US Researchers Develop AI Algorithm to Improve Detection of Hypertrophic Cardiomyopathy (HCM)
A team of US researchers has developed an innovative artificial intelligence (AI) algorithm aimed at improving the detection and diagnosis of hypertrophic cardiomyopathy (HCM), a type of heart disease that affects millions worldwide. The algorithm, named Viz HCM, has been calibrated to more quickly and accurately identify patients with the condition, enabling clinicians to prioritize high-risk cases for further evaluation during doctor’s appointments.
The Viz HCM algorithm had previously received approval from the Food and Drug Administration (FDA) for detecting HCM on electrocardiograms (ECGs). However, the latest study from Mount Sinai researchers, published in NEJM AI, takes the technology a step further by providing numeric probabilities to its findings, enhancing its clinical utility.
Joshua Lampert, Director of Machine Learning at Mount Sinai’s Fuster Heart Hospital, explained the development: “While the algorithm previously flagged cases as ‘suspected HCM’ or ‘high risk,’ our study enables more specific interpretations. For instance, it could now say, ‘You have about a 60 percent chance of having HCM.’ This added precision can offer patients a clearer understanding of their disease risk.”
This advancement has the potential to transform the way HCM is identified, particularly for individuals who have not been diagnosed with the condition but may be at risk. By providing a more individualized assessment, the algorithm can expedite diagnosis and help clinicians deliver targeted treatment to prevent serious complications such as sudden cardiac death, particularly in younger patients.
“This is an important step forward in translating novel deep-learning algorithms into clinical practice by providing clinicians and patients with more meaningful information,” Lampert said. “Clinicians can streamline their workflows by ensuring that the highest-risk patients are prioritized in their clinical schedules using a sorting tool.”
HCM is a leading cause of heart transplantation and affects approximately one in 200 people worldwide. However, many patients remain undiagnosed until the disease has progressed and symptoms appear. The AI-powered tool aims to bridge this gap, offering earlier detection and more proactive management.
“This study reflects pragmatic implementation science at its best,” said Girish N. Nadkarni, co-senior author of the study and Chair of the Windreich Department of Artificial Intelligence and Human Health. “It demonstrates how advanced AI tools can be responsibly and thoughtfully integrated into real-world clinical workflows to improve patient outcomes.”
With its potential to significantly impact patient care, the Viz HCM algorithm marks a promising development in the intersection of AI and cardiology, offering a more efficient and personalized approach to managing heart disease.
