CoChat

AI-driven evidence synthesis: data extraction of randomized controlled trials with large language models

Open access

The DOI matches its Crossref record; 27 of the 27 references it cites were found in a registry or an index.

Abstract

The advancement of large language models (LLMs) presents promising opportunities to enhance evidence synthesis efficiency, particularly in data extraction processes, yet existing prompts for data extraction remain limited, focusing primarily on commonly used items without accommodating diverse extraction needs. This research letter developed structured prompts for LLMs and evaluated their feasibility in extracting data from randomized controlled trials (RCTs). Using Claude (Claude-2) as the platform, we designed comprehensive structured prompts comprising 58 items across six Cochrane Handbook domains and tested them on 10 randomly selected RCTs from published Cochrane reviews. The results demonstrated high accuracy with an overall correct rate of 94.77% (95% CI: 93.66% to 95.73%), with domain-specific performance ranging from 77.97% to 100%. The extraction process proved efficient, requiring only 88 seconds per RCT. These findings substantiate the feasibility and potential value of LLMs in evidence synthesis when guided by structured prompts, marking a significant advancement in systematic review methodology.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1097/js9.0000000000002215

Cites

27 of 27 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1. Flow diagram of the main study process.
Figure 1. Flow diagram of the main study process.CC BY-SA · PubMed Central
Figure 2. Domain-specific data extraction correct rates.
Figure 2. Domain-specific data extraction correct rates.CC BY-SA · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 27 references

Cited by

See all 19

Metadata

Authors
Liu, J., Lai, H., Zhao, W., Huang, J., Xia, D., Liu, H., Luo, X., Wang, B., Pan, B., Hou, L., Chen, Y., & Ge, L.
Affiliations
  • Lanzhou University (CN)
  • Gansu University of Traditional Chinese Medicine (CN)
  • Chinese Academy of Medical Sciences & Peking Union Medical College (CN)
Corresponding author
Ge, Long
Venue
International Journal of Surgery
Published
2025-02-04
Volume
111
Issue
3
Pages
2722-2726
ISSN
1743-9159 (ISSN-L)
OpenAlex
W4407119832
Cited by
19
References
27
Citations by year
2026: 16 · 2025: 3
FWCI
12.02
Type
journal article
Language
en
Open access
Locations
  • International Journal of Surgery (publishedVersion, cc-by-sa)
  • SSRN Electronic Journal (acceptedVersion)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by-sa)
  • PubMed Central (publishedVersion, cc-by-sa)
  • PubMed (publishedVersion)
Funders
  • National Natural Science Foundation of China
  • China Academy of Chinese Medical Sciences
  • Fundamental Research Funds for the Central Universities
Topics
  • Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Social Sciences › General Social Sciences › Computational and Text Analysis Methods
Keywords
large language models, data extraction, evidence synthesis, randomized controlled trials, prompt engineering, structured prompting, Claude 2, Cochrane Handbook, systematic reviews
MeSH terms
Large Language Models, Artificial Intelligence, Humans, Randomized Controlled Trials as Topic, Information Storage and Retrieval

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: AI-driven evidence synthesis: data extraction of randomized controlled trials with large language models. https://app.cochat.ai/papers/10.1097/js9.0000000000002215
The paper
Liu, J., Lai, H., Zhao, W., Huang, J., Xia, D., Liu, H., Luo, X., Wang, B., Pan, B., Hou, L., Chen, Y., & Ge, L. (2025). AI-driven evidence synthesis: data extraction of randomized controlled trials with large language models. International Journal of Surgery. https://doi.org/10.1097/js9.0000000000002215

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.