AI tool uses CT scans to identify patients at risk of reduced blood flow to the heart


Cedars-Sinai researchers and colleagues have developed an artificial intelligence (AI) tool that uses computed tomography (CT) scans to identify patients at risk of reduced blood flow to the heart. The tool is able to accurately predict reduced blood flow in both coronary arteries and heart muscle. The advantage of this AI tool is that it could potentially be used in real time during routine patient visits to perform CT scans to help doctors determine the next step in the treatment plan.


Coronary artery blockages usually occur due to fatty plaque buildup. This can restrict blood flow to the heart, causing chest pain, heart attacks, or even death. Identifying which arteries are at risk of reduced blood flow can help inform clinicians which patients should be referred for further testing or stenting. The current clinical standard for diagnosing reduced coronary artery blood flow is called invasive fractional flow reserve (FFR). It measures the pressure drop within the arteries and therefore calculates how much each blockage limits blood flow. Meanwhile, a positron emission tomography (PET) scan of the heart is an imaging test that uses a radioactive tracer to look for reduced blood flow in the heart muscle.


The researchers analyzed data from 203 patients who had participated in a previous study called the PACIFIC trial. As part of the PACIFIC trial, all patients had undergone multiple tests at a two-week interval, including coronary CT scans, invasive coronary angiography with FFR, and positron emission tomography (PET) scans of the heart. The researchers developed an artificial intelligence tool that analyzes plaque characteristics on coronary CT scans and then predicts the likelihood of reduced blood flow on invasive FFR and PET scans.


This AI tool can be incorporated into routine analysis of coronary CT scans, according to the authors. Having this information on hand during patient visits could help doctors know which patients to refer for further testing, such as noninvasive stress testing or invasive coronary angiography. For some patients, this would mean avoiding invasive tests.


The research was published in the peer-reviewed journal Circulation: Cardiovascular Image.

expert commentary

“Coronary CT angiography is the first-line test for chest pain as it allows us to measure atherosclerotic plaque and narrowing,” said Damini Dey, PhD, director of the quantitative imaging analysis laboratory at the Coronary Research Institute. Biomedical Imaging and Professor of Biomedical Sciences. Sciences and Medicine at Cedars-Sinai and corresponding author of the study. “If we can integrate CTA plaque data with AI stenosis to predict altered FFR, we might risk stratifying patients correctly to realize the functional significance of stenosis.”


Other Cedars-Sinai authors include Andrew Lin, MBBS, PhD; Priscilla McElhinney; Yuka Otaki, MD, PhD; Donghee Han, MD; Alan Kwan, MD; Gospels Tzolos, MD; Eyal Klein, MD; Keiichiro Kuronuma, MD; Kajetan Grodecki, MD, PhD; Benjamin Shō; Richard Rios, PhD; Japanese Manral, MSc; Sebastian Cadet, MSc; Dr. Daniel S. Berman; and Piotr J. Slomka, PhD.


The research was supported by the National Heart, Lung, and Blood Institute (award number 1R01HL148787-01A1) and the Dr. Miriam and Sheldon G. Adelson Medical Research Foundation.


Magazine reference:

Lin, A. et al. (2022). Machine learning of quantitative coronary computed tomography angiography predicts ischemia defined by fractional flow reserve and impaired myocardial blood flow. Circulation: Cardiovascular Imaging.

Leave a Reply

Your email address will not be published. Required fields are marked *