Understanding AI-Driven Cardiovascular Risk Prediction in Underserved Populations: Addressing Social Determinants of Health through Data Analytics

Abstract

Cardiovascular disease (CVD) is a leading cause of morbidity and mortality internationally, and underserved populations bear an out sized burden of risk. In these communities, access to adequate healthcare, burdened by social determinants of health (SDOH) like socioeconomic status, education, and environmental factors, can pose a barrier to many individuals. The crucial role of Artificial Intelligence (AI) and Machine Learning (ML) to address problems of health disparity by leveraging large scale data to predict cardiovascular risks and impact appropriate interventions is discussed. The integration of diverse sources of information, such as electronic health records (EHR) social data, and behavioral data, allows AI models to identify at risk individuals even in settings with limited resources. In this paper, we investigate the use of AI driven cardiovascular risk prediction models in underserved populations and how they can consider the effect of SDOH. The paper also addresses ethical considerations, data challenges, and opportunities for use of these prediction tools in public health initiatives to address disparities in health. The potential of combining AI and data analytics is to enhance cardiovascular health outcomes, bridging gaps in equitable access to preventive care, especially for vulnerable communities.