MetaGP: A generative foundation model integrating electronic health records and multimodal imaging for addressing unmet clinical needs

Artificial intelligence makes strides in specialized diagnostics but faces challenges in complex clinical scenarios, such as rare disease diagnosis and emergency condition identification. To address these limitations, we develop Meta General Practitioner (MetaGP), a 32-billion-parameter generative foundation model trained on extensive datasets, including over 8 million electronic health records, biomedical literature, and medical textbooks. MetaGP demonstrates robust diagnostic capabilities, achieving accuracy comparable to experienced clinicians. In rare disease cases, it achieves an average diagnostic score of 1.57, surpassing GPT-4's 0.93. For emergency conditions, it improves diagnostic accuracy for junior and mid-level clinicians by 53% and 46%, respectively. MetaGP also excels in generating medical imaging reports, producing high-quality outputs for chest X-rays and computed tomography, often rated comparable to or superior to physician-authored reports. These findings highlight MetaGP's potential to transform clinical decision-making across diverse medical contexts.

Authors

Institutions

Publication Details

Journal
Cell Reports Medicine
Published
2025-04-01
DOI
https://doi.org/10.1016/j.xcrm.2025.102056
Citations
10
Primary Topic
Machine Learning in Healthcare
Type
article
Field-Weighted Citation Impact
24.81
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

MetaGP: A generative foundation model integrating electronic health records and multimodal imaging for addressing unmet clinical needs

Yun Yin, Sian Liu, B Li, Xiao‐Ying Huang et al.
10 citations
Cell Reports Medicine
Machine Learning in Healthcare
24.81
article

MetaGP: A generative foundation model integrating electronic health records and multimodal imaging for addressing unmet clinical needs

Yun Yin, Sian Liu, B Li, Xiao‐Ying Huang, Shanshan Sun, Shengwei Jin, Eric K. Oermann, Hanpei Miao, Kanmin Xue, Ting Hou, Kai Wang, Yuanxu Gao, Yunfang Yu, Ting Li, Kang Zhang, Hong-Yu Zhou, Zhenqi Li, Manson Fok, Nivritti G. Patil, Jia Qu, Zixing Zou, Zhuo Sun, Fei Liu, Yang Liu
article en
10 citations

Abstract

Artificial intelligence makes strides in specialized diagnostics but faces challenges in complex clinical scenarios, such as rare disease diagnosis and emergency condition identification. To address these limitations, we develop Meta General Practitioner (MetaGP), a 32-billion-parameter generative foundation model trained on extensive datasets, including over 8 million electronic health records, biomedical literature, and medical textbooks. MetaGP demonstrates robust diagnostic capabilities, achieving accuracy comparable to experienced clinicians. In rare disease cases, it achieves an average diagnostic score of 1.57, surpassing GPT-4's 0.93. For emergency conditions, it improves diagnostic accuracy for junior and mid-level clinicians by 53% and 46%, respectively. MetaGP also excels in generating medical imaging reports, producing high-quality outputs for chest X-rays and computed tomography, often rated comparable to or superior to physician-authored reports. These findings highlight MetaGP's potential to transform clinical decision-making across diverse medical contexts.

Cell Reports MedicineVol. 6(4)
Macau University of Science and Technology (MO), Sun Yat-sen University (CN), Chinese Academy of Medical Sciences & Peking Union Medical College (CN), University of Macau (MO), Wenzhou Medical University (CN), First Affiliated Hospital of Wenzhou Medical University (CN), Nuffield Orthopaedic Centre (GB), Chinese PLA General Hospital (CN), University of Oxford (GB), NYU Langone Health (US), Affiliated Eye Hospital of Wenzhou Medical College (CN), Sun Yat-sen Memorial Hospital (CN), Second Affiliated Hospital & Yuying Children's Hospital of Wenzhou Medical University (CN), Dongguan People’s Hospital (CN), Hospital Conde S. Januário (CN), Southern Medical University (CN), City University of Macau (MO)
Openalex Percentile: Top 1%
Machine Learning in Healthcare
24.81
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.