Breaking binary in cardiovascular disease risk prediction

Abstract

Atherosclerotic cardiovascular disease (ASCVD) remains the leading cause of death in the world. However, advances in genetics, omics research, machine learning (ML), and precision medicine have inspired revolutionary new tools in ASCVD risk stratification. Together, polygenic risk scores (PRS) and composite ML-based algorithms help shift the paradigm away from binary predictions towards more comprehensive continuum models. Continued efforts are needed to address socioeconomic and racial disparities in the PRS space.