Critical Assessment of Large Language Models’ (ChatGPT) Performance in Data Extraction for Systematic Reviews: Exploratory Study
Open accessPublished 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.
Integrity signals
Registry
Cites
Statistics
Figures


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.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Although these proof-of-concept studies have reported encouraging results and the potential to substantially reduce manual workload and human error, most evaluations have been limited to single models, small or restricted datasets, or single extraction runs (15–20).”
From Performance of large language models and prompt engineering strategies for data extraction in systematic reviews (2026) · cites this paper as [15]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“background characteristics were extracted with high accuracy by recent LLMs (12, 14–16)”
From Performance of large language models and prompt engineering strategies for data extraction in systematic reviews (2026) · cites this paper as [15]
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
Estimated effectiveness of symptom and risk screening to prevent the spread of COVID-19
Gostic, K., Gomez, A. C., Mummah, R. O., Kucharski, A. J., & Lloyd-Smith, J. O. (2020) · eLife · doi:10.7554/elife.55570 · Cited by 417
Automating data extraction in systematic reviews: a systematic review
Jonnalagadda, S. R., Goyal, P., & Huffman, M. D. (2015) · Systematic Reviews · doi:10.1186/s13643-015-0066-7 · Cited by 287
Can ChatGPT Write a Good Boolean Query for Systematic Review Literature Search?
Wang, S., Scells, H., Koopman, B., & Zuccon, G. (2023) · Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.1145/3539618.3591703 · Cited by 275 · cited 1×
“First, this study focused on one aspect of the SLR process, given that other steps (eg, writing Boolean query formulations [35] and screening titles and abstracts [10,36]) have already been examined in greater detail.”
Khraisha, Q., Put, S., Kappenberg, J., Warraitch, A., & Hadfield, K. (2024) · Research Synthesis Methods · doi:10.1002/jrsm.1715 · Cited by 269 · cited 4×
“To understand whether recently developed LLMs can overcome this barrier, many studies have evaluated the performance of various LLMs in automating SLR tasks [10-12].”
InfluentialKhraisha, Q., Put, S., Kappenberg, J., Warraitch, A., & Hadfield, K. (2023) · arXiv · doi:10.48550/arxiv.2310.17526 · Cited by 268
ChatGPT for Automated Qualitative Research: Content Analysis
Bijker, R., Merkouris, S., Dowling, N. A., & Rodda, S. N. (2024) · Journal of Medical Internet Research · doi:10.2196/59050 · Cited by 265
Prompt Engineering in Medical Education
Heston, T., & Khun, C. (2023) · International Medical Education · doi:10.3390/ime2030019 · Cited by 232
Using artificial intelligence methods for systematic review in health sciences: A systematic review
Blaizot, A., Veettil, S. K., Saidoung, P., Moreno‐Garcia, C. F., Wiratunga, N., Aceves‐Martins, M., Lai, N. M., & Chaiyakunapruk, N. (2022) · Research Synthesis Methods · doi:10.1002/jrsm.1553 · Cited by 223
Qureshi, R., Shaughnessy, D., Gill, K. A. R., Robinson, K. A., Li, T., & Agai, E. (2023) · Systematic Reviews · doi:10.1186/s13643-023-02243-z · Cited by 201
Giordano, G., Colaneri, M., Di Filippo, A., Blanchini, F., Bolzern, P., De Nicolao, G., Sacchi, P., Colaneri, P., & Bruno, R. (2021) · Nature Medicine · doi:10.1038/s41591-021-01334-5 · Cited by 192 · cited 5×
“Two trained researchers independently extracted data from the 10 studies [19-28] and then reconciled discrepancies in their findings—6 related to study settings and 11 to behavioral components—for convergence.”
InfluentialArtificial intelligence to automate the systematic review of scientific literature
de la Torre-López, J., Ramírez, A., & Romero, J. R. (2023) · Computing · doi:10.1007/s00607-023-01181-x · Cited by 170
Data extraction for evidence synthesis using a large language model: A proof-of-concept study
Gartlehner, G., Kahwati, L., Hilscher, R., Thomas, I., Kugley, S., Crotty, K., Viswanathan, M., Nussbaumer‐Streit, B., Booth, G., Erskine, N., et al. (2024) · Research Synthesis Methods · doi:10.1002/jrsm.1710 · Cited by 164 · cited 1×
“These results support previous research, which indicates the potential of LLMs for handling basic data extraction tasks effectively [10,11] and their use as a collaborator [32] or a second rater [33] in SLRs.”
Scherbakov, D., Hubig, N., Jansari, V., Bakumenko, A., & Lenert, L. A. (2024) · arXiv · doi:10.48550/arxiv.2409.04600 · Cited by 156
Scherbakov, D., Hubig, N., Jansari, V., Bakumenko, A., & Lenert, L. A. (2025) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocaf063 · Cited by 154
Systematic reviews: Brief overview of methods, limitations, and resources
Owens, J. K. (2021) · Nurse author & editor · doi:10.1111/nae2.28 · Cited by 144
How to optimize the systematic review process using AI tools
Fabiano, N., Gupta, A., Bhambra, N., Luu, B., Wong, S., Maaz, M., Fiedorowicz, J. G., Smith, A. L., & Solmi, M. (2024) · JCPP Advances · doi:10.1002/jcv2.12234 · Cited by 130 · cited 1×
“Several reviews have found that artificial intelligence (AI)–enabled methods exhibit reasonable performance and improved efficiency in literature screening [5-9], an integral component of SLRs.”
Sneppen, K., Nielsen, B. F., Taylor, R. J., & Simonsen, L. (2021) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2016623118 · Cited by 125
Data extraction methods for systematic review (semi)automation: a living systematic review
Schmidt, L., Olorisade, B. K., McGuinness, L. A., Thomas, J., & Higgins, J. P. T. (2021) · F1000Research · doi:10.12688/f1000research.51117.1 · Cited by 106
Quantifying the impact of quarantine duration on COVID-19 transmission
Ashcroft, P., Lehtinen, S., Angst, D. C., Low, N. N., & Bonhoeffer, S. (2021) · eLife · doi:10.7554/elife.63704 · Cited by 94
Systematic reviews: Structure, form and content
Phillips, V., & Barker, E. (2021) · Journal of Perioperative Practice · doi:10.1177/1750458921994693 · Cited by 91
Feng, Y., Liang, S., Zhang, Y., Chen, S., Wang, Q., Huang, T., Sun, F., Liu, X., Zhu, H., & Pan, H. (2022) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocac066 · Cited by 87
Screening articles for systematic reviews with ChatGPT
Syriani, E., David, I., & Kumar, G. (2024) · Journal of Computer Languages · doi:10.1016/j.cola.2024.101287 · Cited by 82
Performance of two large language models for data extraction in evidence synthesis
Konet, A., Thomas, I., Gartlehner, G., Kahwati, L., Hilscher, R., Kugley, S., Crotty, K., Viswanathan, M., & Chew, R. (2024) · Research Synthesis Methods · doi:10.1002/jrsm.1732 · Cited by 79
Data extraction methods for systematic review (semi)automation: Update of a living systematic review
Schmidt, L., Finnerty, A. N., Elmore, R., Olorisade, B. K., Thomas, J., & Higgins, J. P. T. (2023) · F1000Research · doi:10.12688/f1000research.51117.2 · Cited by 74
Application ChatGPT in conducting systematic reviews and meta-analyses
Mahuli, S. A., Rai, A., Mahuli, A. V., & Kumar, A. (2023) · British Dental Journal · doi:10.1038/s41415-023-6132-y · Cited by 61 · cited 1×
“Given the recent rapid advancement of large language models (LLMs), researchers have proposed their potential utility in conducting SLRs [3,4].”
ChatGPT-4o can serve as the second rater for data extraction in systematic reviews
Motzfeldt Jensen, M., Brix Danielsen, M., Riis, J., Assifuah Kristjansen, K., Andersen, S., Okubo, Y., & Jørgensen, M. G. (2025) · PLOS ONE · doi:10.1371/journal.pone.0313401 · Cited by 60
Evaluating literature reviews conducted by humans versus ChatGPT: comparative study
Mostafapour, M., Fortier, J. H., Pacheco, K., Murray, H., & Garber, G. (2024) · JMIR AI · doi:10.2196/56537 · Cited by 55 · cited 1×
“…advantages in assisting researchers, such as having rapid response times and providing high-level summaries of results [15]; however, a recent study revealed the shortcomings in ChatGPT’s depth of knowledge and contextual understanding for conducting SLRs in comparison to researchers [16].”
Paul, A., Chatterjee, S., & Bairagi, N. (2020) · medRxiv · doi:10.1101/2020.04.08.20055095 · Cited by 48
Wong, M. C. S., Ng, R. W. Y., Chong, K. C., Lai, C. K. C., Huang, J., Chen, Z., Boon, S. S., & Chan, P. K. S. (2020) · BMJ Global Health · doi:10.1136/bmjgh-2020-003573 · Cited by 48
Kinoshita, R., Anzai, A., Jung, S.-M., Linton, N. M., Miyama, T., Kobayashi, T., Hayashi, K., Suzuki, A., Yang, Y., Akhmetzhanov, A. R., et al. (2020) · Journal of Clinical Medicine · doi:10.3390/jcm9103125 · Cited by 40
An agent-based epidemic model REINA for COVID-19 to identify destructive policiesPreprint
Tuomisto, J. T., Yrjölä, J., Kolehmainen, M., Bonsdorff, J., Pekkanen, J., & Tikkanen, T. (2020) · medRxiv · doi:10.1101/2020.04.09.20047498 · Cited by 36
Ebigbo, A., Römmele, C., Bartenschlager, C. C., Temizel, S., Kling, E., Brunner, J. O., & Messmann, H. (2020) · Endoscopy · doi:10.1055/a-1294-0427 · Cited by 30
Impact of Superspreaders on dissemination and mitigation of COVID-19Preprint
Sneppen, K., Taylor, R. J., & Simonsen, L. (2020) · medRxiv · doi:10.1101/2020.05.17.20104745 · Cited by 27
Achter, S., Borit, M., Cottineau, C., Meyer, M., Polhill, G. J., & Radchuk, V. (2023) · Environmental Modelling & Software · doi:10.1016/j.envsoft.2023.105867 · Cited by 24
Using ChatGPT and other forms of generative AI in systematic reviews: Challenges and opportunities
Hossain, M. M. (2023) · Journal of medical imaging and radiation sciences · doi:10.1016/j.jmir.2023.11.005 · Cited by 22
Automated contact tracing: a game of big numbers in the time of COVID-19
Kim, H., & Paul, A. (2021) · Journal of The Royal Society Interface · doi:10.1098/rsif.2020.0954 · Cited by 21
Large language models streamline automated systematic review: A preliminary study
Chen, X., & Xue, Z. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.15702 · Cited by 14
Review of human behavior integration in COVID-19 modeling studies
Lee, H., Mahmoudi, H., Chang, D., & Jalali, M. S. (2025) · Journal of Public Health · doi:10.1093/pubmed/fdaf082 · Cited by 7
Self-citation
Research works printed but not linked: 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
Potential Roles of Large Language Models in the Production of Systematic Reviews and Meta-Analyses
Luo, X., Chen, F., Zhu, D., Wang, L., Wang, Z., Liu, H., Lyu, M., Wang, Y., Wang, Q., & Chen, Y. (2024) · Journal of Medical Internet Research · doi:10.2196/56780 · Cited by 109
Can generative AI reliably synthesise literature? exploring hallucination issues in ChatGPT
Adel, A., & Saleem, N. H. (2025) · AI & Society · doi:10.1007/s00146-025-02406-7 · Cited by 101
Gartlehner, G., Kahwati, L. C., Nußbaumer-Streit, B., Crotty, K., Hilscher, R., Kugley, S., Viswanathan, M., Thomas, I., Konet, A., Booth, G., et al. (2024) · BMJ Evidence-Based Medicine · doi:10.1136/bmjebm-2024-113199 · Cited by 42
Artificial Intelligence–Assisted Data Extraction With a Large Language Model: A Study Within Reviews
Gartlehner, G., Kugley, S., Crotty, K., Viswanathan, M., Dobrescu, A., Nussbaumer-Streit, B., Booth, G., Treadwell, J. R., Han, J. M., Wagner, J., et al. (2025) · Annals of Internal Medicine · doi:10.7326/annals-25-00739 · Cited by 36
Janoudi, G., Uzun, M., Disher, T. C., Jurdana, M., Fuzul, E., Ivkovic, J., & Hutton, B. (2025) · Value in Health · doi:10.1016/j.jval.2025.09.008 · Cited by 7
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
- Publisher
- JMIR Publications Inc.
- Published
- 2025-09-11
- Volume
- 4
- Pages
- e68097-e68097
- ISSN
- 2817-1705 (ISSN-L)
- PMC
- PMC12425462
- OpenAlex
- W4414113806
- Semantic Scholar
- 1a652dcdb155653c450fa18fc2c710da65dc6c8e
- Cited by
- 35
- References
- 34
- Citations by year
- 2026: 23 · 2025: 7
- FWCI
- 5.73
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- 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
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.