Health AI Central
Peer-Reviewed Publication
J Am Med Inform Assoc2025;32(11):1718-1725.November 1, 2025Journal Article

Enabling inclusive systematic reviews: incorporating preprint articles with large language model-driven evaluations.

Rui Yang1, Jiayi Tong2, Haoyuan Wang3, Hui Huang4, Ziyang Hu5, Peiyu Li3, Nan Liu1, Christopher J Lindsell3,6, Michael J Pencina3, Yong Chen7, Chuan Hong3,6
1Centre for Quantitative Medicine, Duke-NUS Medical School, Singapore, 169857, Singapore.
2Department of Biostatistics, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD, 21205, United States.
3Department of Biostatistics and Bioinformatics, Duke School of Medicine, Durham, NC, 27710, United States.
4Children's Healthcare of Atlanta, Emory University School of Medicine, Atlanta, GA, 30329, United States.
5Department of Genome Sciences, University of Virginia, Charlottesville, VA, 22903, United States.
6Duke Clinical Research Institute, Duke University, Durham, NC, 27701, United States.
7Department of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, 19104, United States.
PubMed PMC DOI PDF

Abstract

OBJECTIVES: Systematic reviews in comparative effectiveness research require timely evidence synthesis. With the rapid advancement of medical research, preprint articles play an increasingly important role in accelerating knowledge dissemination. However, as preprint articles are not peer-reviewed before publication, their quality varies significantly, posing challenges for evidence inclusion in s…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free AccountSign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.