NEW YORK — Scientists at Mount Sinai have refined an artificial intelligence (AI) tool to more accurately detect a serious heart condition known as hypertrophic cardiomyopathy (HCM). This upgraded algorithm is designed to help doctors quickly identify high-risk patients and provide more personalized care.
The enhanced AI system, called Viz HCM, was previously approved by the U.S. Food and Drug Administration to detect signs of HCM using electrocardiograms (ECGs). Now, researchers have improved the tool’s ability to assign specific risk levels, offering more detailed assessments. The findings were published on April 22 in the journal NEJM AI.
“Instead of simply flagging someone as a potential HCM case, the algorithm can now estimate a patient’s likelihood of having the disease — for example, a 60 percent chance,” explained Dr. Joshua Lampert, Director of Machine Learning at Mount Sinai Fuster Heart Hospital and lead author of the study.
This added layer of detail could help patients better understand their health risks and seek faster evaluations and treatments. It also offers a clearer path to preventing serious complications like sudden cardiac death, particularly among younger individuals.
HCM affects about 1 in 200 people globally. It is a leading cause of heart transplants and often goes undetected until symptoms appear, sometimes when the disease has already progressed.
In the study, researchers tested the Viz HCM tool on nearly 71,000 patients who had ECGs between March 7, 2023, and January 18, 2024. The algorithm flagged 1,522 patients as potentially having HCM. Medical records and imaging data were then reviewed to confirm the diagnoses.
The updated system may lead to earlier detection and targeted care for thousands of patients who might otherwise go undiagnosed.
Related topics:
