Los Angeles,
06:30 AM

AI Measures Fat Around the Heart, a Key to Predicting Heart Attacks

A Collaborative Group of Cedars-Sinai Investigators Suggest Artificial Intelligence Can Accurately Assess Volume, Density of Heart Fat—Both of Which Are Linked to Cardiovascular Risk

A collaborative group of investigators used artificial intelligence (AI) to quickly and accurately measure fat around the heart using a low-dose computed tomography (CT) scan during a routine test. The technique, identified by the Division of Artificial Intelligence in Medicine and the Biomedical Imaging Research Institute at Cedars-Sinai, can help physicians better understand and manage heart disease risk in patients.

The investigators, whose results are published in the peer-reviewed journal npj Digital Medicine, say their AI measurement tool offers new help in predicting heart attacks and cardiovascular disease.Piotr Slomka, PhD

“Our research shows that people with a larger volume of heart fat—a key indicator of metabolic health—and those with more dense heart fat—a marker of inflammation—are at higher risk for cardiovascular disease,” said Piotr J. Slomka, PhD, director of Innovation in Imaging at Cedars-Sinai and a professor of Medicine in the Division of Artificial Intelligence in Medicine. “This novel technology uses AI to more quickly and accurately assess the volume and density of heart fat, offering valuable insight beyond traditional methods.”

Slomka and colleagues hope to translate these findings into clinical use more broadly, offering doctors and clinicians this specialized software.

“These results underscore the efficiency and clinical importance of AI in heart disease risk assessment, offering a fast and reliable tool for predicting cardiovascular risk,” said Slomka, also a professor of Cardiology in the Department of Cardiology in the Smidt Heart Institute at Cedars-Sinai.

Investigators included 8,781 patients from four clinical sites in their study. None of the patients had known coronary artery disease—a type of heart disease—at the time of the study, and all underwent heart imaging.

Key results include:

  • AI measurements of heart fat were performed in under two seconds, compared with 15 minutes typically required for manual measurement.
  • During the follow-up period, which was 2.7 years, individuals with larger volumes of heart fat and higher densities of heart fat experienced greater incidence of heart-related issues or death.
  • The risk of cardiovascular-related death, and heart attacks, was almost three times higher in patients with both elevated heart fat volumes and density.
  • The association with cardiovascular risk persisted, even after taking into account other risk factors like age, medical history, past heart imaging results and coronary artery calcium scores.

Study results align with previous research but offer new insight through the use of AI. Sumeet Chugh, MD

“These findings validate the use of AI for quick and accurate heart fat measurement, highlighting a potential shift toward more AI-assisted diagnostic methods in cardiology,” said Sumeet Chugh, MD, Cedars-Sinai’s director of the Division of Artificial Intelligence in Medicine and associate director of the Smidt Heart Institute.

Chugh, who was not involved in the study, said that by establishing a clear link between heart fat and cardiovascular risk, the study encourages further research into heart fat as a key factor in heart disease.

“This approach serves as a practical, real-world test of the application's effectiveness when implemented in clinical settings,” Chugh said.

As a next step, investigators plan to further test their algorithm in a more diverse patient population to ensure accuracy and generalizability of the findings.

Other authors involved in the study include Robert J. H. Miller, Aakash Shanbhag, Aditya Killekar, Mark Lemley, Bryan Bednarski, Serge D. Van Kriekinge, Paul B. Kavanagh, Joanna X. Liang, Valerie Builoff, Attila Feher, Edward J. Miller, Andrew J. Einstein, Terrence D. Ruddy, Daniel S. Berman, and Damini Dey.

This research was supported in part by grants R01HL089765 and R35HL161195 from the National Heart, Lung, and Blood Institute at the National Institutes of Health (PI: Piotr Slomka).

Read more on the Cedars-Sinai Blog: Graduate Students Are Using AI in Medical Imaging