Why deep learning can help cardiologists—without threatening them

Clinicians might be saved time and improve their diagnostic accuracy when deep learning is applied to echocardiography, according to a recent article from Cardiovascular Business (CVB) regarding this year's American College of Cardiology annual meeting in Orlando. 

"Machine learning—and its self-training subset, deep learning—is often perceived as a threat to cardiologists, but the tools could aid clinical decision-making in a way humans can’t," said Randolph Martin, MD, a Georgia based radiologist who spoke of the topic at the annual meeting.  

According CVB, Edwards’ CardioCare program revealed that in a study of 150,000 consecutive echocardiograms screening for aortic stenosis, 24 percent of echoes were of inadequate quality. Additionally, most cases couldn't complete quantification of aortic valve parameters and the trial saw frequent discordance between guideline recommendations and reality. 

Martin expressed that machine learning could enhance interpretation of results, but now is really the time for deep learning which can improve workflow, the completeness of studies, and doctors' ability to interpret data and make management decisions.  

“These things have got so much power that they learn from data,” he said, according to CVB. “We’re not talking about replacing you or super-sophisticated echocardiography machines, but we are talking about improving quality, improving acquisition and improving the ability to interpret studies.” 

""

A recent graduate from Dominican University (IL) with a bachelor’s in journalism, Melissa joined TriMed’s Chicago team in 2017 covering all aspects of health imaging. She’s a fan of singing and playing guitar, elephants, a good cup of tea, and her golden retriever Cooper.

Trimed Popup
Trimed Popup