AI predicts cardiovascular risk during CT scans—no invasive tests or contrast required

Advanced artificial intelligence (AI) models can evaluate cardiovascular risk in routine chest computed tomography (CT) scans without contrast, according to new research published in Nature Communications.[1] In fact, the authors noted, the AI approach may be more effective at identifying issues than relying on guidance from radiologists.  

A team of cardiac imaging specialists with Cedars-Sinai Medical Center used two separate AI algorithms—one that measures coronary artery calcium (CAC) scores and another that segments cardiac chamber volumes—to examine low-dose chest CT results from nearly 30,000 patients with a median age of 61 years old. All CT exams were originally performed for lung cancer screening. The AI models delivered CAC scores and chamber volumes in just a matter of seconds, and they only failed to segment 0.1% of cases.

While 19% of patients had a CAC score of zero, 37% had a CAC score of 1-100, 19.8% a score of 101-400 and 24.3% had a score of more than 400.

Overall, the group’s “fully automated pipeline” was able to accurately assess risk. Patients with higher AI-based CAC scores were associated with a higher risk of all-cause mortality and cardiovascular mortality, for example. The same was true for patients presenting with higher atrial and ventricular volumes. Each of these imaging variables improved patient assessments on their own, but incorporating them all into a single evaluation was associated with “the greatest improvement in categorical risk classification compared to radiologist identification of abnormalities.”

“These results are likely practice-changing for many patients because this technology can accurately identify cardiovascular risk without the use of invasive tests or contrast dye that some patients cannot receive,” senior author Piotr Slomka, PhD, director of innovation in imaging at Cedars Sinai and a professor of cardiology with the Smidt Heart Institute, said in a statement.

“Coronary artery disease is the leading cause of disability and death at a global level,” added Sumeet Chugh, MD, associate director of the Smidt Heart Institute. “These findings highlight how AI tools could leverage existing CT images performed for lung disease investigation, to make a cost-effective, public health impact on heart disease.”

Michael Walter
Michael Walter, Managing Editor

Michael has more than 16 years of experience as a professional writer and editor. He has written at length about cardiology, radiology, artificial intelligence and other key healthcare topics.

Around the web

Ron Blankstein, MD, professor of radiology, Harvard Medical School, explains the use of artificial intelligence to detect heart disease in non-cardiac CT exams.

Eleven medical societies have signed on to a consensus statement aimed at standardizing imaging for suspected cardiovascular infections.

Kate Hanneman, MD, explains why many vendors and hospitals want to lower radiology's impact on the environment. "Taking steps to reduce the carbon footprint in healthcare isn’t just an opportunity," she said. "It’s also a responsibility."

Trimed Popup
Trimed Popup