A comparative study of screening performance between abstrackr and GPT models: Systematic review and contextual analysis
The DOI matches its Crossref record; 44 of the 44 references it cites were found in a registry or an index.
Abstract
BACKGROUND: Systematic reviews (SRs) and rapid reviews (RRs) are critical methodologies for synthesizing existing research evidence. However, the growing volume of literature has made the process of screening studies one of the most challenging steps in conducting systematic reviews. METHODS: This systematic review aimed to compare the performance of Abstrackr and GPT models (including GPT-3.5 and GPT-4) in literature screening for systematic reviews. We identified relevant studies through comprehensive searches in PubMed, Cochrane Library, and Web of Science, focusing on those that provided key performance metrics such as recall, precision, specificity, and F1 score. RESULTS: GPT models demonstrated superior performance compared to Abstrackr in precision (0.51 vs. 0.21), specificity (0.84 vs. 0.71), and F1 score (0.52 vs. 0.31), reflecting a higher overall efficiency and better balance in screening. This makes GPT models particularly effective in reducing false positives during fine-screening tasks. CONCLUSION: Abstrackr and GPT models each offer distinct advantages in literature screening. Abstrackr is more suitable for the initial screening phases, whereas GPT models excel in fine-screening tasks. To optimize the efficiency and accuracy of systematic reviews, future screening tools could integrate the strengths of both models, potentially leading to the development of hybrid systems tailored to different stages of the screening process.
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
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.
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
Rayyan-a web and mobile app for systematic reviews.
Ouzzani, M., Hammady, H., Fedorowicz, Z., & Elmagarmid, A. (2016) · Systematic Reviews · doi:10.1186/s13643-016-0384-4 · Cited by 26,092 · cited 1×
“This suggests that Abstrackr has a higher rate of false positives when marking relevant studies, while GPT achieves significantly better accuracy in screening relevant articles [29, 30].”
Natural language processing: state of the art, current trends and challenges
Khurana, D., Koli, A., Khatter, K., & Singh, S. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-022-13428-4 · Cited by 1,823 · cited 2×
“This means that many studies marked as relevant by Abstrackr are actually irrelevant, significantly increasing the screening workload [39].”
Borah, R., Brown, A. W., Capers, P. L., & Kaiser, K. A. (2017) · BMJ Open · doi:10.1136/bmjopen-2016-012545 · Cited by 737
A full systematic review was completed in 2 weeks using automation tools: a case study
Clark, J., Glasziou, P., Del Mar, C., Bannach-Brown, A., Stehlik, P., & Scott, A. M. (2020) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2020.01.008 · Cited by 687 · cited 1×
“The performance of Abstrackr and GPT models was evaluated using common metrics: recall, precision, specificity, F1 score, accuracy, and error rates [10].”
Chelli, M., Descamps, J., Lavoué, V., Trojani, C., Azar, M., Deckert, M., Raynier, J.-L., Clowez, G., Boileau, P., & Ruetsch-Chelli, C. (2024) · Journal of Medical Internet Research · doi:10.2196/53164 · Cited by 602
Deploying an interactive machine learning system in an evidence-based practice center: abstrackr
Wallace, B. C., Small, K., Brodley, C. E., Lau, J., & Trikalinos, T. A. (2012) · Proceedings of the 2nd ACM SIGHIT International Health Informatics Symposium · doi:10.1145/2110363.2110464 · Cited by 532
Prompt engineering in consistency and reliability with the evidence-based guideline for LLMs
Wang, L., Chen, X., Deng, X., Wen, H., You, M., Liu, W., Li, Q., & Li, J. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01029-4 · Cited by 390
Artificial intelligence in systematic reviews: promising when appropriately used
van Dijk, S. H. B., Brusse-Keizer, M. G. J., Bucsán, C. C., van der Palen, J., Doggen, C. J. M., & Lenferink, A. (2023) · BMJ Open · doi:10.1136/bmjopen-2023-072254 · Cited by 256
Automated Paper Screening for Clinical Reviews Using Large Language Models
Guo, E., Gupta, M., Deng, J., Park, Y.-J., Paget, M., & Naugler, C. (2023) · arXiv · doi:10.48550/arxiv.2305.00844 · Cited by 230
Dennstädt, F., Zink, J., Putora, P. M., Hastings, J., & Čihorić, N. (2024) · Systematic Reviews · doi:10.1186/s13643-024-02575-4 · Cited by 220
Research works printed but not linked: 1
- Dennstadt F, Zink J, Putora PM, et al. Syst Rev. 2024;13(1):158. · DOI
Cited by
Teaching with intelligence; AI-enhanced pedagogies in nursing education: a scoping review
Nugent, L., Murray, B., Moore, Z., Patton, D., O’Connor, T., Watson, C., Walsh, K., Renjith, V., & George, J. (2026) · Nurse Education in Practice · doi:10.1016/j.nepr.2026.104878 · Cited by 4
Metadata
- Authors
- Xu, S., Zhao, Z., Liu, X., & Meng, X.-L.
- Venue
- BMC Medical Informatics and Decision Making
- Published
- 2025-08-07
- Volume
- 25
- Issue
- 1
- ISSN
- 1472-6947
- Cited by
- 8
- References
- 44
- Language
- en
- Licence
- creativecommons.org/licenses/by-nc-nd/4.0 (tdm)
- creativecommons.org/licenses/by-nc-nd/4.0 (vor)
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: A comparative study of screening performance between abstrackr and GPT models: Systematic review and contextual analysis. https://app.cochat.ai/papers/10.1186/s12911-025-03138-w
- The paper
- Xu, S., Zhao, Z., Liu, X., & Meng, X.-L. (2025). A comparative study of screening performance between abstrackr and GPT models: Systematic review and contextual analysis. BMC Medical Informatics and Decision Making. https://doi.org/10.1186/s12911-025-03138-w
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.