Application Status and Challenges of Medical Foundation Models

Corresponding author: Zhao Yuhong, zhaoyh@sj-hospital.org

DOI: 10.12201/bmr.202511.00060

•  

  Abstract: Purpose/Significance This study systematically evaluates the potential and limitations of Medical Foundation Models (MFM) in clinical applications.Method/Process Through a systematic literature review, we analyze the technological evolution of representative MFMs in multimodal fusion, retrieval-augmented generation, and parameter-efficient fine-tuning, and assess their performance and applicability boundaries in real-world medical tasks. Result/Conclusion Findings show that MFMs, empowered by multimodal learning and explainability mechanisms, can markedly enhance diagnostic efficiency and decision reliability. However, data silos, algorithmic bias, and generative uncertainty remain major obstacles to large-scale adoption. Future development should establish a collaborative ecosystem that integrates technological innovation, data governance, and ethical regulation to ensure the safe and sustainable advancement of MFMs in healthcare.

  Key words: Medical foundation model; Multimodal fusion; Privacy and ethics; 

  Submit time: 20 November 2025

  Copyright: The copyright holder for this preprint is the author/funder, who has granted biomedRxiv a license to display the preprint in perpetuity.
• html

• 图表

• ZhengYanli, Han Fuhai, LI Shuyu, SU Wenxing. Application Status and Prospect of Artificial Intelligence Large Models in Medicine. 2023. doi: 10.12201/bmr.202312.00027

  GE Xiaoling. Application of Artificial Intelligence Large Models in Healthcare:a Survey. 2024. doi: 10.12201/bmr.202408.00039

  WU Hong, HU Jun, CHEN Erzhen, DONG Chenjie, LI Jianhua, YE Qi. Construction of a Medical Quality Control Application System Based on Large Language Models. 2025. doi: 10.12201/bmr.202503.00004

  GAO Jing-hong, LI Ming-yuan, WANG Lin, ZhAI Yun-kai, ZHAO Jie. The application and challenges of health and medical big data in the field of precision medicine. 2021. doi: 10.12201/bmr.202106.00014

  yang yazhou, wang li. A Review of the Application of Multimodal Fusion in Artificial Intelligence-Driven Pharmaceutical Industry. 2025. doi: 10.12201/bmr.202512.00054

  Lv Hairong. DeepSeek and Medical Big Models: Technological Innovation and Reconstruction of Medical Service Models. 2025. doi: 10.12201/bmr.202503.00023

  zhangyoujian, zhouguanqun, zhouhaotian, wangzhongya, zhangzhicheng. Survey on the Applications of Generative Models in Medical Image Analysis. 2025. doi: 10.12201/bmr.202511.00066

  HUANGYOULIANG. The application and development trend of active health in smart medical care：Based on SWOT-CLPV model analysis. 2022. doi: 10.12201/bmr.202112.00009

  SU Xuemei, WANG Wei, ZHAO Zixiong, ZHAO Jia. Status, Applications and Challenges of Digital Intelligence for Disease Prevention and Control Construction. 2025. doi: 10.12201/bmr.202503.00022

  Li Rili, PAN Jiaming, RONG Shiqiang, SUN Xiaocui, YI Faling. Advances in Integrating Knowledge Graphs and Large Language Models for Health Management of Diabetes. 2025. doi: 10.12201/bmr.202508.00035

• ID	Submit time	Number	Download
  1	2025-09-26	10.12201/bmr.202511.00060V1	Download

• Public  Anonymous  To author only Submit Comments