Automation of Systematic Reviews with Large Language Models

Importance Systematic reviews (SRs) inform evidence-based decision making. Yet, many take over a year to complete, are labor intensive, prone to human error, and face reproducibility challenges; thus limiting access to timely and reliable information.

To validate a large language model (LLM)-based workflow (otto-SR) to automate three of the most labour intensive tasks in performing SR’s: article screening, data extraction, and risk of bias assessment; and to assess its feasibility in rapidly updating existing reviews. Design, setting, and participants We conducted a validation study in four phases, with direct benchmarking against graduate-level human researchers in phases 1 and 2. Phase 1: article screening performance was measured across 32,357 citations from 5 systematic reviews. The reference standard consisted of the original reviews’ screening decisions after full-text screening. Phase 2: data extraction performance was measured across 4,495 data points from 495 studies in 7 reviews. Phase 3: risk of bias assessment (ROB2, Newcastle-Ottawa, QUADAS2) performance was measured across 345 studies from 12 reviews. Reference standards for Phase 2 and Phase 3 were created after blinded adjudication of the original review extraction and RoB assessments. Phase 4: otto-SR was used to reproduce and update the primary analysis from an issue of Cochrane reviews (n=12 reviews, 146,276 citations), with analytical comparisons to the original meta-analyzed findings. All discrepancies underwent dual human review.

otto-SR showed high performance in phase 1 article screening (otto-SR: 96.7% sensitivity, 97.9% specificity; human: 81.7% sensitivity, 98.1% specificity) and phase 2 data extraction (otto-SR: 93.1% accuracy; human: 79.7% accuracy). In phase 3, otto-SR demonstrated high interrater reliability for risk of bias judgements (ROB2 0.98, Newcastle-Ottawa 0.95, QUADAS2 0.74; Gwet AC2). In phase 4, otto-SR, reproduced and updated the primary analysis from an issue of Cochrane reviews. Across Cochrane reviews, otto-SR incorrectly excluded a median of 0 studies (IQR 0 to 0.25), and found nearly twice as many eligible studies compared to the original authors (n= 114 vs. 64). Meta-analyses based on otto-SR generated screening and extraction outputs, subsequently verified through dual human review, yielded newly statistically significant effect estimates in 2 reviews and negated significance in 1 review.

and relevance LLMs have high performance in article screening, data extraction, and risk of bias assessments. They can rapidly reproduce and update existing systematic reviews, laying the foundation for automated, scalable, and reliable evidence synthesis. Competing Interest Statement There was no direct funding support for this manuscript. N.B reports grants from the Public Health Agency of Canada through Canada's COVID-19 Immunity Task Force, the World Health Organization Health Emergencies Programme, the Robert Koch Institute, the Canadian Medical Association Joule Innovation Fund, the Canadian Association of Emergency Physicians and Alberta Health Services Emergency Strategic Clinical Network. Disclosures for G.M.C. can be found at http://arep.med.harvard.edu/gmc/tech.html. R.K.A. is employed at OpenAI and owns stock as part of the standard compensation package. R.A. reports grants from the CIHR Institute of Genetics. C.C. P.C. J.S. are founders of and hold equity in Otto Science Institute. N.B, D.M, A.C.T, A.B hold equity in Otto Science Institute. Of note, Otto Science institute was founded after the time of initial manuscript writing. No funding source had any role in the design of this study, its execution, analyses, interpretation of the data, or decision to submit results. Funding Statement There was no direct funding support for this manuscript. Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes Footnotes ↵† Co-supervision of work - Issue with figure rendering. Uploaded new PDF in an effort to address Data Availability All datasets and code used for data analysis will be made available on publication.