An artificial intelligence (AI) algorithm has been calibrated by a team of US researchers studying hypertrophic cardiomyopathy (HCM), a type of heart disease, to more quickly and precisely identify patients with the condition and flag them as high risk for extra attention during doctor’s appointments.

The Food and Drug Administration (FDA) has previously authorized the algorithm, called Viz HCM, for the identification of HCM on an electrocardiogram (ECG).

The results of the algorithm are given numerical probabilities by the Mount Sinai research, which was published in the journal NEJM AI.

Joshua Lampert, Director of Machine Learning at Mount Sinai Fuster Heart Hospital, stated that the Mount Sinai study permits interpretations like “You have about a 60 percent chance of having HCM,” even though the algorithm might have previously said “flagged as suspected HCM” or “high risk of HCM.”

Patients who had not previously received a diagnosis of HCM might be better able to understand their personal risk for the disease, which could result in a quicker and more customized evaluation and treatment to potentially avoid complications like sudden cardiac death, particularly in younger patients.

By giving patients and physicians more insightful data, this is a significant advancement in integrating cutting-edge deep learning algorithms into clinical practice.

According to Lampert, Assistant Professor of Medicine (Cardiology, and Data-Driven and Digital Medicine) at the Icahn School of Medicine at Mount Sinai, “clinicians can enhance their clinical workflows by making sure the highest-risk patients are identified at the top of their clinical work list using a sorting tool.”

HCM is a major cause of heart transplants and affects one in 200 persons globally.

However, the illness may have be advanced by the time symptoms appear, and many individuals are unaware that they have the ailment.

As the director of the Hasso Plattner Institute for Digital Health and chair of the Windreich Department of Artificial Intelligence and Human Health, co-senior author Girish N. Nadkarni said, “This study reflects pragmatic implementation science at its best, demonstrating how we can responsibly and thoughtfully integrate advanced AI tools into real-world clinical workflows.”