Researchers at the Los Angeles health system have developed an algorithm that can reportedly predict a patient's chances of having a heart attack over the next five years by analyzing plaque deposits in coronary arteries.
Researchers at Cedars-Sinai have created an AI tool that may help care providers predict a patient’s chances of having a heart attack over the next five years.
The algorithm analyzes the amount and composition of plaque in arteries that supply blood to the heart to determine heart attack risk. In the 11-site, international SCOT-HEART study involving almost 1,611 patients from 2010 to 2019, the tool offered “excellent or good agreement” with expert reader measurements and intravascular ultrasound.
“Coronary plaque is often not measured because there is not a fully automated way to do it,” Damini Dey, PhD, director of the quantitative image analysis lab in the Biomedical Imaging Research Institute at Cedars-Sinai and senior author of the study, recently published in The Lancet, said in a press release issued by Cedards-Sinai. “When it is measured, it takes an expert at least 25 to 30 minutes, but now we can use this program to quantify plaque from CTA images in five to six seconds.”
The study is the latest effort by healthcare providers to apply AI tools to the clinical care process, and it offers a glimpse into how the technology can help healthcare providers treat their patient and improve outcomes.
“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,” Dey and her colleagues said in the study. “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.”
According to the press release, Dey and her colleagues designed an algorithm that outlines coronary arteries in 3D images, then identifies the blood and plaque deposits within them. They found that the measurements corresponded with plaque amounts seen in coronary CTAs, and also matched results with “images taken by two invasive tests considered to be highly accurate in assessing coronary artery plaque and narrowing: intravascular ultrasound and catheter-based coronary angiography.”
Using AI in healthcare was a hot topic at the recent HIMS22 conference in Orlando, but experts are divided on where the hype ends and the reality begins. Some also worried that the potential could lead researchers and providers to overlook bias in AI, or use the technology incorrectly.
In their study, Dey and her colleagues noted that they searched available databases for past research on AI, and found 26 articles exploring the use of deep learning to assess coronary lesions on CCTA. Most of those were proof-of-concept studies, they said, and none were detailed enough to provide evidence of long-term viability.
“More studies are needed, but it’s possible we may be able to predict if and how soon a person is likely to have a heart attack based on the amount and composition of the plaque imaged with this standard test,” Dey, a professor of biomedical sciences at Cedars-Sinai, said in the press release.
Eric Wicklund is the associate content manager and senior editor for Innovation at HealthLeaders.