AI Offers Personalized Care Recommendations to Curb Heart Disease Risk

Researchers have validated a causal artificial intelligence model designed to identify a patient’s inherited risk of coronary artery disease (CAD) and provide personalized recommendations for reducing their blood pressure or low-density lipoprotein (LDL) cholesterol to address that risk, according to a study presented at the American College of Cardiology’s Annual Scientific Session Together With the World Congress of Cardiology.

The Centers for Disease Control and Prevention (CDC) note that CAD is the most common type of heart disease in the US. The condition is caused by plaque buildup in the walls of the arteries that supply blood to the heart. These buildups are created from cholesterol deposits, particularly LDL, causing the artery to narrow over time and decrease blood flow to the heart.

The press release states that the AI tool assessed in the study was developed to help explain why a patient is at risk of CAD, how to reduce risk, and how much a patient will benefit from certain actions designed to reduce risk.

The study combined the causal AI with polygenic risk scores for CAD to identify and quantify how blood pressure and LDL levels, two major modifiable heart disease risk factors, can provide guidance on how patients can combat their inherited risk of the disease.

The researchers found that polygenic risk was a relatively weak risk factor for most individuals in the study cohort. They also observed that the risk could be addressed relatively easily with moderate reductions in LDL and blood pressure. However, the impact of LDL and blood pressure accumulates over time, indicating that the reduction in LDL and blood pressure needed to overcome polygenic risk is higher the later it is achieved, the press release notes.

The AI tool can be leveraged to give each patient clear goals and guidance for achieving risk reduction, the researchers explained.

“The breakthrough of causal AI is that it quantifies all of these recommendations and personalizes them so each person can know exactly how much they need to lower their LDL, their blood pressure or both to overcome their inherited risk,” said Brian A. Ference, MD, professor and director of translational therapeutics at the University of Cambridge in the United Kingdom and the study’s lead author, in the press release. “It’s much more motivating and powerful to persuade people to invest in their health if you can explain to them how they can reduce their risk and how much they’ll benefit from the recommended actions, rather than simply telling them what their risk is.”

The researchers also found that polygenic risk and family history of heart disease are independent of one another and that family history is a much stronger risk predictor in most patients. By combining family history and polygenic risk using AI, researchers may better understand a patient’s CAD risk.

“This approach transforms AI into something we can think about using in clinical medicine because it is explainable and can be tested using randomized evidence,” Ference said. “It empowers people with specific, actionable information and goals. This can not only help guide physicians and patients, it can even help governments and health care systems set more rational policy about how to incorporate polygenic risk into clinical medicine and public health policies.”