AI Algorithm Enhances Identification of High-Risk Heart Patients: Research

Synopsis

A new study reveals how an AI algorithm can accurately identify high-risk patients with hypertrophic cardiomyopathy (HCM), allowing for better patient understanding and management of heart disease risks. This advancement could lead to improved clinical workflows and outcomes.

Key Takeaways

AI algorithm identifies high-risk heart patients.
Refined interpretations of HCM risk probabilities.
Patients gain insights into their disease risks.
Potential to prevent serious health complications.
Integration of AI tools into clinical practices is crucial.

New York, April 22 (IANS) A group of researchers from the United States, focused on a heart condition called hypertrophic cardiomyopathy (HCM), announced on Tuesday that they have refined an artificial intelligence (AI) algorithm to swiftly and accurately identify individuals with this condition, marking them as high-risk for enhanced attention during medical consultations.

The algorithm, referred to as Viz HCM, had previously received approval from the Food and Drug Administration (FDA) for identifying HCM via an electrocardiogram (ECG).

The research from Mount Sinai, published in the journal NEJM AI, provides numeric probabilities based on the algorithm's assessments.

For instance, instead of merely stating “flagged as suspected HCM” or “high risk of HCM,” the Mount Sinai findings enable interpretations such as, “You have approximately a 60 percent chance of having HCM,” according to Joshua Lampert, Director of Machine Learning at Mount Sinai Fuster Heart Hospital.

This advancement allows patients who have not yet been diagnosed with HCM to gain a clearer perspective on their individual disease risk, facilitating a quicker and more tailored evaluation, as well as treatment options that could avert complications such as sudden cardiac death, particularly in younger individuals.

“This represents a significant advancement in bringing innovative deep-learning algorithms into clinical settings by equipping both clinicians and patients with more substantial information. Clinicians can enhance their workflows by prioritizing the highest-risk patients on their clinical task list using a sorting mechanism,” stated Lampert, who is also an Assistant Professor of Medicine (Cardiology, and Data-Driven and Digital Medicine) at the Icahn School of Medicine at Mount Sinai.

HCM affects one in every 200 people globally and is a primary cause of heart transplants. Unfortunately, many individuals remain unaware of their condition until symptoms arise, often when the disease has progressed significantly.

“This research exemplifies exceptional pragmatic implementation science, showcasing how we can responsibly and thoughtfully incorporate cutting-edge AI tools into everyday clinical practices,” remarked Girish N Nadkarni, co-senior author, Chair of the Windreich Department of Artificial Intelligence and Human Health, and Director of the Hasso Plattner Institute for Digital Health.