To accomplish this, the team developed an AI model that “learns” from patient scans.

Source: Case Western Reserve University

Specifically, the AI tool is designed to analyze calcium-scoring computed tomography (CT) scans, which are commonly used for detecting arterial plaque.

In addition to measuring plaque, the CT scans can also capture other information about the aorta, heart shape, lungs, muscles and liver, thus offering even more data for AI analysis.

The AI-driven predictive model is expected to interpret combined data from CT scans, clinical risk factors, and demographic information to potentially reveal insights into the relationship between heart health and body composition.

“Accurate risk prediction allows us to tailor preventative treatments, reducing the burden of cardiovascular diseases and improving patient outcomes,” the researchers explained. “By identifying risks early, this project can potentially redefine care protocols, save lives, and lower healthcare costs.”