Generative AI for Healthcare: Fundamentals, Challenges, and Perspectives

TL;DR

GenAI has vast potential to transform healthcare but is hampered by fragmented data, governance gaps, and limited data–model feedback loops. The paper advocates a data-centric paradigm and introduces SAGE-Health, a Sustainable, Adaptive, and Generative Ecosystem for Healthcare, to unify data management, model adaptation, and agentic collaboration. It details a three-layer architecture (Sustainable Medical Data Ecosystem, Adaptive Medical GenAI Layer, Agentic Collaboration Layer) plus a Healthcare Application Layer, and illustrates implementation via a radiology workflow and case studies that demonstrate retrieval-augmented generation and continuous data–model co-evolution. By enabling scalable, trustworthy GenAI deployment through continuous data improvement and governance, the work outlines a practical pathway toward clinically impactful GenAI systems.

Abstract

Generative Artificial Intelligence (GenAI) is taking the world by storm. It promises transformative opportunities for advancing and disrupting existing practices, including healthcare. From large language models (LLMs) for clinical note synthesis and conversational assistance to multimodal systems that integrate medical imaging, electronic health records, and genomic data for decision support, GenAI is transforming the practice of medicine and the delivery of healthcare, such as diagnosis and personalized treatments, with great potential in reducing the cognitive burden on clinicians, thereby improving overall healthcare delivery. However, GenAI deployment in healthcare requires an in-depth understanding of healthcare tasks and what can and cannot be achieved. In this paper, we propose a data-centric paradigm in the design and deployment of GenAI systems for healthcare. Specifically, we reposition the data life cycle by making the medical data ecosystem as the foundational substrate for generative healthcare systems. This ecosystem is designed to sustainably support the integration, representation, and retrieval of diverse medical data and knowledge. With effective and efficient data processing pipelines, such as semantic vector search and contextual querying, it enables GenAI-powered operations for upstream model components and downstream clinical applications. Ultimately, it not only supplies foundation models with high-quality, multimodal data for large-scale pretraining and domain-specific fine-tuning, but also serves as a knowledge retrieval backend to support task-specific inference via the agentic layer. The ecosystem enables the deployment of GenAI for high-quality and effective healthcare delivery.

Figures (8)

• Figure 1: Evolution to co-evolving healthcare GenAI with a sustainable data ecosystem.
• Figure 2: Evolution of GenAI for healthcare: From the pre-foundation model era to domain-specific medical foundation models.
• Figure 3: SAGE-Health Architecture.
• Figure 4: Overview of the Agentic Collaboration Layer.
• Figure 5: Workflow of SAGE-Health for Radiology Report Generation from Chest X-rays.