Advancing PICO element detection in biomedical text via deep neural networks.
Open accessThe DOI matches its Crossref record; the references it cites are not checked yet.
Abstract
Motivation: In evidence-based medicine, defining a clinical question in terms of the specific patient problem aids the physicians to efficiently identify appropriate resources and search for the best available evidence for medical treatment. In order to formulate a well-defined, focused clinical question, a framework called PICO is widely used, which identifies the sentences in a given medical text that belong to the four components typically reported in clinical trials: Participants/Problem (P), Intervention (I), Comparison (C) and Outcome (O). In this work, we propose a novel deep learning model for recognizing PICO elements in biomedical abstracts. Based on the previous state-of-the-art bidirectional long-short-term memory (bi-LSTM) plus conditional random field architecture, we add another layer of bi-LSTM upon the sentence representation vectors so that the contextual information from surrounding sentences can be gathered to help infer the interpretation of the current one. In addition, we propose two methods to further generalize and improve the model: adversarial training and unsupervised pre-training over large corpora. Results: We tested our proposed approach over two benchmark datasets. One is the PubMed-PICO dataset, where our best results outperform the previous best by 5.5%, 7.9% and 5.8% for P, I and O elements in terms of F1 score, respectively. And for the other dataset named NICTA-PIBOSO, the improvements for P/I/O elements are 3.9%, 15.6% and 1.3% in F1 score, respectively. Overall, our proposed deep learning model can obtain unprecedented PICO element detection accuracy while avoiding the need for any manual feature selection. Availability and implementation: Code is available at https://github.com/jind11/Deep-PICO-Detection.
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
“described that the same problem needs to be addressed through stratification of the positive instances of each class within folds.”
From Data extraction methods for systematic review (semi)automation: a living systematic review (2021) · cites this paper as [54]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In terms of system evaluation, 10-fold cross-validation causes high variance in results when using small datasets such as NICTA-PIBOSO, 54 , 85 , 104”
From Data extraction methods for systematic review (semi)automation: a living systematic review (2021) · cites this paper as [54]
Experimental — accuracy not yet measuredIn the citing paper
“39,54,87,95,98,136”
From Data extraction methods for systematic review (semi)automation: Update of a living systematic review (2025) · cites this paper as [54]
In the citing paper
“Examples of this are sentences that could belong to multiple categories, e.g., those that should have both ' P ' and an ' I ' label, or sentences that were assigned to the class ' other ' while containing PICO information”
From Data extraction methods for systematic review (semi)automation: Update of a living systematic review (2025) · cites this paper as [54]
In the citing paper
“Corpora such as the ebm-nlp dataset, 55 or PubMed-PICO 54 are available for direct download.”
From Data extraction methods for systematic review (semi)automation: a living systematic review (2021) · cites this paper as [54]
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 15 · Cited by 41
Research works printed but not linked: 3
- Huang, 2006, AMIA Annual Symposium Proceedings, 359
- Mikolov, 2013, Distributed representations of words and phrases and their compositionality, 3111
- Vaswani, 2017, Attention is all you need, 5998
Metadata
- Authors
- Jin, D., & Szolovits, P.
- Affiliations
- Massachusetts Institute of Technology (US)
- Compter Science and Artificial Intelligence Laboratory , Massachusetts Institute of Technology, Cambridge, MA 02139, USA
- Corresponding author
- Jin, Di
- ORCID
- Jin, Di
- Venue
- Bioinformatics
- Publisher
- Oxford University Press (OUP)
- Published
- 2020-04-20
- Volume
- 36
- Issue
- 12
- Pages
- 3856-3862
- ISSN
- 1367-4803 (ISSN-L)
- 1367-4811
- OpenAlex
- W3016407396
- Cited by
- 41
- References
- 15
- Citations by year
- 2026: 5 · 2025: 10 · 2024: 5 · 2023: 8 · 2022: 6 · 2021: 5 · 2020: 1
- FWCI
- 1.62
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- academic.oup.com/journals/pages/open_access/funder_policies/chorus/standard_publication_model (vor)
- Locations
- Bioinformatics (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Health Sciences › Medicine › Health Informatics › Biomedical Text Mining and Ontologies
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Keywords
- clinical question formulation, biomedical abstracts, clinical trial reporting, BiLSTM, conditional random fields, adversarial training, unsupervised pre-training, evidence-based medicine, biomedical text mining
- MeSH terms
- Humans, Language, Neural Networks, Computer, PubMed
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: Advancing PICO element detection in biomedical text via deep neural networks. https://app.cochat.ai/papers/10.1093/bioinformatics/btaa256
- The paper
- Jin, D., & Szolovits, P. (2020). Advancing PICO element detection in biomedical text via deep neural networks. Bioinformatics. https://doi.org/10.1093/bioinformatics/btaa256
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.