AgentMD: Empowering language agents for risk prediction with large-scale clinical tool learning

Qiao Jin, Zhizheng Wang, Yifan Yang, Qingqing Zhu, Donald Wright, Thomas Huang, Nikhil Khandekar, Nicholas Wan, Xuguang Ai, W. John Wilbur, Zhe He, R. Andrew Taylor, Qingyu Chen and Zhiyong Lu ()
Additional contact information
Qiao Jin: National Institutes of Health (NIH)
Zhizheng Wang: National Institutes of Health (NIH)
Yifan Yang: National Institutes of Health (NIH)
Qingqing Zhu: National Institutes of Health (NIH)
Donald Wright: Yale University
Thomas Huang: Yale University
Nikhil Khandekar: National Institutes of Health (NIH)
Nicholas Wan: National Institutes of Health (NIH)
Xuguang Ai: Yale University
W. John Wilbur: National Institutes of Health (NIH)
Zhe He: National Institutes of Health (NIH)
R. Andrew Taylor: Yale University
Qingyu Chen: Yale University
Zhiyong Lu: National Institutes of Health (NIH)

Nature Communications, 2025, vol. 16, issue 1, 1-11

Abstract: Abstract Clinical calculators play a vital role in healthcare, but their utilization is often hindered by usability and dissemination challenges. We introduce AgentMD, a novel language agent capable of curating and applying clinical calculators across various clinical contexts. As a tool builder, AgentMD first uses PubMed to curate a diverse set of 2,164 executable clinical calculators with over 85% accuracy for quality checks and over 90% pass rate for unit tests. As a tool user, AgentMD autonomously selects and applies the relevant clinical calculators. Our evaluations show that AgentMD significantly outperforms GPT-4 for risk prediction (87.7% vs. 40.9% in accuracy). Results on 698 real-world emergency department notes confirm that AgentMD accurately computes medical risks at an individual level. Moreover, AgentMD can provide population-level insights for institutional risk management. Our study illustrates the capabilities of language agents to curate and utilize clinical calculators for both individual patient care and at-scale healthcare analytics.

Date: 2025
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-025-64430-x Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:16:y:2025:i:1:d:10.1038_s41467-025-64430-x

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-025-64430-x

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().