Foundation Model for Advancing Healthcare: Challenges, Opportunities, and Future Directions

TL;DR

This survey analyzes healthcare foundation models (HFMs) across four subfields—language, vision, bioinformatics, and multimodal—identifying progress, challenges, and future directions. It presents a systematic taxonomy of pre-training paradigms (generative, contrastive, hybrid, supervised) and adaptation strategies (fine-tuning, adapters, and prompts), detailing how LFMs, VFMs, BFMs, and MFMs are constructed and deployed in healthcare. By synthesizing 200+ papers and 114 datasets, the work maps the data, methods, and applications, and discusses core data, algorithmic, and infrastructure challenges including ethics, diversity, reliability, and environmental cost, while outlining future directions such as AI–human collaboration, dynamic models, multi-domain and multi-modality integration, explainability, security, and sustainability. The paper concludes that HFMs hold substantial potential to augment diverse clinical tasks but require careful governance, efficient adaptation, and scalable, trustable deployment to achieve real-world impact.

Abstract

Foundation model, which is pre-trained on broad data and is able to adapt to a wide range of tasks, is advancing healthcare. It promotes the development of healthcare artificial intelligence (AI) models, breaking the contradiction between limited AI models and diverse healthcare practices. Much more widespread healthcare scenarios will benefit from the development of a healthcare foundation model (HFM), improving their advanced intelligent healthcare services. Despite the impending widespread deployment of HFMs, there is currently a lack of clear understanding about how they work in the healthcare field, their current challenges, and where they are headed in the future. To answer these questions, a comprehensive and deep survey of the challenges, opportunities, and future directions of HFMs is presented in this survey. It first conducted a comprehensive overview of the HFM including the methods, data, and applications for a quick grasp of the current progress. Then, it made an in-depth exploration of the challenges present in data, algorithms, and computing infrastructures for constructing and widespread application of foundation models in healthcare. This survey also identifies emerging and promising directions in this field for future development. We believe that this survey will enhance the community's comprehension of the current progress of HFM and serve as a valuable source of guidance for future development in this field. The latest HFM papers and related resources are maintained on our website: https://github.com/YutingHe-list/Awesome-Foundation-Models-for-Advancing-Healthcare.

Figures (5)

• Figure 1: The pipeline of the healthcare foundation models (HFMs) including the methods (Sec.\ref{['sec:methods']}), datasets (Sec.\ref{['sec:datasets']}), and applications (Sec.\ref{['sec:applications']}).
• Figure 2: The number of representative papers on healthcare foundation models from 2018 to 2024 (Jan-Feb).
• Figure 3: The Sankey diagram of healthcare foundation models demonstrates the associations between the pre-training paradigms, sub-fields of HFM, and adaptation paradigms. "Non" means that the work directly adapted existing pre-trained models to their tasks and did not pre-train their model by themselves.
• Figure 4: The challenges of the healthcare foundation model on data, algorithm, and computing infrastructure.
• Figure 5: The future directions of the healthcare foundation model. In this paper, we discuss its transformation of role, implementation, applications, and emphasis in the future.