An AI algorithm can assess echocardiograms “more rapidly and comprehensively” than experienced cardiologists, according to a new study published in Nature. The video-based model could be a significant upgrade for facilities where human specialists and state-of-the-art technology are unavailable.
“By developing a new machine-learning algorithm for echocardiogram videos, we can comprehensively assess the state of the heart,” co-senior author James Zou, PhD, a biomedical data scientist at Stanford University, said in a statement. “Our model accurately identifies important heart structures and tracks the heart's motion to precisely assess cardiac function.”
The team’s findings could be a game-changer for cardiology, helping specialists assess heart function with more speed and accuracy than ever before. It could also be beneficial in the emergency department, providing a valuable resource for physicians who haven’t been trained to evaluate ejection fraction.
The AI, in other words, could serve as a cardiologist in situations when one isn’t present or lead to high-quality care in areas often limited by a lack of technology.
The researchers did note that their work is far from complete.
“In the future, our focus is really on integrating AI into the health care system,” co-senior author Euan Ashley, DPhil, MB ChB, a cardiologist at Stanford, said in the same statement. “We are tremendously interested in the cycle of adaptation between human intelligence and artificial intelligence. We want to put this to work for our patients in real time.”