Researchers at the National Institutes of Health (NIH) and the University of Wisconsin have demonstrated that using artificial intelligence (AI) to analyze CT scans can produce more accurate risk assessment for major cardiovascular events than standard methods, such as the Framingham risk score (FRS) and body-mass index (BMI).
More than 80 million body CT scans are performed every year in the U.S. alone, but valuable prognostic information on body composition is typically overlooked. In this study, for example, abdominal scans done for routine colorectal cancer screening revealed important information about heart-related risks when AI was used to analyze the images.
The study compared the ability of automated CT-based body composition biomarkers derived from image-processing algorithms to predict major cardiovascular events and overall survival against routinely used clinical parameters.
The study used five AI computer programs on abdominal CT scans to accurately measure liver volume and fatty change, visceral fat volume, skeletal muscle volume, spine bone mineral density, and artery narrowing.
The investigators found that the CT-based measures were more accurate than FRS and BMI in predicting downstream adverse events, including death or myocardial infarction, cerebrovascular accident, or congestive heart failure. The results appeared in The Lancet Digital Health.
The researchers also observed that BMI was a poor predictor of cardiovascular events and overall survival, and all five automated CT-based measures clearly outperformed BMI for adverse event prediction.
This research builds on prior efforts designing AI algorithms to develop, train, test, and validate fully automated algorithms for measuring body composition using abdominal CT. The researchers plan to test the approach in other studies, including more racially diverse populations.
