CoChat

Critical Assessment of Large Language Models’ (ChatGPT) Performance in Data Extraction for Systematic Reviews: Exploratory Study

Open access

Published version of a preprint

The DOI matches its Crossref record; 38 of the 38 references it cites were found in a registry or an index.

Abstract

Background: Systematic literature reviews (SLRs) are foundational for synthesizing evidence across diverse fields and are especially important in guiding research and practice in health and biomedical sciences. However, they are labor intensive due to manual data extraction from multiple studies. As large language models (LLMs) gain attention for their potential to automate research tasks and extract basic information, understanding their ability to accurately extract explicit data from academic papers is critical for advancing SLRs. Objective: Our study aimed to explore the capability of LLMs to extract both explicitly outlined study characteristics and deeper, more contextual information requiring nuanced evaluations, using ChatGPT (GPT-4). Methods: We screened the full text of a sample of COVID-19 modeling studies and analyzed three basic measures of study settings (ie, analysis location, modeling approach, and analyzed interventions) and three complex measures of behavioral components in models (ie, mobility, risk perception, and compliance). To extract data on these measures, two researchers independently extracted 60 data elements using manual coding and compared them with the responses from ChatGPT to 420 queries spanning 7 iterations. Results: ChatGPT’s accuracy improved as prompts were refined, showing improvements of 33% and 23% between the initial and final iterations for extracting study settings and behavioral components, respectively. In the initial prompts, 26 (43.3%) of 60 ChatGPT responses were correct. However, in the final iteration, ChatGPT extracted 43 (71.7%) of the 60 data elements, showing better performance in extracting explicitly stated study settings (28/30, 93.3%) than in extracting subjective behavioral components (15/30, 50%). Nonetheless, the varying accuracy across measures highlighted its limitations. Conclusions: Our findings underscore LLMs’ utility in extracting basic as well as explicit data in SLRs by using effective prompts. However, the results reveal significant limitations in handling nuanced, subjective criteria, emphasizing the necessity for human oversight.

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 · 10.2196/68097

Cites

38 of 38 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1. Average percentage of correct ChatGPT responses throughout iterations (bars) in comparison to the average accuracy of screeners before consensus (dashed lines) across study settings and behavioral components in COVID-19 models.
Figure 1. Average percentage of correct ChatGPT responses throughout iterations (bars) in comparison to the average accuracy of screeners before consensus (dashed lines) across study settings and behavioral components in COVID-19 models.CC BY · PubMed Central
Figure 2. Percentage of correct ChatGPT responses throughout iterations of each prompt. The red bars depict the progression of ChatGPT’s accuracy for the three study setting elements, and the blue bars present the progression for the three behavioral component elements. Since the location of analysis achieved 100% by the second version, we concluded further iterations for this prompt.
Figure 2. Percentage of correct ChatGPT responses throughout iterations of each prompt. The red bars depict the progression of ChatGPT’s accuracy for the three study setting elements, and the blue bars present the progression for the three behavioral component elements. Since the location of analysis achieved 100% by the second version, we concluded further iterations for this prompt.CC BY · 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 38 references

Research works printed but not linked: 1

  1. Li T Higgins JP Deeks JJ . Chapter 5: collecting data. In: Higgins JPT Thomas J Chandler J Cumpston M Li T Page MJ Welch VA , editors. Cochrane Handbook for Systematic Reviews of Interventions. Cochrane; 2023. URL: https://www.cochrane.org/authors/handbooks-and-manuals/handbook [Accessed 15-08-2025]

Cited by

See all 35

Metadata

Authors
Mahmoudi, H., Chang, D., Lee, H., Ghaffarzadegan, N., & Jalali, M. S.
Affiliations
  • Harvard University (US)
  • Virginia Tech (US)
Corresponding author
Jalali, Mohammad S
Venue
JMIR AI
Published
2025-09-11
Volume
4
Pages
e68097-e68097
ISSN
2817-1705 (ISSN-L)
OpenAlex
W4414113806
Cited by
35
References
34
Citations by year
2026: 23 · 2025: 7
FWCI
5.73
Type
journal article
Language
en
Open access
Licence
cc-by
Locations
  • JMIR AI (publishedVersion, cc-by)
  • SSRN Electronic Journal (acceptedVersion)
  • PubMed (publishedVersion)
  • PubMed Central (publishedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • National Science Foundation (2229819)
  • Division of Social and Economic Sciences (2229819)
  • Division of Mathematical Sciences (2229819)
Topics
  • Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews
  • Social Sciences › General Social Sciences › Computational and Text Analysis Methods
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
Keywords
large language models, ChatGPT, data extraction, systematic reviews, prompt engineering, study characteristics, behavioral component, risk perception, compliance, mobility, extraction accuracy, human oversight

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: Critical Assessment of Large Language Models’ (ChatGPT) Performance in Data Extraction for Systematic Reviews: Exploratory Study. https://app.cochat.ai/papers/10.2196/68097
The paper
Mahmoudi, H., Chang, D., Lee, H., Ghaffarzadegan, N., & Jalali, M. S. (2025). Critical Assessment of Large Language Models’ (ChatGPT) Performance in Data Extraction for Systematic Reviews: Exploratory Study. JMIR AI. https://doi.org/10.2196/68097

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.