Abstract: This paper explores the integration of Explainable AI (XAI) into healthcare to enhance transparency and trust in AI-driven diagnostic, risk assessment, and personalized treatment. Techniques applied include SHAP, LIME, and Grad-CAM towards interpretability enhancement without diminishing predictive accuracy by much. The study discusses the way XAI would help clinicians enable actionable insights that build patient trust through clear explanations. It addresses challenges such as model complexity and interpretability while highlighting the need for interdisciplinary efforts in designing user-friendly systems. A structured framework for XAI integration is proposed to enhance clinical decision-making, regulatory compliance, and patient engagement, thereby ensuring AI systems remain ethical, transparent, and inclusive

Keywords: Explainable AI (XAI), Healthcare AI, Clinical decision-making, Ethical AI

Download: | DOI: 10.17148/IMRJR.2025.021105