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.”
Influential
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
Alharbi, F., & Asiri, S. N. (2024) · Applied Sciences · doi:10.3390/app142210323 · Cited by 5
Tu, J., Nacke, L. E., & Rogers, K. (2025) · Interacting with Computers · doi:10.1093/iwc/iwaf001 · Cited by 4
Oami, T., Okada, Y., Maeda, K., & Nakada, T.-A. (2026) · Frontiers in Digital Health · doi:10.3389/fdgth.2026.1799623 · Cited by 4
“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).”
Brini, S., & Leung, T. I. (2026) · Journal of Medical Internet Research · doi:10.2196/92132 · Cited by 8
Rogić, S., Mancarci, B. O., Xu, B., Xiao, A., Yan, C., & Pavlidis, P. (2026) · Database · doi:10.1093/database/baag041 · Cited by 4
Kalmer, T. L., Ancajas, C. M. F., Cheng, Z., Oyedele, A. S., Davis, H. L., & Walker, A. S. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.08.01.606186 · Cited by 3
AI-Assisted Data Extraction with a Large Language Model: A Study Within ReviewsPreprint
Gartlehner, G., Kugley, S., Crotty, K., Viswanathan, M., Dobrescu, A. I., Nußbaumer-Streit, B., Booth, G., Treadwell, J. R., Han, J. M., Wagner, J., et al. (2025) · medRxiv · doi:10.1101/2025.03.20.25324350 · Cited by 3
Stuhlfauth, V., Saheb, Y., & Bouzouina, L. (2026) · Environmental Research Communications · doi:10.1088/2515-7620/ae4563 · Cited by 2
Fan, S., Chen, M., Doi, S. A. R., Ye, Z., Peng, Z., Tian, Y., Zhang, C., Furuya‐Kanamori, L., Lin, L., Mayo‐Wilson, E., et al. (2026) · BMJ Evidence-Based Medicine · doi:10.1136/bmjebm-2025-114044 · Cited by 5
Sulaimanov, U., Şanlıer, N., Moniri, A., Demir, B., Serikkanov, Y. S., BAYRAMOĞLU, A. R., Al-Jebur, M. S., Sanlier, M. Y., Erginoğlu, U., Ötleş, E., et al. (2026) · Journal of Clinical Medicine · doi:10.3390/jcm15114230 · Cited by 1
Chenchula, S., Srinivasamurthy, S. K., Vincent, V., Thakkar, H., Ganguly, S., Kayal, S., Keerthivasagam, S., Ramamoorthy, J. G., Sharma, S., Murugadoss, K., et al. (2026) · Pharmaceuticals · doi:10.3390/ph19081204 · Cited by 1
Liu, Y., Wang, X., Zhou, Z., He, Y., Li, Y., Liu, C., & Zhou, D. (2026) · Journal of Evaluation in Clinical Practice · doi:10.1111/jep.70596 · Cited by 1
From Research to Practice in Days, not Decades: Why Leaders Must Act now
Peltonen, L., Topaz, M., & Zhang, Z. (2025) · Journal of Medical Systems · doi:10.1007/s10916-025-02305-w · Cited by 2
Xia, Z., Ye, J., Hu, B., Qiang, Q., & Debnath, R. (2024) · Research Square · doi:10.21203/rs.3.rs-5063165/v1 · Cited by 1
Harrison, T., Hu, D., Jia, H., Tan, S. H., Chen, F., Zhang, Z., Lu, Q., Wang, J., Huang, M., Prokop, L. J., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5137601 · Cited by 2
Jansen, T., Liebenow, L. W., Schaller, N.-J., Hattie, J., & Møller, J. (2026) · Educational Psychology Review · doi:10.1007/s10648-026-10136-5 · Cited by 3
Derdouri, A., Oyama, T., Murayama, Y., & Masago, Y. (2026) · Research Square · doi:10.21203/rs.3.rs-9582053/v1
Lawton, A., Tripodi, N., Wospil, R., Wright, B., Menz, H. B., Martin, S. “., Bonanno, D. R., Linton, C., Bastani, A., Ross, A., et al. (2026) · BMJ Open · doi:10.1136/bmjopen-2025-113943
Applications and Limitations of Large Language Models in Digital Forensics: A Survey
Saunders, S. A., Ibrahem, M. I., & Abouyoussef, M. S. (2026) · IEEE International Conference on Secure IoT, Assured and Trusted Computing (SATC) · doi:10.1109/satc69565.2026.11542508
Performance of large language models in data extraction for evidence synthesis: A systematic review
Shankar, R., Lim, A., & Qian, X. (2026) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2026.105086 · Cited by 7
Zheng, X., Dong, P., Yuan, W., Fan, Y., & Chen, Y. (2026) · Heart Lung and Circulation · doi:10.1016/j.hlc.2026.05.032
Lai, H., & Li, Y. (2026) · Telematics and Informatics · doi:10.1016/j.tele.2026.102447
Pavlidis, P., Mancarci, B. O., Maximo, A., Yan, C., & Schwartz, R. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.07.30.741874
Şanlıer, N., Sulaimanov, U., Moniri, A., Demir, B., Ismayilova, G., Sanlier, M. Y., Erginoğlu, U., BAYRAMOĞLU, A. R., Al-Jebur, M. S., Ammanuel, S. G., et al. (2026) · Journal of Clinical Medicine · doi:10.3390/jcm15156005 · Cited by 1
Imre, A., Németh, B., Józwiak, Á. B., Nagy, B., Balkányi, L., Fasseeh, A. N., Kaló, Z., & Zemplenyi, A. (2026) · Expert Review of Pharmacoeconomics & Outcomes Research · doi:10.1080/14737167.2026.2717289
LLM-assisted evidence audit of late-stage cancer incidence as a screening trial endpointPreprint
Li, S., Zhang, W., Xing, X., Shen, Z., Wang, Y., Chen, Z., Leal-Neto, O. B., Yu, Y., Wu, C., & Lin, L. (2026) · medRxiv · doi:10.64898/2026.08.29.26361733
Jin, S., Thaivalappil, A., Young, I., & MacKay, M. (2026) · Knowledge · doi:10.3390/knowledge6030024
Research quality metrics as a complement to bibliometrics: an opinion paper
Hannerz, H., Hansen, K. S., Pejtersen, J. H., & Willadsen, H. K. (2026) · Scientometrics · doi:10.1007/s11192-026-05840-6
An Auditable Large Language Model Pipeline for Data Extraction in Systematic Literature ReviewsPreprint
Macháček, P. A., Segelcke, D., Vollert, J., Pogatzki-Zahn, E. M., & Pradier, B. (2026) · Research Square · doi:10.21203/rs.3.rs-11150018/v1
Bridging the Literacy Gap in Breast Reconstruction Patient Education Using Artificial Intelligence
Kim, E., Paliwoda, E. D., Farmer, R., Wakeman, M., Shihadeh, H., Kpodzo, D., & Schalet, B. J. (2026) · Aesthetic Plastic Surgery · doi:10.1007/s00266-026-06400-2
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.