Generative artificial intelligence (Gen-AI) revolutionizes health care by enabling data-driven innovations across diagnostics, treatment, and patient engagement. The transformational applications of Gen-AI are examined in this systematic study, including using Generative Adversarial Networks (GANs) to generate synthetic data to address data scarcity and class imbalance in time-series, tabular, and medical imaging data. Significant developments include using Large Language Models (LLMs) for automated documentation, patient communication, and clinical decision support, as well as improved diagnosis accuracy in cardiology, neurology, ophthalmology, and oncology using AI-driven imaging analysis. The review highlights AI’s role in drug discovery and underscores privacy-preserving frameworks like federated learning and blockchain for secure data collaboration. Despite breakthroughs, challenges persist, including algorithmic bias, data privacy risks, interoperability issues, and robust clinical validation, emphasizing the necessity of ethical governance and human-AI collaboration. By synthesizing 92 studies (2020–2025), this chapter illustrates AI’s potential to democratize healthcare access, improve precision medicine, and streamline workflows while advocating for equitable, transparent, and patient-centric AI integration. Future directions hinge on balancing innovation with regulatory compliance, fostering trust, and addressing underrepresented populations in AI training datasets.