Computational Analysis Of Healthcare Inequality Using AI-Based Decision Support Systems

Abstract

Healthcare inequality remains a critical global issue, driven by disparities in access, quality, and outcomes across diverse populations. This research presents a computational framework for analyzing inequality in data-driven systems, implemented through an Artificial Intelligence (AI)-based Decision Support System (DSS). The proposed approach integrates heterogeneous data sources, including electronic health records (EHRs), social determinants of health (SDOH), and Healthcare Inequality Analytics datasets, to integrate demographic, clinical, access, and social determinants data for fairness evaluation and data-driven healthcare decision systems. The methodology combines a machine learning (ML) based Prairie Dog Optimized Kernel-tuned Support Vector Machine (PDO-Kernel SVM) model for predictive analytics to detect disparities and support equitable decision-making. Data preprocessing techniques, such as Synthetic Minority Over-sampling Technique (SMOTE), are used to address imbalance and distribution bias. Feature extraction with the Independent Component Analysis (ICA) algorithm is used for extracting independent informative components from the data. While explainable AI (XAI) ensures transparency and interpretability of model outputs. PDO optimizes model parameters and features to improve performance, while Kernel SVM handles nonlinear classification and regression by mapping data into a higher-dimensional space for better separation. The suggested PDO-Kernel SVM, which is simulated using Python, has shown excellent results in the analysis of healthcare inequality. It has an accuracy of 94.9%, precision of 93.4%, recall of 96.1%, and F1-score of 96.7%.  In conclusion, the proposed AI-driven DSS provides a scalable and transparent solution for computational analysis of inequality, enabling data-driven, inclusive healthcare interventions. This research highlights the potential of fairness-aware intelligent systems to mitigate disparities and support equitable healthcare delivery across diverse population groups.