CoChat
Sign Up
Cited by 10Meta-analysis and systematic reviewsInformation Retrieval and Search BehaviorTopic Modeling

A comprehensive systematic review dataset is a rich resource for training and evaluation of AI systems for title and abstract screening

Open access
Chan, Gary C. K., He, Estrid, Leung, Janni, Verspoor, Karin·2025·Research Synthesis Methods
DOI 10.1017/rsm.2025.1PMC PMC12527522
Open this paper in CoChat — free account

Abstract

When conducting a systematic review, screening the vast body of literature to identify the small set of relevant studies is a labour-intensive and error-prone process. Although there is an increasing number of fully automated tools for screening, their performance is suboptimal and varies substantially across review topic areas. Many of these tools are only trained on small datasets, and most are not tested on a wide range of review topic areas. This study presents two systematic review datasets compiled from more than 8600 systematic reviews and more than 540000 abstracts covering 51 research topic areas in health and medical research. These datasets are the largest of their kinds to date. We demonstrate their utility in training and evaluating language models for title and abstract screening. Our dataset includes detailed metadata of each review, including title, background, objectives and selection criteria. We demonstrated that a small language model trained on this dataset with additional metadata has excellent performance with an average recall above 95% and specificity over 70% across a wide range of review topic areas. Future research can build on our dataset to further improve the performance of fully automated tools for systematic review title and abstract screening.

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

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Integrity signals

Registry

Crossref · 10.1017/rsm.2025.1

Cites

12 of 12 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

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

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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.

Cites

Flagged first, then by citations

Research works printed but not linked: 16

  1. [1]Leung J, Ferrari A, Baxter A, Schoultz M, Beattie M, Harris M. Systematic reviews: inducting research students into scholarly conversations? Higher Educ Res Dev. 2017; 36(1): 217– 220.
  2. [6]Feng Y, Liang S, Zhang Y, et al. Automated medical literature screening using artificial intelligence: a systematic review and meta-analysis. J Am Med Inform Assoc. 2022; 29(8): 1425– 1432. 35641139 PMC9277646
  3. [7]Chappell M, Edwards M, Watkins D, Marshall C, Graziadio S. Machine learning for accelerating screening in evidence reviews. Cochrane Evidence Synth Methods. 2023; 1(5):e12021. PMC11795896 40475071
  4. [8]Halman A, Oshlack A. Catchii: Empowering literature review screening in healthcare. Res Synth Methods. 2024; 15(1): 157– 165. 37771210
  5. [10]Aum S, Choe S. srBERT: automatic article classification model for systematic review using BERT. Syst Rev. 2021; 10: 1– 8. 34717768 PMC8556883
  6. [11]Sadri N, Cormack GV. Continuous active learning using pretrained transformers. arXiv preprint arXiv:220806955. 2022;
  7. [14]Alharbi A, Stevenson M. A dataset of systematic review updates. In: SIGIR’19: Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. 2019: 1257– 1260. doi: 10.1145/3331184.3331358 · DOI
  8. [16]Šuster S, Baldwin T, Verspoor K. Analysis of predictive performance and reliability of classifiers for quality assessment of medical evidence revealed important variation by medical area. J Clin Epidemiol. 2023; 159: 58– 69. 37120028
  9. [17]Wang S, Scells H, Koopman B, Zuccon G. Neural rankers for effective screening prioritisation in medical systematic review literature search. In: ADCS ’22: Proceedings of the 26th Australasian Document Computing Symposium. Article No.: 4, 2022: 1– 10. doi: 10.1145/3572960.3572980 · DOI
  10. [18]Robinson A, Thorne W, Wu BP, et al. Bio-sieve: Exploring instruction tuning large language models for systematic review automation. arXiv preprint arXiv:230806610. 2023.
  11. [19]Schiavo JH. PROSPERO: an international register of systematic review protocols. Med Ref Serv Q. 2019; 38(2): 171– 180. 31173570
  12. [20]Reimers N, Gurevych I. Sentence-bert: sentence embeddings using siamese bert-networks. arXiv preprint arXiv:190810084. 2019.
  13. [21]Lee J, Yoon W, Kim S, et al. BioBERT: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics. 2020; 36(4): 1234– 1240. 31501885 PMC7703786
  14. [22]Devlin J, Chang M-W, Lee K, Toutanova K. BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:181004805. 2018.
  15. [23]Wang S, Scells H, Clark J, Koopman B, Zuccon G. From little things big things grow: a collection with seed studies for medical systematic review literature search. 2022: 3176– 3186.
  16. [25]Brown TB, NBenjamin M, Ryder N, et al. Language models are few-shot learners. arXiv preprint arXiv:200514165. 2020.

Cited by

Sorted by citations

Authors
Chan, G. C. K., He, E., Leung, J., & Verspoor, K.
Affiliations
  • The University of Queensland (AU)
  • RMIT University (AU)
  • The University of Melbourne (AU)
Corresponding author
Chan, Gary C. K.
ORCID
Venue
Research Synthesis Methods
Publisher
Cambridge University Press (CUP)
Published
2025-03
Volume
16
Issue
2
Pages
308-322
ISSN
  • 1759-2879 (ISSN-L)
  • 1759-2887
DOI
10.1017/rsm.2025.1
PMC
PMC12527522
OpenAlex
W4408236898
Cited by
10
References
12
Citations by year
2026: 8 · 2025: 2
FWCI
1.90
Type
journal article
Language
en
Open access
Licence
Locations
  • Research Synthesis Methods (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • Minerva Access (University of Melbourne) (submittedVersion, cc-by)
Topics
  • Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews
  • Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
Keywords
abstract screening, language models, AI-assisted literature screening, data curation
MeSH terms
Metadata, Systematic Reviews as Topic, Artificial Intelligence, Humans, Natural Language Processing, Reproducibility of Results

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