population-Based Health Informatics Research to Improve Care for Patients with Cardiovascular Diseases.

There are common clinical scenarios in chronic heart disease where no randomized controlled data exist to guide management, and it is likely that well-designed observational studies will have to be used to inform clinical practice. Showing the clinical applicability of this type of study design, using record linkage of population electronic health records, we have provided key observational evidence that use of renin-angiotensin-system (RAS) blockers is associated with better outcomes in patients with aortic stenosis and that metformin could be used safely as an antiglycemic drug in patients with diabetes and heart failure. Each of these pieces of underpinning research has made a major contribution to relevant international clinical practice guidelines, helped the Food and Drug Administration in their decision making and changed prescribing practice.