Sign In

Communications of the ACM

ACM TechNews

Researchers Construct Computer-Derived Marker for Coronary Artery Disease

View as: Print Mobile App Share:
An visual explanation of coronary artery disease.

The model incorporates hundreds of different clinical features from the electronic health record, and compared it to both an existing clinical score for CAD and to a genetic score for CAD.

Credit: Modern Heart and Vascular

Researchers at the Icahn School of Medicine at Mount Sinai developed a computer-derived marker for coronary artery disease (CAD) using machine learning and clinical data from electronic health records (EHRs), mapping CAD characteristics on a spectrum for the first time.

The machine learning model ISCAD (In Silico Score for Coronary Artery Disease) was trained on 95,935 EHRs from the BioMe Biobank of the Mount Sinai Health System and the U.K. Biobank.

The model includes hundreds of different clinical features, while the existing clinical score for CAD incorporates a much smaller number of predetermined features.

The researchers found the model's probabilities accurately tracked the degree of coronary stenosis, mortality, and complications like heart attack.

From News-Medical Life Sciences
View Full Article


Abstracts Copyright © 2022 SmithBucklin, Washington, DC, USA


No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account