Building Interpretable AI Models for Healthcare Decision Support

Abstract: The increasing integration of artificial intelligence (AI) into healthcare decision-making underscores the urgent need for models that are not only accurate but also interpretable. This study develops and evaluates interpretable AI models designed to support clinical decision-making while maintaining high predictive performance. Utilizing de-identified electronic health records (EHRs), the research implements tree-based algorithms and attention-augmented neural networks to generate clinically meaningful outputs. A combination of explainability tools—SHAP (Shapley Additive Explanations), LIME (Local Interpretable Model-agnostic Explanations), and Integrated Gradients—is employed to provide granular insights into model predictions. The results demonstrate that interpretable models approach the accuracy levels of black-box models, with enhanced transparency and trustworthiness from a clinical perspective. These findings reinforce the value of interpretable AI in facilitating ethical compliance, increasing clinician trust, and enabling actionable insights. The study concludes with recommendations for deploying such models in real-world healthcare environments, advocating for the routine integration of interpretability techniques in clinical AI pipelines. Keywords: Interpretable AI, Healthcare Decision Support, Explainable Models, SHAP, LIME, Predictive Analytics, EHR, Clinical AI