Summary: AI can accurately assess cardiovascular risk in standard chest CT scans without contrast, potentially revolutionizing risk identification with non-invasive methods.

Key Takeaways

  1. Cedars-Sinai’s study shows AI accurately assesses risk in chest CT scans without contrast, offering a non-invasive option for risk identification.
  2. The findings suggest AI could change cardiovascular risk assessment by reducing the need for invasive tests and contrast dye, making it more accessible and affordable.
  3. Using AI to analyze existing CT data could identify individuals at risk for coronary artery disease on a large scale, potentially revolutionizing global heart disease prevention.


A recent Cedars-Sinai study discovered that artificial intelligence (AI) accurately assesses cardiovascular risk during standard chest CT scans without contrast, potentially offering a less costly and invasive means of identifying cardiovascular risk factors. Published in Nature Communications, this method measures coronary calcium and heart chamber and muscle sizes.

Non-invasive Cardiovascular Risk Identification

“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,” says Piotr J. Slomka, PhD, director of Innovation in Imaging at Cedars-Sinai, professor of medicine in the Division of Artificial Intelligence in Medicine and senior author of the study.

Slomka, a cardiology professor at Cedars-Sinai’s Smidt Heart Institute, highlights that more than 15 million CT scans are conducted annually in the U.S., yet many remain underused or lacking in study. While clinicians typically assess cardiovascular risk using contrast-enhanced CT scans, Slomka emphasizes the significance of a new AI algorithm. 

“This algorithm makes it possible to get crucial heart health insights from cheaper scans that use less radiation, potentially making detailed heart evaluations part of regular diagnostic procedures,” Slomka says.

AI Revolutionizes Heart Risk Assessment

Investigators incorporated two AI models to evaluate data on coronary calcium and heart muscle chamber sizes from nearly 30,000 patient imaging records. They were able to determine that those measures are a better indicator of cardiac risk than a radiologist’s identification of abnormalities.

Sumeet Chugh, MD, director of the Division of Artificial Intelligence in Medicine, who was not involved in the study, says this technology allows for large-scale use of existing CT data to spot individuals at risk sooner.

“Coronary artery disease is the leading cause of disability and death at a global level,” says Chugh. “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.”