Calibrated AI tool accurately identifies hypertrophic cardiomyopathy risk

The Viz HCM algorithm had previously been approved by the US Food and Drug Administration for the detection of HCM on an electrocardiogram (ECG). In a study published in NEJM AI, researchers from Mount Sinai Hospital in New York assigned numeric probabilities to the algorithm’s findings.

The algorithm might previously have said ‘flagged as suspected HCM’ or ‘high risk of HCM,’ but the Mount Sinai study allows for interpretations such as, ‘You have about a 60 per cent chance of having HCM,’ said corresponding author Joshua Lampert, MD, director of Machine Learning at Mount Sinai Fuster Heart Hospital.

Consequently, patients who had not previously been diagnosed with HCM may be able to get a better understanding of their individual disease risk, leading to a faster and more individualised evaluation, along with treatment to potentially prevent complications such as sudden cardiac death.

“This is an important step forward in translating novel deep-learning algorithms into clinical practice by providing clinicians and patients with more meaningful information,” Dr Lampert said in a statement. “Clinicians can improve their clinical workflows by ensuring the highest-risk patients are identified at the top of their clinical work list using a sorting tool. Patients can be better counselled by receiving more individualised information through model calibration which improves interpretability of model classification scores.”