Machine learning to assist risk-of-bias assessments in systematic reviews
Open accessThe DOI matches its Crossref record; 35 of the 36 references it cites were found in a registry or an index.
Abstract
BACKGROUND: Risk-of-bias assessments are now a standard component of systematic reviews. At present, reviewers need to manually identify relevant parts of research articles for a set of methodological elements that affect the risk of bias, in order to make a risk-of-bias judgement for each of these elements. We investigate the use of text mining methods to automate risk-of-bias assessments in systematic reviews. We aim to identify relevant sentences within the text of included articles, to rank articles by risk of bias and to reduce the number of risk-of-bias assessments that the reviewers need to perform by hand. METHODS: We use supervised machine learning to train two types of models, for each of the three risk-of-bias properties of sequence generation, allocation concealment and blinding. The first model predicts whether a sentence in a research article contains relevant information. The second model predicts a risk-of-bias value for each research article. We use logistic regression, where each independent variable is the frequency of a word in a sentence or article, respectively. RESULTS: We found that sentences can be successfully ranked by relevance with area under the receiver operating characteristic (ROC) curve (AUC) > 0.98. Articles can be ranked by risk of bias with AUC > 0.72. We estimate that more than 33% of articles can be assessed by just one reviewer, where two reviewers are normally required. CONCLUSIONS: We show that text mining can be used to assist risk-of-bias assessments.
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 cited source says what the claim attributes to it.
In the citing paper
“One further RoB (semi)automation tool was published by Millard et al. [35], it is available as web-application to support the bias-assessment process.”
From A narrative review of recent tools and innovations toward automating living systematic reviews and evidence syntheses (2023) · cites this paper as [35]
The cited source says what the claim attributes to it.
In the citing paper
“In related work, Millard et al16 found that predicting risks of bias from abstracts was possible, though modestly less accurately than using full-texts.”
From Trialstreamer: A living, automatically updated database of clinical trial reports (2020) · cites this paper as [16]
The cited source says what the claim attributes to it.
In the citing paper
“Data extraction systems have been created that can automatically retrieve unstructured information on the trial PICO elements,10–12 and risk of bias.13–16”
From Trialstreamer: A living, automatically updated database of clinical trial reports (2020) · cites this paper as [16]
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
The Cochrane Collaboration's tool for assessing risk of bias in randomised trials
Higgins, J. P. T., Altman, D. G., Gotzsche, P. C., Juni, P., Moher, D., Oxman, A. D., Savovic, J., Schulz, K. F., Weeks, L., Sterne, J. A. C., et al. (2011) · BMJ · doi:10.1136/bmj.d5928 · Cited by 33,817
Self-citationCochrane Handbook for Systematic Reviews of Interventions: Cochrane Book Series
(2008) · doi:10.1002/9780470712184 · Cited by 25,048
Self-citationDermyshi, E., Wang, Y., Yan, C., Hong, W., Qiu, G., Gong, X., & Zhang, T. (2017) · Neonatology · doi:10.1159/000454668 · Cited by 24,451
An introduction to ROC analysis
Fawcett, T. (2006) · Pattern Recognition Letters · doi:10.1016/j.patrec.2005.10.010 · Cited by 21,879
Predicting good probabilities with supervised learning
Niculescu-Mizil, A., & Caruana, R. (2005) · Proceedings of the 22nd international conference on Machine learning - ICML '05 · doi:10.1145/1102351.1102430 · Cited by 1,884
Allocation concealment in randomised trials: defending against deciphering
Schulz, K. F., & Grimes, D. A. (2002) · The Lancet · doi:10.1016/s0140-6736(02)07750-4 · Cited by 923
(2001) · Cited by 683
Hopewell, S., Dutton, S., Yu, L.-M., Chan, A.-W., & Altman, D. G. (2010) · BMJ · doi:10.1136/bmj.c723 · Cited by 504 · cited 1×
“An automated approach is limited by the degree of reporting in trial publications, as although the CONSORT statement specifies that information relevant to risk of bias should be described in a trial report, this is often not the case.(31) However, it is known that trial protocols can contain information that is not r…”
MethodSystematic review automation technologies
Tsafnat, G., Glasziou, P., Choong, M. K., Dunn, A., Galgani, F., & Coiera, E. (2014) · Systematic Reviews · doi:10.1186/2046-4053-3-74 · Cited by 472
Reducing Workload in Systematic Review Preparation Using Automated Citation Classification
Cohen, A. M., Hersh, W. R., Peterson, K., & Yen, P.-Y. (2006) · Journal of the American Medical Informatics Association · doi:10.1197/jamia.m1929 · Cited by 411
Semi-automated screening of biomedical citations for systematic reviews
Wallace, B. C., Trikalinos, T. A., Lau, J., Brodley, C., & Schmid, C. H. (2010) · BMC Bioinformatics · doi:10.1186/1471-2105-11-55 · Cited by 351
Risk of bias versus quality assessment of randomised controlled trials: cross sectional study
Hartling, L., Ospina, M., Liang, Y., Dryden, D. M., Hooton, N., Krebs Seida, J., & Klassen, T. P. (2009) · BMJ · doi:10.1136/bmj.b4012 · Cited by 348
Savović, J., Weeks, L., Sterne, J. A., Turner, L., Altman, D. G., Moher, D., & Higgins, J. P. (2014) · Systematic Reviews · doi:10.1186/2046-4053-3-37 · Cited by 340 · cited 1×
“One study estimated that 80% of risk-of-bias assessments took between 10 and 60 min to perform.(4) Furthermore, risk-of-bias judgements are imperfect.”
BackgroundSelf-citationRobotReviewer: evaluation of a system for automatically assessing bias in clinical trials
Marshall, I. J., Kuiper, J., & Wallace, B. C. (2016) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocv044 · Cited by 317
Applications of text mining within systematic reviews
Thomas, J., McNaught, J., & Ananiadou, S. (2011) · Research Synthesis Methods · doi:10.1002/jrsm.27 · Cited by 212
Pildal, J., Chan, A.-W., Hróbjartsson, A., Forfang, E., Altman, D. G., & Gøtzsche, P. C. (2005) · BMJ · doi:10.1136/bmj.38414.422650.8f · Cited by 209
ExaCT: automatic extraction of clinical trial characteristics from journal publications
Kiritchenko, S., de Bruijn, B., Carini, S., Martin, J., & Sim, I. (2010) · BMC Medical Informatics and Decision Making · doi:10.1186/1472-6947-10-56 · Cited by 188 · cited 1×
“Previous text mining work has used metrics that focus only on a set of n highly ranked examples.(18,25) For this sentence”
MethodHartling, L., Hamm, M. P., Milne, A., Vandermeer, B., Santaguida, P. L., Ansari, M., Tsertsvadze, A., Hempel, S., Shekelle, P., & Dryden, D. M. (2013) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2012.07.005 · Cited by 173
Supporting Systematic Reviews Using Text Mining
Ananiadou, S., Rea, B., Okazaki, N., Procter, R., & Thomas, J. (2009) · Social Science Computer Review · doi:10.1177/0894439309332293 · Cited by 144
Armijo-Olivo, S., Ospina, M., da Costa, B. R., Egger, M., Saltaji, H., Fuentes, J., Ha, C., & Cummings, G. G. (2014) · PLoS ONE · doi:10.1371/journal.pone.0096920 · Cited by 124
Rapid evidence assessments of research to inform social policy: taking stock and moving forward
Thomas, J., Newman, M., & Oliver, S. (2013) · Evidence and Policy · doi:10.1332/174426413x662572 · Cited by 109
A new algorithm for reducing the workload of experts in performing systematic reviews
Matwin, S., Kouznetsov, A., Inkpen, D., Frunza, O., & O'Blenis, P. (2010) · Journal of the American Medical Informatics Association · doi:10.1136/jamia.2010.004325 · Cited by 100
Hartling, L., Bond, K., Vandermeer, B., Seida, J., Dryden, D. M., & Rowe, B. H. (2011) · PLoS ONE · doi:10.1371/journal.pone.0017242 · Cited by 78
Identifying scientific artefacts in biomedical literature: The Evidence Based Medicine use case.
Hassanzadeh, H., Groza, T., & Hunter, J. (2014) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2014.02.006 · Cited by 62
Optimizing feature representation for automated systematic review work prioritization.
Cohen, A. M. (2008) · PubMed Central · Cited by 62
Automating Risk of Bias Assessment for Clinical Trials
Marshall, I. J., Kuiper, J., & Wallace, B. C. (2015) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2015.2431314 · Cited by 59
Automated information extraction of key trial design elements from clinical trial publications.
(2008) · PubMed Central · Cited by 54
Cohen, A. M., Adams, C. E., Davis, J. M., Yu, C., Yu, P. S., Meng, W., Duggan, L., McDonagh, M., & Smalheiser, N. R. (2010) · Proceedings of the 1st ACM International Health Informatics Symposium · doi:10.1145/1882992.1883046 · Cited by 45
Hsu, W. W. Y., Speier, W. F., & Taira, R. K. (2012) · PubMed · Cited by 30
Automating risk of bias assessment for clinical trials
Marshall, I. J., Kuiper, J., & Wallace, B. C. (2014) · Proceedings of the 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics · doi:10.1145/2649387.2649406 · Cited by 28
Improving Search for Evidence-based Practice using Information Extraction.
Zhao, J. Z., Kan, M., Procter, P. M., Zubaidah, S., Yip, W. K., & Li, G. M. (2010) · PubMed Central · Cited by 12
Spá: A Web-Based Viewer for Text Mining in Evidence Based Medicine
Kuiper, J., Marshall, I. J., Wallace, B., & Swertz, M. A. (2014) · Lecture notes in computer science · doi:10.1007/978-3-662-44845-8_33 · Cited by 10
Rate-Constrained Ranking and the Rate-Weighted AUC
Millard, L. A. C., Flach, P. A., & Higgins, J. P. T. (2014) · Lecture notes in computer science · doi:10.1007/978-3-662-44851-9_25 · Cited by 7
Self-citationRate-Oriented Point-Wise Confidence Bounds for ROC Curves
Millard, L. A. C., Kull, M., & Flach, P. A. (2014) · Lecture notes in computer science · doi:10.1007/978-3-662-44851-9_26 · Cited by 4
Self-citationRisk of bias:are judgements consistent between reviews?
Lensen, S., Farquhar, C., & Jordan-Cole, V. (2014) · ResearchSpace (University of Auckland) · Cited by 3
Research works printed but not linked: 1
- Flach PA . ROC analysis. In: Encyclopedia of Machine Learning. New York, NY: Springer, 2011.
Cited by
Considering bias and conflicts of interest among the included studies
Boutron, I., Page, M. J., Higgins, J. P., Altman, D. G., Lundh, A., Hróbjartsson, A., & on behalf of the Cochrane Bias Methods Group (2019) · Cochrane Handbook for Systematic Reviews of Interventions · doi:10.1002/9781119536604.ch7 · Cited by 258
Self-citationPrioritising references for systematic reviews with RobotAnalyst: A user study
Przybyła, P., Brockmeier, A. J., Kontonatsios, G., Le Pogam, M., McNaught, J., von Elm, E., Nolan, K., & Ananiadou, S. (2018) · Research Synthesis Methods · doi:10.1002/jrsm.1311 · Cited by 148
“Tools to automatically recognise these 69 , 67 - 70 , 71 can be”
BackgroundLi, T., Higgins, J. P., & Deeks, J. J. (2019) · Cochrane Handbook for Systematic Reviews of Interventions · doi:10.1002/9781119536604.ch5 · Cited by 127
Self-citationData 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
Self-citationVinkers, C. H., Lamberink, H. J., Tijdink, J. K., Heus, P., Bouter, L., Glasziou, P., Moher, D., Damen, J. A., Hooft, L., & Otte, W. M. (2021) · PLOS Biology · doi:10.1371/journal.pbio.3001162 · Cited by 103
Metadata
- Authors
- Millard, L. A., Flach, P. A., & Higgins, J. P.
- Affiliations
- University of Bristol (GB)
- MRC Integrative Epidemiology Unit (GB)
- Corresponding author
- Millard, Louise AC
- Venue
- International Journal of Epidemiology
- Publisher
- Oxford University Press (OUP)
- Published
- 2015-12-08
- Volume
- 45
- Issue
- 1
- Pages
- 266-277
- ISSN
- 0300-5771 (ISSN-L)
- 1464-3685
- PMC
- PMC4795562
- OpenAlex
- W2271587360
- Cited by
- 65
- References
- 36
- Citations by year
- 2026: 5 · 2025: 10 · 2024: 3 · 2023: 11 · 2022: 5 · 2021: 9 · 2020: 5 · 2019: 6 · 2018: 4 · 2017: 5 · 2016: 2
- FWCI
- 0.61
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- International Journal of Epidemiology (publishedVersion, cc-by)
- Europe PMC (PubMed Central) (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Bristol Research (University of Bristol) (submittedVersion, cc-by)
- Explore Bristol Research (submittedVersion, cc-by)
- HighWire Press Open Archive (submittedVersion)
- Funders
- National Institute for Health and Care Research (NF-SI-0514-10114)
- Medical Research Council (MR/K025643/1, MC_UU_12013, MC_UU_12013/1‐9, MCUU12013/1)
- Topics
- Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews
- Social Sciences › General Social Sciences › Computational and Text Analysis Methods
- Social Sciences › Library and Information Sciences › scientometrics and bibliometrics research
- Keywords
- risk of bias assessment, systematic reviews, text mining, sequence generation, allocation concealment, blinding, logistic regression
- MeSH terms
- Machine Learning, Humans, Review Literature as Topic, ROC Curve, Bias, Logistic Models, Data Mining, Datasets as Topic
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.