The rise of artificial intelligence (AI) has revolutionized many sectors including healthcare, which has benefitted from unique opportunities to harness AI-based personalized medicine. Despite the promise of ML, there are certain challenges like data bias, a lack of explainability, ethical concerns, high computational costs, and regulatory constraints that have limited its widespread usage in the real world. This study outlines a novel personalized medicine framework for the next generation of AI systems that overcomes these obstacles through the utilization of explainable AI (XAI), federated learning (FL) techniques that additionally bolster privacy, generation of adaptive AI models, and optimization of cost-efficient edge computing capabilities. The framework provides a foundation for developing ethical, transparent, and scalable approaches to integrating AI into clinical workflows, as an assistive rather than replacement tool for health care professionals. These advancements include implementing human-AI collaboration models, standardized evaluation metrics, and augmenting domain-specific AI applications, which collectively improve diagnostic precision, treatment efficacy, and the accessibility of AI-based healthcare systems. Thus, the proposed system will close the translation gap between the AI laboratory and the healthcare field, ultimately resulting in personalized medicine that is inclusive, efficient, and global.
Nagarajaiah et al. (2025) studied this question.