Investigating the impact of weakly supervised data on text mining models of publication transparency: a case study on randomized controlled trials
Open accessThe DOI matches its Crossref record; 52 of the 52 references it cites were found in a registry or an index.
Abstract
Lack of large quantities of annotated data is a major barrier in developing effective text mining models of biomedical literature. In this study, we explored weak supervision strategies to improve the accuracy of text classification models developed for assessing methodological transparency of randomized controlled trial (RCT) publications. Specifically, we used Snorkel, a framework to programmatically build training sets, and UMLS-EDA, a data augmentation method that leverages a small number of existing examples to generate new training instances, for weak supervision and assessed their effect on a BioBERT-based text classification model proposed for the task in previous work. Performance improvements due to weak supervision were limited and were surpassed by gains from hyperparameter tuning. Our analysis suggests that refinements to the weak supervision strategies to better deal with multi-label case could be beneficial.
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.
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
“The effect of data augmentation on PubMedBERT fine-tuning was minimal, which is consistent with our previous findings22.”
From Text classification models for assessing the completeness of randomized controlled trial publications based on CONSORT reporting guidelines (2024) · cites this paper as [22]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“CONSORT-TM is relatively small and some checklist items are infrequently reported (e.g., 6b (Changes to Outcomes)). This has led to poor performance for rare items in previous work21,22.”
From Text classification models for assessing the completeness of randomized controlled trial publications based on CONSORT reporting guidelines (2024) · cites this paper as [22]
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
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325 · cited 4×
“, the word concealment to the item Allocation Concealment (9)).”
BackgroundInfluentialEvidence based medicine: what it is and what it isn't
Sackett, D. L., Rosenberg, W. M. C., Gray, J. A. M., Haynes, R. B., & Richardson, W. S. (1996) · BMJ · doi:10.1136/bmj.312.7023.71 · Cited by 15,769
CONSORT 2010 Statement: updated guidelines for reporting parallel group randomised trials
the CONSORT Group, Schulz, K. F., Altman, D. G., & Moher, D. (2010) · BMC Medicine · doi:10.1186/1741-7015-8-18 · Cited by 13,371
CONSORT 2010 Statement: updated guidelines for reporting parallel group randomised trials
Schulz, K. F., Altman, D. G., Moher, D., & for the CONSORT Group (2010) · BMJ · doi:10.1136/bmj.c332 · Cited by 9,329
Moher, D., Hopewell, S., Schulz, K. F., Montori, V., Gotzsche, P. C., Devereaux, P. J., Elbourne, D., Egger, M., & Altman, D. G. (2010) · BMJ · doi:10.1136/bmj.c869 · Cited by 8,883
BioBERT: a pre-trained biomedical language representation model for biomedical text mining
Lee, J., Yoon, W., Kim, S., Kim, D., Kim, S., So, C. H., & Kang, J. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btz682 · Cited by 7,218 · cited 2×
“This classifier uses the BioBERT pretrained language model 8 as a sentence encoder, considering the model’s output for the [CLS] token as the sentence representation, and trains a sigmoid layer for multi-label classification of 17 CONSORT methodology items.”
MethodThe Stanford CoreNLP Natural Language Processing Toolkit
Manning, C., Surdeanu, M., Bauer, J., Finkel, J., Bethard, S., & McClosky, D. (2014) · Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations · doi:10.3115/v1/p14-5010 · Cited by 7,037
The unified medical language system (UMLS): integrating biomedical terminology
Bodenreider, O. (2004) · Nucleic Acids Research · doi:10.1093/nar/gkh061 · Cited by 4,356
Yeh, M.-L. (2014) · Journal of Nursing Research · doi:10.1097/jnr.0000000000000065 · Cited by 3,829
Distant supervision for relation extraction without labeled data
Mintz, M., Bills, S., Snow, R., & Jurafsky, D. (2009) · Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 2 - ACL-IJCNLP '09 · doi:10.3115/1690219.1690287 · Cited by 2,752 · cited 2×
“One well-known technique is distant supervision 13 , based on using domain knowledge in external knowledge bases.”
BackgroundMethodSelf-Training With Noisy Student Improves ImageNet Classification
Xie, Q., Luong, M.-T., Hovy, E., & Le, Q. V. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01070 · Cited by 2,393
Avoidable waste in the production and reporting of research evidence
Chalmers, I., & Glasziou, P. (2009) · The Lancet · doi:10.1016/s0140-6736(09)60329-9 · Cited by 2,208
EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks
Wei, J., & Zou, K. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1670 · Cited by 1,911
Gross, K. S., Brandner, D. D., Martinez, L. A., Olive, M. F., Meisel, R. L., & Mermelstein, P. G. (2016) · PLOS ONE · doi:10.1371/journal.pone.0162755 · Cited by 1,609
Snorkel: rapid training data creation with weak supervision
Ratner, A., Bach, S. H., Ehrenberg, H., Fries, J., Wu, S., & Ré, C. (2017) · Proceedings of the VLDB Endowment · doi:10.14778/3157794.3157797 · Cited by 777
O’Mara-Eves, A., Thomas, J., McNaught, J., Miwa, M., & Ananiadou, S. (2015) · Systematic Reviews · doi:10.1186/2046-4053-4-5 · Cited by 681
On the Complexity of Best Arm Identification in Multi-Armed Bandit Models
Kaufmann, E., Cappé, O., & Garivier, A. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1407.4443 · Cited by 661
Turner, L., Shamseer, L., Altman, D. G., Schulz, K. F., & Moher, D. (2012) · Systematic Reviews · doi:10.1186/2046-4053-1-60 · Cited by 628
Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations
Kobayashi, S. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers) · doi:10.18653/v1/n18-2072 · Cited by 603
Avoidable Waste in the Production and Reporting of Research Evidence
Chalmers, I., & Glasziou, P. (2009) · Obstetrics & Gynecology · doi:10.1097/aog.0b013e3181c3020d · Cited by 600 · cited 1×
“RCTs are time-consuming and expensive, and if inadequately designed, conducted, or reported, they lead to poor health outcomes and significant research waste 3 .”
BackgroundSnorkel: rapid training data creation with weak supervision
Ratner, A., Bach, S. H., Ehrenberg, H., Fries, J., Wu, S., & Ré, C. (2020) · The VLDB Journal · doi:10.1007/s00778-019-00552-1 · Cited by 510
Genetic determinants of daytime napping and effects on cardiometabolic health
Dashti, H. S., Daghlas, I., Lane, J. M., Huang, Y., Udler, M. S., Wang, H., Ollila, H. M., Jones, S. E., Kim, J., Wood, A. R., et al. (2021) · Nature Communications · doi:10.1038/s41467-020-20585-3 · Cited by 446
A clinical text classification paradigm using weak supervision and deep representation
Wang, Y., Sohn, S., Liu, S., Shen, F., Wang, L., Atkinson, E. J., Amin, S., & Liu, H. (2019) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-018-0723-6 · Cited by 405
O’Mara-Eves, A., Thomas, J., McNaught, J., Miwa, M., & Ananiadou, S. (2015) · Systematic Reviews · doi:10.1186/s13643-015-0031-5 · Cited by 353
In Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC
Grover, C., & Tobin, R. (2006) · Cited by 324
RobotReviewer: 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 · cited 3×
“For example, risk of bias judgements in the Cochrane database of systematic reviews were used to automatically label sentences in RCT publications and train models for assessing risk of bias in the publications 15 .”
BackgroundMethodAutomating 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
Distant Supervision for Relation Extraction beyond the Sentence Boundary
Quirk, C., & Poon, H. (2017) · Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers · doi:10.18653/v1/e17-1110 · Cited by 248
Nye, B., Li, J. J., Patel, R., Yang, Y., Marshall, I., Nenkova, A., & Wallace, B. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1019 · Cited by 224
Automatic classification of sentences to support Evidence Based Medicine.
Kim, S. N., Martinez, D., Cavedon, L., & Yencken, L. (2011) · BMC Bioinformatics · doi:10.1186/1471-2105-12-s2-s5 · Cited by 214
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
EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks
Wei, J., & Zou, K. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.11196 · Cited by 186
Measuring Agreement on Set-valued Items (MASI) for Semantic and Pragmatic Annotation
Passonneau, R. J. (2006) · Language Resources and Evaluation Conference (LREC) · doi:10.63317/4nuo6thi27ax · Cited by 139
(2016) · PubMed · Cited by 134
Few-shot Text Classification with Distributional Signatures
Bao, Y., Wu, M., Chang, S., & Barzilay, R. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.06039 · Cited by 115
Ontology-driven weak supervision for clinical entity classification in electronic health records
Fries, J. A., Steinberg, E., Khattar, S., Fleming, S. L., Posada, J., Callahan, A., & Shah, N. H. (2021) · Nature Communications · doi:10.1038/s41467-021-22328-4 · Cited by 95
Pandis, N., Shamseer, L., Kokich, V. G., Fleming, P. S., & Moher, D. (2014) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2014.04.001 · Cited by 92
Cohen, A. M., Smalheiser, N. R., McDonagh, M. S., Yu, C., Adams, C. E., Davis, J. M., & Yu, P. S. (2015) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocu025 · Cited by 78
Improving reference prioritisation with PICO recognition.
Brockmeier, A. J., Ju, M., Przybyła, P., & Ananiadou, S. (2019) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-019-0992-8 · Cited by 62
UMLS-based data augmentation for natural language processing of clinical research literature
Kang, T., Perotte, A., Tang, Y., Ta, C., & Weng, C. (2021) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocaa309 · Cited by 55
Contextual Augmentation: Data Augmentation by Words with Paradigmatic RelationsPreprint
Kobayashi, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.06201 · Cited by 50
Advancing PICO element detection in biomedical text via deep neural networks.
Jin, D., & Szolovits, P. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btaa256 · Cited by 41
Toward assessing clinical trial publications for reporting transparency
Kilicoglu, H., Rosemblat, G., Hoang, L., Wadhwa, S., Peng, Z., Malički, M., Schneider, J., & ter Riet, G. (2021) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2021.103717 · Cited by 34
Self-citationBio-SCoRes: A Smorgasbord Architecture for Coreference Resolution in Biomedical Text
Kilicoglu, H., & Demner‐Fushman, D. (2016) · PLoS ONE · doi:10.1371/journal.pone.0148538 · Cited by 26
Self-citationBeyond MeSH: Fine-grained semantic indexing of biomedical literature based on weak supervision
Nentidis, A., Krithara, A., Tsoumakas, G., & Παλιούρας, Γ. (2020) · Information Processing & Management · doi:10.1016/j.ipm.2020.102282 · Cited by 18
Schneider, J., Hoang, L., Kansara, Y., Cohen, A. M., & Smalheiser, N. R. (2022) · JAMIA Open · doi:10.1093/jamiaopen/ooac015 · Cited by 18
Self-citationWang, Y., Liu, F., Verspoor, K. M., & Baldwin, T. (2020) · Workshop on Biomedical Language Processing (BioNLP) · doi:10.18653/v1/2020.bionlp-1.11 · Cited by 16
Dietrich, G., Krebs, J., Liman, L., Fette, G., Ertl, M., Kaspar, M., Störk, S., & Puppe, F. (2019) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-018-0729-0 · Cited by 12
Ontology-driven weak supervision for clinical entity classification in electronic health records.Preprint
Fries, J., Steinberg, E., Khattar, S., Fleming, S. L., Posada, J., Callahan, A., & Shah, N. H. (2020) · PubMed · Cited by 12
Wang, L., Yu, X., Wang, H., Lu, Y., de Ruiter, M., Prins, M., & Yk, H. (2011) · Figshare · Cited by 10
Skreta, M., Arbabi, A., Wang, J., & Brudno, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.06174 · Cited by 8
Cited by
Methodology reporting improved over time in 176,469 randomized controlled trials
Kilicoglu, H., Jiang, L., Hoang, L., Mayo-Wilson, E., Vinkers, C. H., & Otte, W. M. (2023) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2023.08.004 · Cited by 19
Self-citationJiang, L., Lan, M., Menke, J. D., Vorland, C. J., & Kilicoglu, H. (2024) · Scientific Reports · doi:10.1038/s41598-024-72130-7 · Cited by 18
“Apart from sentences reporting Interpretation (22), false negatives involved sentences that describe how outcomes were assessed or interventions were administered, as opposed to what the outcomes and interventions were.”
BackgroundMethodResultInfluentialSelf-citationLan, M., Cheng, M., Hoang, L., ter Riet, G., & Kilicoglu, H. (2024) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2024.104628 · Cited by 15
Self-citationJiang, L., Vorland, C. J., Ying, X., Brown, A. W., Menke, J. D., Hong, G., Lan, M., Mayo‐Wilson, E., & Halil Kilicoglu, B. (2025) · medRxiv · doi:10.1101/2025.01.14.25320543
Self-citationDobrescu, A., Cohen-Boulakia, S., & Naderi, N. (2025) · ACM REP · doi:10.1145/3736731.3746133 · Cited by 1
Metadata
- Authors
- Hoang, L., Jiang, L., & Kilicoglu, H.
- Affiliations
- University of Illinois Urbana-Champaign (US)
- Corresponding author
- Hoang, Linh
- Venue
- medRxiv
- Publisher
- openRxiv
- Published
- 2021-09-22
- OpenAlex
- W3199007285
- Cited by
- 5
- References
- 52
- Citations by year
- 2025: 2 · 2024: 2 · 2023: 1
- Type
- posted content
- Language
- en
- Open access
- green
- doi.org
- Licence
- cc-by-nc
- Locations
- medRxiv (acceptedVersion, cc-by-nc)
- Topics
- Health Sciences › Medicine › Health Informatics › Biomedical Text Mining and Ontologies
- Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews
- Social Sciences › General Social Sciences › Computational and Text Analysis Methods
- Keywords
- weakly supervised learning, text classification, randomized controlled trials, methodological transparency, snorkel, data augmentation, BioBERT, multi-label classification, hyperparameter optimization, biomedical literature, annotated data scarcity
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.