EHR score improves CAD prediction, reclassification

The electronic health record (EHR) score has improved prediction and reclassification for coronary artery disease (CAD), exhibiting its capacity for population health monitoring of short-term CAD risk in large health systems, reveals a recent study.

A team of investigators sought to determine whether an HER score could enhance CAD prediction and reclassification 1 year before diagnosis, beyond conventional clinical guidelines as determined by the pooled cohort equations (PCE) and a polygenic risk score for CAD.

A machine learning framework was applied using clinical features from the EHR in a multiethnic, clinical care cohort (BioMe), including 555 CAD patients and 6,349 control participants, and in a population-based cohort (UK Biobank), comprising 3,130 CAD patients and 378,344 controls for external validation.

The EHR score resulted in 12-percent better CAD prediction in the BioMe Biobank and 9-percent improved prediction in the UK Biobank compared with the PCE. The EHR score also reclassified 25.8 percent and 15.2 percent of individuals in each cohort, respectively, relative to the PCE.

Larger improvements were observed in the EHR score vs the PCE in a subgroup of individuals with low CAD risk, with 20-percent and 34.4-percent increased discrimination and reclassification, respectively.

Furthermore, the polygenic risk score for CAD in all models failed to improve CAD prediction in comparison to the PCE or EHR score.

“Clinical features from EHRs can be used to build a complementary tool to predict CAD susceptibility,” the investigators said.