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

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

Results

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 the coronary arteries and the heart muscle. The advantage of this AI tool is that it could potentially be used in real time during routine patient visits for CT scans to help doctors determine the next step in the treatment plan.

background

Coronary artery blockages typically occur due to the buildup of fatty plaques. This can restrict blood flow to the heart and cause chest pain, heart attacks, or even death. Identifying which arteries are at risk of reduced blood flow can inform doctors which patients should be referred for follow-up testing or stent placement. 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 calculates how much each blockage restricts blood flow. Meanwhile, a cardiac positron emission tomography (PET) scan is an imaging test that uses a radioactive tracer to look for reduced blood flow in the heart muscle.

method

Investigators analyzed data from 203 patients who participated in a previous study called the PACIFIC trial. As part of the PACIFIC study, all patients underwent multiple tests within two weeks, including coronary CT scans, invasive coronary angiography with FFR, and cardiac PET scans. The researchers developed an AI tool that analyzes features of the plaques on coronary CT scans and then predicts the likelihood of reduced blood flow on invasive FFR and PET scans.

impact

According to the authors, this AI tool can be integrated into the routine analysis of coronary CT scans. Having this information on hand during patient visits could help doctors know which patients should be considered for further testing, such as: B. non-invasive stress tests or invasive coronary angiography. For some patients, this would mean avoiding invasive testing.

diary

The research was published in the journal Circulation: Cardiovascular Imaging.

Expert commentary

“The coronary CT angiogram is the first-line test for chest pain because it allows us to measure atherosclerotic plaque and narrowing,” said Dr. Damini Dey, head of the Quantitative Image Analysis Laboratory at the Biomedical Imaging Research Institute and professor of Biomedical Sciences and Medicine at Cedars-Sinai and corresponding author of the study. “If we can integrate CTA plaque data with stenosis with AI to predict impaired FFR, we could risk correctly stratifying patients to detect the functional significance of the stenosis.”

Authors

Other Cedars-Sinai authors include Andrew Lin, MBBS, PhD; Priscilla McElhinney; Yuka Otaki, MD, PhD; Donghee Han, MD; Alan Kwan, MD; Evangelos Tzolos, MD; Eyal Klein, MD; Keiichiro Kuronuma, MD; Kajetan Grodecki, MD, PhD; Benjamin Shou; Richard Rios, PhD; Nipun Manral, MSc; Sebastien Kadett, MSc; Daniel S. Berman, MD; and Piotr J. Slomka, PhD.

financing

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 supported.

Source:

Cedar Sinai

Reference:

Lin, A., et al. (2022) Machine learning from quantitative coronary computed tomography angiography predicts fractional flow reserve - defined ischemia and impaired myocardial blood flow. Circulation: Cardiovascular imaging. doi.org/10.1161/CIRCIMAGING.122.014369.

.