Towards precise PICO extraction from abstracts of randomized controlled trials using a section-specific learning approach.
Open accessThe DOI matches its Crossref record; 33 of the 33 references it cites were found in a registry or an index.
Abstract
Motivation: Automated extraction of population, intervention, comparison/control, and outcome (PICO) from the randomized controlled trial (RCT) abstracts is important for evidence synthesis. Previous studies have demonstrated the feasibility of applying natural language processing (NLP) for PICO extraction. However, the performance is not optimal due to the complexity of PICO information in RCT abstracts and the challenges involved in their annotation. Results: We propose a two-step NLP pipeline to extract PICO elements from RCT abstracts: (i) sentence classification using a prompt-based learning model and (ii) PICO extraction using a named entity recognition (NER) model. First, the sentences in abstracts were categorized into four sections namely background, methods, results, and conclusions. Next, the NER model was applied to extract the PICO elements from the sentences within the title and methods sections that include >96% of PICO information. We evaluated our proposed NLP pipeline on three datasets, the EBM-NLPmod dataset, a randomly selected and re-annotated dataset of 500 RCT abstracts from the EBM-NLP corpus, a dataset of 150 Coronavirus Disease 2019 (COVID-19) RCT abstracts, and a dataset of 150 Alzheimer’s disease (AD) RCT abstracts. The end-to-end evaluation reveals that our proposed approach achieved an overall micro F1 score of 0.833 on the EBM-NLPmod dataset, 0.928 on the COVID-19 dataset, and 0.899 on the AD dataset when measured at the token-level and an overall micro F1 score of 0.712 on EBM-NLPmod dataset, 0.850 on the COVID-19 dataset, and 0.805 on the AD dataset when measured at the entity-level. Availability and implementation: Our codes and datasets are publicly available at https://github.com/BIDS-Xu-Lab/section_specific_annotation_of_PICO.
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
“Prior work in this area has explored the feasibility of using natural language processing (NLP) to automate PICO extraction from biomedical abstracts with limited success [5, 27, 28].”
From Automated Mass Extraction of Over 680,000 PICOs from Clinical Study Abstracts Using Generative AI: A Proof-of-Concept Study. (2024) · cites this paper as [28]
In the citing paper
“Entities: 150 Covid RCT abstracts+ 150 Alzheimers disease (AD) RCT abstracts.”
From Data extraction methods for systematic review (semi)automation: Update of a living systematic review (2025) · cites this paper as [145]
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
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
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×
“2018), BioBERT (Lee et al. 2020), BioM-ALBERT (Alrowili and Vijay-Shanker 2021), and BioM-ELECTRA (Gu et al.”
MethodLiu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2021) · arXiv · doi:10.48550/arxiv.2107.13586 · Cited by 4,352
The well-built clinical question: A key to evidence-based decisions
(1995) · ACP Journal Club · doi:10.7326/acpjc-1995-123-3-a12 · Cited by 2,931 · cited 1×
“In1995, the PICO (P: Population, I: Intervention, C: Comparison/Control, O: Outcomes) framework (Richardson et al. 1995) was introduced to formulate a well-defined research question and facilitate the literature search for evidence-based medicine (EBM).”
BackgroundDomain-specific language model pretraining for biomedical natural language processing
Gu, Y., Tinn, R., Cheng, H., Lucas, M., Usuyama, N., Liu, X., Naumann, T., Gao, J., & Poon, H. (2022) · ACM Transactions on Computing for Healthcare · doi:10.1145/3458754 · Cited by 2,170 · cited 3×
“We also experimented with the NER models with other pre-trained models including BERT (Devlin et al. 2018), BioBERT (Lee et al. 2020), BioM-ALBERT (Alrowili and Vijay-Shanker 2021), and BioM-ELECTRA (Gu et al. 2022).”
MethodInfluentialAbani, O., Abbas, A., Abbas, F., Abbas, M., Abbasi, S., Abbass, H., Abbott, A., Abdallah, N., Abdelaziz, A., Abdelfattah, M., et al. (2021) · The Lancet · doi:10.1016/s0140-6736(21)00676-0 · Cited by 1,983 · cited 1×
“With the evidence and insights gained from well-designed clinical studies such as randomized control trials (RCTs) in PubMed (Frost et al. 2020, Abani et al. 2021, Emani et al. 2021), it is possible to explore the best treat-ment options for diseases such as Coronavirus Disease 2019 (COVID-19)…”
MethodRECOVERY Collaborative Group (2021) · White Rose Research Online (University of Leeds, The University of Sheffield, University of York) · doi:10.17863/cam.70428 · Cited by 1,067
Peng, Y., Yan, S., & Lu, Z. (2019) · Proceedings of the 18th BioNLP Workshop and Shared Task · doi:10.18653/v1/w19-5006 · Cited by 899
Evaluation of PICO as a knowledge representation for clinical questions.
Huang, X., Lin, J., & Demner‐Fushman, D. (2006) · Europe PMC (PubMed Central) · Cited by 898
PubMed 200k RCT: a Dataset for Sequential Sentence Classification in Medical AbstractsPreprint
Dernoncourt, F., & Lee, J. Y. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1710.06071 · Cited by 320
Cited by
Data 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
Advancing Chinese biomedical text mining with community challenges
Zong, H., Wu, R., Cha, J., Feng, W., Wu, E., Li, J., Shao, A., Tao, L., Li, Z., Tang, B., et al. (2024) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2024.104716 · Cited by 44
Benchmarking Large Language Models in Evidence-Based Medicine
Li, J., Deng, Y., Sun, Q., Zhu, J., Tian, Y., Li, J., & Zhu, T. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3483816 · Cited by 35
“Therefore, we adopt the version re-annotated by Hu et al. [22].”
InfluentialShakeri, A., & Farmanbar, M. (2025) · Alzheimer s & Dementia Diagnosis Assessment & Disease Monitoring · doi:10.1002/dad2.70082 · Cited by 53
Data extraction methods for systematic review (semi)automation: Update of a living systematic review
Schmidt, L., Finnerty Mutlu, A. N., Elmore, R., Olorisade, B. K., Thomas, J., & Higgins, J. P. T. (2025) · F1000Research · doi:10.12688/f1000research.51117.3 · Cited by 27
Anderson, L. N., Hoyt, C. T., Zucker, J., McNaughton, A. D., Teuton, J., Karis, K., Arokium-Christian, N. N., Warley, J. T., Stromberg, Z. R., Gyori, B. M., et al. (2025) · Frontiers in Immunology · doi:10.3389/fimmu.2025.1502484 · Cited by 31
Zhang, G., Zhou, Y., Hu, Y., Xu, H., Weng, C., & Peng, Y. (2024) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocae065 · Cited by 17
Self-citationLiu, J., Lai, H., Zhao, W., Huang, J., Xia, D., Liu, H., Luo, X., Wang, B., Pan, B., Hou, L., et al. (2025) · International Journal of Surgery · doi:10.1097/js9.0000000000002215 · Cited by 19
Self-citationReason, T., Langham, J., & Gimblett, A. (2024) · Pharmaceutical Medicine · doi:10.1007/s40290-024-00539-6 · Cited by 16
“Prior work in this area has explored the feasibility of using natural language processing (NLP) to automate PICO extraction from biomedical abstracts with limited success [5, 27, 28].”
BackgroundShi, X., Zhao, W., Chen, T., Yang, C., & Du, J. (2025) · Nature Communications · doi:10.1038/s41467-025-62783-x · Cited by 17
Lan, 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
Chen, F., Zhang, G., Fang, Y., Peng, Y., & Weng, C. (2025) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocae326 · Cited by 12
Natural Language Processing in Support of Evidence-based Medicine: A Scoping Review
Xu, Z., Ma, H., Ding, Y., Zhang, G., Weng, C., & Peng, Y. (2025) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2025.findings-acl.1103 · Cited by 11
Kartchner, D., Turner, H., Ye, C., Al-Hussaini, I., Nursal, B., Lee, A. J. B., Deng, J., Curtis, C., Cho, H., Duvaris, E. L., et al. (2025) · Bioengineering · doi:10.3390/bioengineering12050486 · Cited by 7
“When examining solely the traditional PICO elements, the TrialSieve schema resulted in similar performance as previous 2-stage NLP pipelines that use both sentence classification and named entity recognition with BERT-based models [30].”
Overview of CHIP 2023 Shared Task 5: Medical Literature PICOS Identification
Zong, H., Yin, K., Tong, Y., Ma, Z., Xu, J., & Tang, B. (2024) · Communications in computer and information science · doi:10.1007/978-981-97-1717-0_14 · Cited by 5
Okui, N., & Horie, S. (2025) · Scientific Reports · doi:10.1038/s41598-025-14680-y · Cited by 4
“As clinical vocabularies fail to align with the language patients use organically, the risk of miscommunication increases 43,44 .”
Diagnosing Structural Failures in LLM-Based Evidence Extraction for Meta-AnalysisPreprint
Tan, Z., & D’Souza, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.10881 · Cited by 5
“Most prior work addresses localized extraction problems, targeting individual elements or simple relations such as populations, interventions, outcomes, or trial characteristics using rule-based, classical machine learning, and neural methods [35, 36, 37, 38].”
Grouin, C., & Grabar, N. (2024) · Yearbook of Medical Informatics · doi:10.1055/s-0044-1800751 · Cited by 5
“…the scientific literature, it is ex - ploited in the context of randomized controlled trials (RCTs) and systematic reviews: extraction of evidence for the RCTs [87], detection of the outcome issues [88-90], automatic assistance for systematic reviews [91,90], detection of high-quality papers [92].”
Task-Specific Model Allocation Medical Papers PICOS Information Extraction
Zhang, Q., Qu, J., Zhao, Q., & Xue, F. (2024) · Communications in computer and information science · doi:10.1007/978-981-97-1717-0_15 · Cited by 4
Makrinsky, K. I., Shendrikov, V. P., Makhonko, A., Merkushkin, D., & Batishchev, O. V. (2025) · Machine Learning and Knowledge Extraction · doi:10.3390/make7040152 · Cited by 2
“The distribution of crucial details across multiple paragraphs, supplementary materials, and figure legends is a well-documented obstacle in automated information extraction and a known contributor to the “reproducibility crisis” in science [29].”
Kaur, R., & Singh, S. (2026) · IISE Transactions on Healthcare Systems Engineering · doi:10.1080/24725579.2026.2619123 · Cited by 1
Reproducibility in Named Entity Recognition: A Case Study Analysis
Villarmin, C. C., Cohen‐Boulakia, S., & Naderi, N. (2024) · IEEE International Conference on eScience · doi:10.1109/e-science62913.2024.10678721 · Cited by 3
“For example, in NER, metrics can be computed using two different approaches, as it has been previously discussed and reported in [13], [25].”
InfluentialDiagnosing the limits of large language models for structured scientific evidence extraction
Tan, Z., D’Souza, J., & Auer, S. (2026) · International Journal on Digital Libraries · doi:10.1007/s00799-026-00449-9
Model-Driven Hybrid AI Framework for End-to-End Autonomous Decision-Making in Drug DevelopmentPreprint
Lee, H., Kang, H., Jung, W., Cho, H., Goo, S., Yun, H.-Y., Kim, M., Chae, J., Park, S.-M., Lee, S., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.02.03.703154
“Extraction performance is evaluated on EBM-NLP [15] and TB-PICO, reporting F1 aggregated over PICO elements and comparing against representative fine-tuned baselines [16, 17, 18].”
Better Together: Hybridizing Encoders and LLMs for Unseen Biomedical Texts
Pyeon, G., Kang, H., Heo, I., & Jung, S. (2026) · IEEE International Conference on Big Data and Smart Computing (BigComp) · doi:10.1109/bigcomp68355.2026.00021
What can artificial intelligence do for randomized controlled trials?: A scoping review
Wang, L. (., Luo, X., Zhang, J., Wu, M., Wang, X., Zhao, J., Estill, J. A. M., & Shao, R. (2026) · AI Evidence-Based Medicine · doi:10.17605/osf.io/cgwjb
LLM-UMLS-PICO: A Large Language Model-Based PICO Extraction Method with UMLS Semantic Validation
Qiao, C., Zhang, M., Huang, H., Yin, Y., & Xiao, W. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31666-0_34
Metadata
- Authors
- Hu, Y., Keloth, V. K., Raja, K., Chen, Y., & Xu, H.
- Affiliations
- The University of Texas Health Science Center at Houston (US)
- Yale University (US)
- University of Pennsylvania Health System (US)
- Corresponding author
- Xu, Hua
- Venue
- Bioinformatics
- Publisher
- Oxford University Press (OUP)
- Published
- 2023-09-01
- Volume
- 39
- Issue
- 9
- ISSN
- 1367-4803 (ISSN-L)
- 1367-4811
- PMC
- PMC10500081
- OpenAlex
- W4386462961
- Cited by
- 21
- References
- 21
- Citations by year
- 2026: 5 · 2025: 8 · 2024: 8
- FWCI
- 1.87
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Bioinformatics (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Funders
- National Library of Medicine (R01LM013519)
- Topics
- Health Sciences › Medicine › Health Informatics › Biomedical Text Mining and Ontologies
- Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- randomized controlled trials, abstracts, named entity recognition, prompt learning, sentence classification, evidence synthesis
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.
