Machine Learning Can Predict Heart Disease Better Than Other Risk Models

A study conducted by researchers from the Yale School of Medicine (New Haven, CT, USA) has demonstrated that machine learning (ML), a type of artificial intelligence, performs better than conventional risk models at predicting heart attacks and other cardiac events when used along with a common heart scan.

Accurate risk assessment is crucial for early interventions in the case of heart diseases, although risk determination is an imperfect science, and popular existing models such as the Framingham Risk Score have limitations, as they do not directly consider the condition of the coronary arteries. Coronary computed tomography arteriography (CCTA), a kind of CT that provides highly detailed images of the heart vessels, has emerged as a promising tool for refining risk assessment. In fact, it has proved so promising that a multi-disciplinary working group recently introduced a scoring system for summarizing CCTA results. The decision-making tool, known as the coronary artery disease reporting and data system (CAD-RADS), emphasizes stenoses, or blockages and narrowing in the coronary arteries. CAD-RADS is an important and a useful development in the management of cardiac patients, although its focus on stenoses could leave out important information about the arteries, according to the researchers.


Noting that CCTA shows more than just stenoses, the researchers investigated an ML system capable of mining the myriad details in these images for a more comprehensive prognostic picture. For the study, the research team compared the ML approach with CAD-RADS and other vessel scoring systems in 6,892 patients. The researchers followed the patients for an average of nine years after CCTA. There were 380 deaths from all causes, including 70 from coronary artery disease. In addition, 43 patients reported heart attacks.

In comparison to CAD-RADS and other scores, the ML approach better discriminated which patients would have a cardiac event from those who would not. When deciding whether to start statins, the ML score ensured that 93% of patients with events would receive the drug, as compared with only 69% if CAD-RADS were relied on.

If machine learning can improve vessel scoring, then it would enhance the contribution of non-invasive imaging to cardiovascular risk assessment. Additionally, if the ML-derived vessel scores could be combined with non-imaging risk factors, such as age, gender, hypertension and smoking, to develop more comprehensive risk models, then it would benefit both physicians and patients.

“The risk estimate that you get from doing the machine learning version of the model is more accurate than the risk estimate you’re going to get if you rely on CAD-RADS. Both methods perform better than just using the Framingham risk estimate. This shows the value of looking at the coronary arteries to better estimate people’s risk,” said study lead author Kevin M. Johnson, M.D, associate professor of radiology and biomedical imaging at the Yale School of Medicine.

Related Links:
Yale School of Medicine