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.”
MORE FROM MEDICAL & HEALTHCARE
According to Mount Sinai, HCM effects one in 200 people globally and is a leading reason for heart transplantation, but many patients do not know they have the condition until they have symptoms and the disease may already be advanced.
The Mount Sinai researchers ran the Viz HCM algorithm on nearly 71,000 patients who had an electrocardiogram between March 7, 2023, and January 18, 2024. The algorithm flagged 1,522 as having a positive alert for HCM. The researchers reviewed the records and imaging data to confirm which patients had a confirmed HCM diagnosis.
After reviewing the confirmed diagnoses, researchers applied model calibration to the AI tool to assess whether the calibrated probability of having HCM correlated with the actual likelihood of patients having the disease. They found that the calibrated model did give an accurate estimate of a patient’s likelihood of having HCM.
“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,” said co-senior author Girish N. Nadkarni, MD, MPH. “It’s not just about building a high-performing algorithm—it’s about making sure it supports clinical decision-making in a way that improves patient outcomes and aligns with how care is actually delivered. This work shows how a calibrated model can help clinicians prioritise the right patients at the right time, and in doing so, help realise the full potential of AI in medicine.”
Radio wave weapon knocks out drone swarms
Probably. A radio-controlled drone cannot be completely shielded to RF, else you´d lose the ability to control it. The fibre optical cable removes...