Researchers at Yale’s Cardiovascular Data Science (CarDS) Lab are using artificial intelligence (AI) to detect a common valvular heart disease from simple ultrasound scans.

Known as severe aortic stenosis or AS, this is a major health disorder, particularly among older adults, caused by a narrowing of the aortic valve. Early diagnosis can enable interventions to alleviate symptoms and reduce the risk of hospitalisation and premature death.

Specialised ultrasound imaging of the heart, called Doppler echocardiography, is the main test to detect AS. But the team at Yale has developed a deep learning model that can use simpler heart ultrasound scans to detect severe AS automatically.

The technology was developed by the study’s senior author Rohan Khera, assistant professor at the CarDS Lab, and colleagues at the Chandra Family Department of Electrical & Computer Engineering at the University of Texas at Austin, with 5257 studies that included 17,570 videos between 2016 and 2020 at Yale New Haven Hospital. The model was validated by 2040 consecutive studies from different cohorts in New England and California.

“Our challenge is that precise evaluation of AS is crucial for patient management and risk reduction,” said Khera. “While specialised testing remains the gold standard, reliance on those who make it to our echocardiographic laboratories likely misses people early in their disease state.”

Evangelos Oikonomou, a cardiology fellow and a postdoctoral researcher in the CarDS Lab, added: “Our goal was to develop a machine-learning approach that would be suitable for point-of-care ultrasound screening.”

Their work allows the early detection of aortic stenosis so patients can receive timely care.

“Our work can allow broader community screening for AS as handheld ultrasounds can increasingly be used without the need for more specialised equipment,” said Khera. “They are already being used frequently in emergency departments, and many other care settings.”

The advance is a result of close collaboration between clinician investigators and computer scientists. Greg Holste, a PhD student at UT Austin being co-advised by Khera, led the development of an innovative method that enabled the technology and was a co-first author of the study.

“To allow practical development that leverages emerging technology for improving clinical care, such multidisciplinary collaboration is essential,” Khera said.

This study was funded in part by a grant from the National Heart, Lung & Blood Institute, and was published this month in the European Heart Journal at academic.oup.com/eurheartj/advance-article/doi/10.1093/eurheartj/ehad456/7248551.

More about Yale University’s Cardiovascular Data Science (CarDS) Lab can be seen at www.cards-lab.org.