• Amit Kumar
• Dr. PAWAN MEENA
• YOGESH RAI

Generative Artificial Intelligence (GenAI), particularly large language models (LLMs) and multimodal foundation models, is rapidly transforming the landscape of healthcare information systems. Unlike conventional machine learning systems that primarily focus on prediction and classification, generative models can interact with users through natural language, synthesize information, summarize clinical records, and produce personalized explanations. These capabilities create opportunities for developing personalized healthcare decision-support systems that consider patient characteristics, medical history, preferences, symptoms, and contextual information. However, the increasing personalization of generative AI introduces important challenges involving explainability, hallucination, privacy, fairness, bias, uncertainty, accountability, and clinical safety. A personalized recommendation without a transparent justification may be difficult for clinicians and patients to trust or evaluate. This paper presents a comprehensive survey of explainable generative AI for personalized healthcare decision support. It examines the evolution from conventional clinical decision-support systems and machine learning toward explainable AI and generative AI. The paper reviews personalization mechanisms based on patient profiles, longitudinal electronic health records, clinical context, preferences, and multimodal information. It analyzes explanation techniques including feature attribution, natural-language explanations, counterfactual explanations, example-based explanations, evidence-grounded explanations, and uncertainty-aware explanations. The paper also investigates applications in disease-risk assessment, personalized treatment support, medication management, patient education, preventive healthcare, mental-health support, chronic disease management, and clinical workflow assistance. A conceptual Explainable Personalized Generative Healthcare Decision Support Framework is proposed, integrating patient profiling, predictive analytics, evidence retrieval, personalization, explanation generation, explanation verification, uncertainty estimation, and human oversight. Finally, major research gaps and future directions are identified, including longitudinal personalization, causal explainability, multimodal personalization, multilingual healthcare AI, privacy-preserving personalization, fairness-aware recommendations, prospective clinical validation, and standardized evaluation. The survey concludes that explainable GenAI has significant potential to support personalized healthcare, but safe deployment requires evidence grounding, transparent explanations, continuous monitoring, privacy protection, and clinician involvement

Generative AI, Explainable AI, Personalized Healthcare, Large Language Models, Clinical Decision Support, Patient-Centered AI, Healthcare Recommendation Systems, Medical AI, Personalization, XAI.

"Explainable Generative AI for Personalized Healthcare Decision Support: A Comprehensive Survey", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.13, Issue 10, page no.a928-a935, October-2026, Available :http://www.jetir.org/papers/JETIR2610096.pdf

"Explainable Generative AI for Personalized Healthcare Decision Support: A Comprehensive Survey", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.13, Issue 10, page no. ppa928-a935, October-2026, Available at : http://www.jetir.org/papers/JETIR2610096.pdf