Researchers Create AI Model to Predict Long-Term Mortality in Coronary Artery Disease Patients

A team led by University of Florida College of Pharmacy researchers has “proposed an artificial intelligence, or AI, model to predict long-term mortality in patients with coronary artery disease.” UF Health has the press release.

Coronary artery disease, or CAD, “limits blood flow to the heart.” It is the most common form of heart disease, causing more than 350,000 deaths in the U.S. in 2022 alone. The AI tool is designed in the hopes of improving “treatment outcomes and [reducing] mortality in CAD patients.”

Traditional factors for predicting CAD mortality “use only established risk factors like age, smoking status, and cholesterol level,” limiting their “accuracy and adaptability to diverse populations.” Existing AI models tend to lack the ability to capture causality. This AI model will help clinicians “determine which factors most prominently contribute to a patient’s risk of death.”

Analysis performed found that this model “outperformed all traditional models in correctly predicting which patients would survive the disease.” Before it becomes available in patient care settings, it still needs to be “validated with demographically diverse external datasets and evaluated for ethical and privacy issues,” but these early results are promising.