DefinePK

Abstract

Health care equity is a fundamental issue because the differences in access, quality of care, and health outcomes persistently influence many people from distinct socio-economic statuses in various health care systems. This study looks at the utility of using machine learning models to help eliminate and correct inequities in medical delivery. Using the mathematics of Decision Tree, Random Forest, SVM, and K-Means Clustering, databases that contain socioeconomic and geographical as well as clinical variables; the objective was to predict the gap in access and segment the people following healthcare needs. The Random Forest algorithm performed best having a 91.6% accuracy, followed by SVM at 89.3%, Decision Tree at 85.1 percentage, and K-Means with a silhouette score of 0.72 for effective population segmentation. Our analysis showed that the combination of classification with unsupervised methods allows for the identification of those at-risk and underserved populations. Based on our findings, our technique appears to outperform in terms of precision and can transfer to larger real-world healthcare systems applications. The research validates that the use of machine learning for its part can significantly promote fair healthcare since it optimizes resource utilization, influences the development of the policy and gives precise interventions. Our results provide a practical, scalable, data-driven framework with which to address complex social and clinical problems, leading to the universal, equitable, and accessible healthcare for all.