AI could help predict heart attack risk better

AI could help predict heart attack risk better

In a new study, researchers found that artificial intelligence (AI) may help predict people’s heart disease risk better than conventional methods.

They found that a common heart scan, machine learning (ML), a type of AI, does better than traditional risk models at predicting heart attacks and other cardiac events.

The research was conducted by a team from the Yale School of Medicine.

Heart disease is the leading cause of death for both men and women in the United States.

Accurate risk assessment is crucial for early interventions including diet, exercise, and drugs like cholesterol-lowering statins.

However, risk determination is an imperfect science, and popular existing models like the Framingham Risk Score have limitations.

For example, they don’t directly consider the condition of the coronary arteries.

Recent studies have shown that coronary computed tomography arteriography (CCTA), a kind of CT that gives highly detailed images of the heart vessels, is a promising tool for refining risk assessment.

One multidisciplinary 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), focuses on blockages and narrowing in the coronary arteries.

CAD-RADS currently is an important and useful tool in the management of cardiac patients.

The team recently investigated an AI system capable of mining the details in these images for a more comprehensive prognostic picture.

In the new study, the team compared the AI approach with CAD-RADS and other vessel scoring systems in 6,892 patients.

They 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.

The team found that compared with CAD-RADS and other scores, the AI approach better discriminated which patients would have a cardiac event from those who would not.

When deciding whether to start statins, the AI score ensured that 93% of patients with events would receive the drug, compared with only 69% if CAD-RADS were used.

The findings showed that both methods perform better than just using the Framingham risk estimate.

The team suggests that if AI can improve vessel scoring, it would enhance the contribution of noninvasive imaging to cardiovascular risk assessment.

The lead author of the study is Kevin M. Johnson, M.D., associate professor of radiology and biomedical imaging.

The study is published in the journal Radiology.

Copyright © 2019 Knowridge Science Report. All rights reserved.