CoChat

Text mining to support abstract screening for knowledge syntheses: a semi-automated workflow

Open access

The DOI matches its Crossref record; the references it cites are not checked yet.

Abstract

Background: Current text mining tools supporting abstract screening in systematic reviews are not widely used, in part because they lack sensitivity and precision. We set out to develop an accessible, semi-automated “workflow” to conduct abstract screening for systematic reviews and other knowledge synthesis methods. Methods: We adopt widely recommended text-mining and machine-learning methods to (1) process title-abstracts into numerical training data; and (2) train a classification model to predict eligible abstracts. The predicted abstracts are screened by human reviewers for (“true”) eligibility, and the newly eligible abstracts are used to identify similar abstracts, using near-neighbor methods, which are also screened. These abstracts, as well as their eligibility results, are used to update the classification model, and the above steps are iterated until no new eligible abstracts are identified. The workflow was implemented in R and evaluated using a systematic review of insulin formulations for type-1 diabetes (14,314 abstracts) and a scoping review of knowledge-synthesis methods (17,200 abstracts). Workflow performance was evaluated against the recommended practice of screening abstracts by 2 reviewers, independently. Standard measures were examined: sensitivity (inclusion of all truly eligible abstracts), specificity (exclusion of all truly ineligible abstracts), precision (inclusion of all truly eligible abstracts among all abstracts screened as eligible), F1-score (harmonic average of sensitivity and precision), and accuracy (correctly predicted eligible or ineligible abstracts). Workload reduction was measured as the hours the workflow saved, given only a subset of abstracts needed human screening. Results: With respect to the systematic and scoping reviews respectively, the workflow attained 88%/89% sensitivity, 99%/99% specificity, 71%/72% precision, an F1-score of 79%/79%, 98%/97% accuracy, 63%/55% workload reduction, with 12%/11% fewer abstracts for full-text retrieval and screening, and 0%/1.5% missed studies in the completed reviews. Conclusion: The workflow was a sensitive, precise, and efficient alternative to the recommended practice of screening abstracts with 2 reviewers. All eligible studies were identified in the first case, while 6 studies (1.5%) were missed in the second that would likely not impact the review’s conclusions. We have described the workflow in language accessible to reviewers with limited exposure to natural language processing and machine learning, and have made the code available to reviewers.

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 · 10.1186/s13643-021-01700-x

Cites

Statistics

Figures

Fig. 1 Workflow — Phase 1: Preparation of abstracts for machine learning, and creation of the training dataset. DFMs: document feature matrices. Dark lines denote iterations. Inputs to the workflow are denoted by black boxes. Box 4a. SVD: singular value decomposition. Box 4b. LDA: latent Dirichlet allocation for topic modeling. Box 4c. Concept or word embeddings are vector representations of words and their relationships. Outputs of this workflow phase are the abstract features, as well as the screening results of the abstracts reviewed by the 2 human reviewers in order to generate the training dataset, denoted by the gray box
Fig. 1 Workflow — Phase 1: Preparation of abstracts for machine learning, and creation of the training dataset. DFMs: document feature matrices. Dark lines denote iterations. Inputs to the workflow are denoted by black boxes. Box 4a. SVD: singular value decomposition. Box 4b. LDA: latent Dirichlet allocation for topic modeling. Box 4c. Concept or word embeddings are vector representations of words and their relationships. Outputs of this workflow phase are the abstract features, as well as the screening results of the abstracts reviewed by the 2 human reviewers in order to generate the training dataset, denoted by the gray boxCC BY · PubMed Central
Fig. 2 Workflow — Phase 2: Screening of abstracts through human-guided machine-learning. Dark lines denote iterations. Inputs to the workflow are denoted by black boxes. Outputs from the workflow are denoted by a gray box. Upper black box and box 1 — SVD, singular value decomposition
Fig. 2 Workflow — Phase 2: Screening of abstracts through human-guided machine-learning. Dark lines denote iterations. Inputs to the workflow are denoted by black boxes. Outputs from the workflow are denoted by a gray box. Upper black box and box 1 — SVD, singular value decompositionCC BY · PubMed Central
Fig. 3 Workflow performance (%) vs recommended practice for abstracts screening (main analysis)
Fig. 3 Workflow performance (%) vs recommended practice for abstracts screening (main analysis)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

The citation lists are queued

They are fetched later and appear here then.

References 52 · Cited by 63

Research works printed but not linked: 2

  1. Joanna Briggs Institute. The Joanna Briggs Institute Reviewer’s Manual: 2014 edition. The Joanna Briggs Institute; 2014.
  2. Thomas J, Brunton J, Graziosi S. EPPI-reviewer 4: software for research synthesis. EPPI-Centre Software. London: Social Science Research Unit, Institute of Education; 2010.

Metadata

Authors
Pham, B., Jovanovic, J., Bagheri, E., Antony, J., Ashoor, H., Nguyen, T. T., Rios, P., Robson, R., Thomas, S. M., Watt, J., Straus, S. E., & Tricco, A. C.
Affiliations
  • St. Michael's Hospital (CA)
  • Toronto Metropolitan University (CA)
Corresponding author
Tricco, Andrea C.
Venue
Systematic Reviews
Published
2021-05-26
Volume
10
Issue
1
Pages
156-156
ISSN
2046-4053 (ISSN-L)
OpenAlex
W3165135368
Cited by
63
References
52
Citations by year
2026: 7 · 2025: 10 · 2024: 17 · 2023: 21 · 2022: 6 · 2021: 2
FWCI
6.67
Type
journal article
Language
en
Open access
Licence
Locations
  • Systematic Reviews (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • TSpace (University of Toronto) (submittedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • Repository of the University of Belgrade Faculty of Organizational Sciences (RFOS) (submittedVersion, cc-by)
Funders
  • Ontario Ministry of Research, Innovation and Science (15-0553-AWA)
  • Canada Excellence Research Chairs, Government of Canada (17-0126-AWA, 17-0245-SUB)
  • Natural Sciences and Engineering Research Council of Canada
Topics
  • Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews
  • Social Sciences › General Social Sciences › Computational and Text Analysis Methods
  • Physical Sciences › Computer Science › Artificial Intelligence › Advanced Text Analysis Techniques
Keywords
abstract screening, text mining, knowledge synthesis, semi-automated workflow, natural language processing
MeSH terms
Machine Learning, Systematic Reviews as Topic, Humans, Natural Language Processing, Workflow, Data Mining

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: Text mining to support abstract screening for knowledge syntheses: a semi-automated workflow. https://app.cochat.ai/papers/10.1186/s13643-021-01700-x
The paper
Pham, B., Jovanovic, J., Bagheri, E., Antony, J., Ashoor, H., Nguyen, T. T., Rios, P., Robson, R., Thomas, S. M., Watt, J., Straus, S. E., & Tricco, A. C. (2021). Text mining to support abstract screening for knowledge syntheses: a semi-automated workflow. Systematic Reviews. https://doi.org/10.1186/s13643-021-01700-x

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.