Federated Learning and Explainable AI for Personalized Healthcare in Resource-Limited Settings

Artificial Intelligence (AI) has transformed healthcare, significantly advancing diagnostic tools, treatment methodologies, and personalized care systems. Despite these advancements, the adoption of AI in resource-constrained environments faces persistent barriers, including data privacy concerns, limited computational resources, and the need for interpretable models. This paper introduces an innovative federated learning framework, integrated with Explainable AI (XAI), to tackle these challenges. The framework enables collaborative training across distributed healthcare institutions while safeguarding patient data privacy and offering clinical decision-making transparency. Additionally, it is optimized for low-resource environments and effectively processes multi-modal healthcare data. Experimental results indicate that the proposed model outperforms conventional AI systems in predictive accuracy, communication efficiency, and interpretability. This work emphasizes the importance of scalable, secure, and interpretable AI solutions in advancing personalized medicine globally, particularly for diverse and underserved populations.