Cedars-Sinai Secures NIH Grant to Use AI in Measuring Cardiac Risk

The Los Angeles-based health system is using a $7 million federal grant to expand a digital health program that will develop AI tools to help providers analyze a patient's risk of heart attack and other cardiac concerns.

Cedars-Sinai researchers have received a federal grant to study how AI can be used to help predict heart attacks and other cardiac concerns.

A team from the Los Angeles health system's Smidt Heart Institute and Division of Artificial Intelligence in Medicine is using a $7 million grant from the National Institutes of Health's National Heart, Lung and Blood Institute to set up the new program, which will use data from positron emission tomography and CT scans to analyze a patient's risk of cardiac issues.

“Advanced imaging data could help predict patients’ risk of serious cardiac events, but is so complex that clinicians aren’t always able to use it,” Piotr Slomka, PhD, director of Innovation in Imaging and professor of Cardiology and Medicine in the Division of Artificial Intelligence in Medicine at Cedars-Sinai and the lead researcher in the project, said in a press release. “This grant will allow us to create artificial intelligence tools that help physicians everywhere identify high-risk patients who would benefit from targeted therapy.” 

According to the American Heart Association, more than 18 million people died of cardiovascular disease in 2019. Many healthcare organizations are looking to digital health to develop new ways to detect cardiac problems early enough for care providers to intervene before they become serious, even deadly.

Cedars-Sinai has long been at the forefront of digital health innovation, working with tools like virtual reality, wearables and AI to improve treatments and clinical outcomes. This past March, researchers in the quantitative image analysis lab at the Biomedical Research Institute announced the development of an AI tool that analyzes the amount and composition of plaque in arteries that supply blood to the heart to determine heart attack risk within five years.

“A deep learning system that rapidly and accurately quantifies coronary artery stenosis has the potential for integration into routine CCTA (coronary CT angiography) workflow, where it could function as a second reader and clinical decision support tool,” the research team reported in a study published in The Lancet. “By providing automated and objective results, deep learning could reduce interobserver variability and interpretative error among physicians. Deep learning-based plaque volume measurements have independent prognostic value for future cardiac events, and could enhance risk stratification in patients with stable chest pain who are undergoing CCTA.”

With this latest program, Slomka and his team plan on expanding the platform.

“This particular grant allows us to build a program—not just a project—which will expedite our innovative plans,” he said in the press release. “In AI, things are changing all the time, and sometimes we find that we could make much more impact if we change direction. The beauty of this grant is that it makes that easy to do.”