A foundation model for human-AI collaboration in medical literature mining

Zifeng Wang (), Lang Cao, Qiao Jin, Joey Chan, Nicholas Wan, Behdad Afzali, Hyun-Jin Cho, Chang-In Choi, Mehdi Emamverdi, Manjot K. Gill, Sun-Hyung Kim, Yijia Li, Yi Liu, Yiming Luo, Hanley Ong, Justin F. Rousseau, Irfan Sheikh, Jenny J. Wei, Ziyang Xu, Christopher M. Zallek, Kyungsang Kim, Yifan Peng, Zhiyong Lu and Jimeng Sun ()
Additional contact information
Zifeng Wang: Keiji AI
Lang Cao: University of Illinois Urbana-Champaign
Qiao Jin: National Institutes of Health
Joey Chan: National Institutes of Health
Nicholas Wan: National Institutes of Health
Behdad Afzali: National Institutes of Health
Hyun-Jin Cho: Massachusetts General Hospital and Harvard Medical School
Chang-In Choi: Massachusetts General Hospital and Harvard Medical School
Mehdi Emamverdi: National Institutes of Health
Manjot K. Gill: Northwestern University Feinberg School of Medicine
Sun-Hyung Kim: Massachusetts General Hospital and Harvard Medical School
Yijia Li: University of Pittsburgh Medical Center
Yi Liu: Weill Cornell Medicine
Yiming Luo: Columbia University Irving Medical Center
Hanley Ong: Weill Cornell Medicine
Justin F. Rousseau: UT Southwestern Medical Center
Irfan Sheikh: UT Southwestern Medical Center
Jenny J. Wei: University of Washington
Ziyang Xu: NYU Langone Health
Christopher M. Zallek: OSF HealthCare Illinois Neurological Institute
Kyungsang Kim: Massachusetts General Hospital and Harvard Medical School
Yifan Peng: Weill Cornell Medicine
Zhiyong Lu: National Institutes of Health
Jimeng Sun: Keiji AI

Nature Communications, 2025, vol. 16, issue 1, 1-15

Abstract: Abstract Applying artificial intelligence (AI) for systematic literature review holds great potential for enhancing evidence-based medicine, yet has been limited by insufficient training and evaluation. Here, we present LEADS, an AI foundation model trained on 633,759 samples curated from 21,335 systematic reviews, 453,625 clinical trial publications, and 27,015 clinical trial registries. In experiments, LEADS demonstrates consistent improvements over four cutting-edge large language models (LLMs) on six literature mining tasks, e.g., study search, screening, and data extraction. We conduct a user study with 16 clinicians and researchers from 14 institutions to assess the utility of LEADS integrated into the expert workflow. In study selection, experts using LEADS achieve 0.81 recall vs. 0.78 without, saving 20.8% time. For data extraction, accuracy reached 0.85 vs. 0.80, with 26.9% time savings. These findings encourage future work on leveraging high-quality domain data to build specialized LLMs that outperform generic models and enhance expert productivity in literature mining.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-025-62058-5 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_s41467-025-62058-5

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

DOI: 10.1038/s41467-025-62058-5

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 ().