The most thorough study to date on the subject has determined that artificial intelligence performs better than humans at evaluating heart ultrasounds, the primary test of overall cardiac health.
The new US study’s authors said it is the first blinded, randomized clinical trial for heart health, despite earlier studies showing the potential power of AI models for reading medical imaging.
Although there is a lot of enthusiasm surrounding AI, principal author David Ouyang of the study told AFP that thorough analysis is still essential.
The cardiologist at Cedars-Sinai Medical Center in Los Angeles continued, “This successful trial definitely enhances the notion that now we’re ready for prime time.”
Sonographers do heart ultrasounds on patients, commonly known as echocardiograms, and often evaluate the scan before submitting it to a cardiologist.
In a recent study, sonographers and an AI model were compared to see who could make the most accurate preliminary assessment.
Both looked at the left ventricular ejection fraction, which gauges the heart’s capacity to pump blood out to the body between heartbeats, on the ultrasound.
The test is the primary tool for assessing how well a heart is working. It is used to determine whether patients have experienced a heart attack or whether they are capable of receiving major therapies like having a defibrillator implanted.
Almost 3,500 heart ultrasounds for the study were divided equally between sonographers and the AI model.
Cardiologists then examined their evaluations, not knowing which ones originated from humans and which from the AI model.