Researchers are reporting an improvement in the automatic detection of calcified atherosclerotic plaque in coronary arteries using computerized tomography (CT) enhanced with artificial intelligence (AI). Their study, partly supported by NHLBI, appeared in the journal Radiology.
The researchers demonstrated that a deep-learning algorithm for AI-assisted calcium scoring they developed can accurately determine cardiovascular risk across a range of CT scans and in a racially diverse population. Deep-learning algorithms are a form of AI that enable computers to “learn” from examples to perform a task.
The algorithm was built and evaluated using 7,240 CT scans, including nearly 2,900 from the NHLBI-supported Jackson Heart Study of African Americans in Jackson, Mississippi, 1,400 from patients treated for breast cancer in the Netherlands, and more than 1,000 from the National Lung Screening Trial (NLST), which was supported by the National Cancer Institute and conducted in 2002-2004.
"This study demonstrates the growing potential of artificial intelligence-assisted technology to enhance efforts to improve the detection of heart disease, the leading cause of death in this country," said David Goff, MD, PhD, director of the Division of Cardiovascular Sciences at NHLBI. "It is part of an ongoing effort by researchers supported by the NHLBI to develop AI tools that can rapidly sift through vast amounts of biomedical data to identify patterns that can help detect disease and hopefully save lives."