Medical foundation large language models for comprehensive text analysis and beyond

Recent advancements in large language models (LLMs) show significant potential in medical applications but are hindered by limited specialized medical knowledge. We present Me-LLaMA, a family of open-source medical LLMs integrating extensive domain-specific knowledge with robust instruction-following capabilities. Me-LLaMA is developed through continual pretraining and instruction tuning of LLaMA2 models using diverse biomedical and clinical data sources (e.g., biomedical literature and clinical notes). We evaluated Me-LLaMA on six text analysis tasks using 12 benchmarks (e.g., PubMedQA and MIMIC-CXR) and assessed its clinical utility in complex case diagnosis through automatic and human evaluations. Me-LLaMA outperforms existing open medical LLMs in zero-shot and supervised settings and surpasses ChatGPT and GPT-4 after task-specific instruction tuning for most text analysis tasks. Its performance is also comparable to ChatGPT and GPT-4 for diagnosing complex clinical cases. Our findings highlight the importance of combining domain-specific continual pretraining with instruction tuning to enhance performance in medical LLMs.

Authors

Institutions

Publication Details

Journal
npj Digital Medicine
Published
2025-03-05
DOI
https://doi.org/10.1038/s41746-025-01533-1
Citations
41
Primary Topic
Machine Learning in Healthcare
Type
article
Field-Weighted Citation Impact
101.72

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Medical foundation large language models for comprehensive text analysis and beyond

Aokun Chen, Lingfei Qian, Yonghui Wu, Peng Cheng et al.
41 citations
npj Digital Medicine
Machine Learning in Healthcare
101.72
article

Medical foundation large language models for comprehensive text analysis and beyond

Aokun Chen, Lingfei Qian, Yonghui Wu, Peng Cheng, Jimin Huang, Jiang Bian, Xueqing Peng, Qingyu Chen, Xinyu Zhou, Dennis Shung, Hua Xu, Lucila Ohno‐Machado, Vipina Keloth, Huan He, Yan Hu, Qianqian Xie, Fongci Lin, Jeffrey Zhang
article en
41 citations

Abstract

Recent advancements in large language models (LLMs) show significant potential in medical applications but are hindered by limited specialized medical knowledge. We present Me-LLaMA, a family of open-source medical LLMs integrating extensive domain-specific knowledge with robust instruction-following capabilities. Me-LLaMA is developed through continual pretraining and instruction tuning of LLaMA2 models using diverse biomedical and clinical data sources (e.g., biomedical literature and clinical notes). We evaluated Me-LLaMA on six text analysis tasks using 12 benchmarks (e.g., PubMedQA and MIMIC-CXR) and assessed its clinical utility in complex case diagnosis through automatic and human evaluations. Me-LLaMA outperforms existing open medical LLMs in zero-shot and supervised settings and surpasses ChatGPT and GPT-4 after task-specific instruction tuning for most text analysis tasks. Its performance is also comparable to ChatGPT and GPT-4 for diagnosing complex clinical cases. Our findings highlight the importance of combining domain-specific continual pretraining with instruction tuning to enhance performance in medical LLMs.

npj Digital MedicineVol. 8(1)
Yale University (US), University of Florida (US), The University of Texas Health Science Center at Houston (US)
Patient-Centered Outcomes Research Institute, National Institutes of Health
Quality Education
Openalex Percentile: Top 0%
Machine Learning in Healthcare
101.72
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.