Artificial intelligence is better than humans at assessing heart ultrasounds, the primary test of overall cardiac health, the most rigorous trial yet conducted on the subject found Wednesday.
While previous research has illustrated the potential power of AI models for reading medical scans, the authors of the new U.S. study said it is the first blinded, randomized clinical trial for heart health.
"There's a lot of excitement around AI," but rigorous evaluation remains critical, the study's senior author David Ouyang told Agence France-Presse (AFP).
This successful trial "really strengthens the argument that now we're ready for prime time," added the cardiologist at the Cedars-Sinai Medical Center in Los Angeles.
Heart ultrasounds, or echocardiograms, are carried out on patients by sonographers, who usually give an initial scan assessment before handing it over to a cardiologist.
The new study, published in Nature, pitted an AI model against sonographers to determine who would give the most accurate initial assessment.
Both assessed the ultrasound for the left ventricular ejection fraction, which measures the heart's ability to pump blood to the body in a heartbeat.
The test is the primary way to measure how well a heart is functioning. It is used to tell if patients have had a heart attack or if they can undertake serious treatments such as implanting a defibrillator.
The study randomly split nearly 3,500 heart ultrasounds between sonographers and the AI model.
Their assessments were then evaluated by cardiologists, who did not know which ones came from humans and which from the AI model.
'Exciting'
The study found that the cardiologists made a substantial change in more than 27 percent of the sonographer assessments – and in nearly 17 percent of those done by the AI model.
"The AI was faster, more precise, and indistinguishable from the cardiologists," Ouyang said.
He added that there is a "tremendous shortage" of sonographers in the United States and worldwide, which would save them valuable time.
The AI model, called EchoNet-Dynamic, was trained on nearly 145,000 echocardiograms and used deep learning to process large amounts of data.
The researchers are applying for the method approved by the Federal Drug Administration and hope to do the same in the European Union, and elsewhere soon, Ouyang said.
Patricia Pellikka, a cardiologist at the Mayo Clinic in the United States not involved in the research, told AFP the study was "exciting" and that the integration of AI tools will increase efficiency and standardization.
French cardiologist Florian Zores said the study was well conducted, but the technology would not be as valuable in France, where cardiologists give the initial assessments of heart ultrasounds.