Biomedical Foundation Model: A Survey

2025-03-03

AI Summary

Biomedical foundation models face challenges in cross-modal and multi-task modeling due to the absence of unified evaluation and adaptation paradigms. Method: We conduct a systematic review across five domains—computational biology, drug discovery, clinical informatics, medical imaging, and public health—and propose the first comprehensive technical analysis framework covering large language models (LLMs), vision-language models (VLMs), multimodal pretraining, self-supervised learning, and domain-adaptive fine-tuning, synthesizing over 100 representative studies. Contribution/Results: We introduce a standardized evaluation framework and a forward-looking challenges map, revealing the synergistic impact of model scale, data quality, and domain alignment on downstream performance. Our work delivers a systematic roadmap for trustworthy deployment and sustained innovation of foundation models in health sciences.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Computer Vision: Medical and Biological Imaging

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Web applications in cross-disciplinary domains and verticals such as mixed reality, smart cities, and digital health

Abstract

Foundation models, first introduced in 2021, are large-scale pre-trained models (e.g., large language models (LLMs) and vision-language models (VLMs)) that learn from extensive unlabeled datasets through unsupervised methods, enabling them to excel in diverse downstream tasks. These models, like GPT, can be adapted to various applications such as question answering and visual understanding, outperforming task-specific AI models and earning their name due to broad applicability across fields. The development of biomedical foundation models marks a significant milestone in leveraging artificial intelligence (AI) to understand complex biological phenomena and advance medical research and practice. This survey explores the potential of foundation models across diverse domains within biomedical fields, including computational biology, drug discovery and development, clinical informatics, medical imaging, and public health. The purpose of this survey is to inspire ongoing research in the application of foundation models to health science.

Problem

• Explores biomedical foundation models' potential in health science.
• Investigates applications in computational biology and drug discovery.
• Surveys impact on medical imaging and clinical informatics.

Innovation

• Large-scale pre-trained models for biomedical applications
• Unsupervised learning from extensive unlabeled datasets
• Adaptable to diverse tasks like drug discovery