New York: A new study by U.S. researchers has shown that an advanced artificial intelligence (AI) algorithm can more accurately identify patients at risk for hypertrophic cardiomyopathy (HCM)—a serious and often undiagnosed heart condition.
The algorithm, known as Viz HCM, was previously approved by the U.S. Food and Drug Administration (FDA) for detecting signs of HCM using electrocardiograms (ECGs). Now, in findings published in the journal NEJM AI, scientists at Mount Sinai have upgraded the tool to deliver personalized probability scores instead of generic alerts.
Rather than simply labeling results as “suspected HCM,” the algorithm can now give a more detailed assessment—such as “You have a 60 percent chance of having HCM,” said Joshua Lampert, Director of Machine Learning at Mount Sinai Fuster Heart Hospital.
This level of precision can help identify at-risk patients earlier and lead to faster diagnoses and preventative treatment, especially in young individuals vulnerable to sudden cardiac death.
“This is a significant step in bringing advanced AI into real-world clinical settings,” said Lampert, who is also an Assistant Professor of Medicine at the Icahn School of Medicine at Mount Sinai. “Doctors can now prioritize patients more effectively by using tools that highlight those most at risk.”
Hypertrophic cardiomyopathy affects approximately 1 in 200 people worldwide and is a leading cause of heart transplants. Many patients remain unaware of their condition until symptoms emerge—often at an advanced stage.
Co-senior author Dr. Girish N. Nadkarni, Chair of the Windreich Department of Artificial Intelligence and Human Health at Mount Sinai, emphasized the importance of integrating AI thoughtfully. “This study is a strong example of responsible AI integration in healthcare,” he said. “It shows how AI can meaningfully enhance patient care without replacing the physician's expertise.”
