Back to Journal Articles

Social Factors in Machine Learning Models Aid CVD Prediction

FRIDAY, Aug. 6, 2021 (HealthDay News) -- Machine learning approaches are useful for cardiovascular disease prediction, and model performance is improved with inclusion of social determinants of health, according to a review published online July 27 in the American Journal of Preventive Medicine.

Yuan Zhao, M.P.H., from the NYU School of Global Public Health in New York City, and colleagues conducted a systematic review of articles on the use of machine learning algorithms for cardiovascular disease prediction that incorporated social determinants of health.

The researchers found that most studies comparing machine learning algorithms with regression showed increased performance of machine learning; comparative studies also showed improved performance of machine learning models with versus without social determinants of health. Gender, race/ethnicity, marital status, occupation, and income were the most frequently included social determinants of health. Studies were mostly from North America, Europe, and China, and therefore, the included populations and variance in social determinants of health were limited.

"Including social determinants of health in machine learning models can help us to disentangle where disparities are rooted and bring attention to where in the risk structure we should intervene," a coauthor said in a statement. "For example, it can improve clinical practice by helping health professionals identify patients in need of referral to community resources like housing services and broadly reinforces the intricate synergy between the health of individuals and our environmental resources."

Abstract/Full Text