PICO Element Detection in Medical Text via Long Short-Term Memory Neural Networks.
Open accessThe DOI matches its Crossref record; 25 of the 26 references it cites were found in a registry or an index.
Abstract
Successful evidence-based medicine (EBM) applications rely on answering clinical questions by analyzing large medical literature databases.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: Participants/Problem (P), Intervention (I), Comparison (C) and Outcome (O).In this work, we present a Long Short-Term Memory (LSTM) neural network based model to automatically detect PICO elements.By jointly classifying subsequent sentences in the given text, we achieve state-of-the-art results on PICO element classification compared to several strong baseline models.We also make our curated data public as a benchmarking dataset so that the community can benefit from it.
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
“Yes, http://evidence-inference.ebm-nlp.com/ download/ Triplets for relation extraction”
From Data extraction methods for systematic review (semi)automation: Update of a living systematic review (2025) · cites this paper as [96]
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
“Abstracts that are pre-structured according to the PICO frame or combined demonstration with PICO phrases enable faster judgement of study relevance for each PICO element [4].”
From PICO entity extraction for preclinical animal literature. (2022) · cites this paper as [4]
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
“Publications in the neural and deep-learning domain described approaches such as early stopping, dropout, L2-regularisation, or weight decay. 59 , 96 , 106”
From Data extraction methods for systematic review (semi)automation: a living systematic review (2021) · cites this paper as [96]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“24,668 abstracts”
From Data extraction methods for systematic review (semi)automation: Update of a living systematic review (2025) · cites this paper as [96]
The cited source says what the claim attributes to it.
In the citing paper
“Publications in the neural and deep-learning domain described approaches such as early stopping, dropout, L2-regularisation, or weight decay. 59,96,106”
From Data extraction methods for systematic review (semi)automation: Update of a living systematic review (2025) · cites this paper as [96]
4 more claims about this paper
Create a free account to see every claim other papers make about this one.
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
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“The model is trained using the Adam optimization method (Kingma and Ba, 2014).”
MethodGlove: Global Vectors for Word Representation
Pennington, J., Socher, R., & Manning, C. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1162 · Cited by 34,071 · cited 1×
“The word embeddings W word can be pre-trained on large unlabeled datasets using unsupervised algorithms such as word2vec (Mikolov et al., 2013), GloVe (Pennington et al., 2014) and fasttext (Bojanowski et al., 2016).”
MethodDistributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533 · cited 1×
“The word embeddings W word can be pre-trained on large unlabeled datasets using unsupervised algorithms such as word2vec (Mikolov et al., 2013), GloVe (Pennington et al., 2014) and fasttext (Bojanowski et al., 2016).”
MethodEvidence 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 · cited 1×
“Such evidence, integrated with the physician’s own expertise and patient-specific factors, can lead to better patient outcomes and higher quality health care (Sackett et al., 1996).”
BackgroundEnriching Word Vectors with Subword Information
Bojanowski, P., Grave, E., Joulin, A., & Mikolov, T. (2017) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00051 · Cited by 9,645 · cited 1×
“The word embeddings W word can be pre-trained on large unlabeled datasets using unsupervised algorithms such as word2vec (Mikolov et al., 2013), GloVe (Pennington et al., 2014) and fasttext (Bojanowski et al., 2016).”
MethodEvidence-Based Medicine: How to Practice and Teach EBM
Sackett, D. L. (2000) · Cited by 5,950
Forney, G. D. (1973) · Proceedings of the IEEE · doi:10.1109/proc.1973.9030 · Cited by 5,647
Hierarchical Attention Networks for Document Classification
Yang, Z., Yang, D., Dyer, C., He, X., Smola, A., & Hovy, E. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/n16-1174 · Cited by 4,712 · cited 2×
“To form the final representation vector s of this sentence, attentive pooling is used, which can be described using the following equations (Yang et al., 2016):”
MethodUtilization of the PICO framework to improve searching PubMed for clinical questions
Schardt, C., Adams, M. B., Owens, T., Keitz, S., & Fontelo, P. (2007) · BMC Medical Informatics and Decision Making · doi:10.1186/1472-6947-7-16 · Cited by 3,053
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×
“And most often, a PICO framework is used to formulate a well-defined, focused clinical question, which decomposes the question into four parts: Participants/Problem (P), Intervention (I), Comparison (C) and Outcome (O) (Richardson et al., 1995).”
MethodDistributional Semantics Resources for Biomedical Text Processing
Pyysalo, S., Ginter, F., Moen, H., Salakoski, T., & Ananiadou, S. (2013) · Research Explorer (The University of Manchester) · Cited by 548
Evidence Based Medicine—How to Practice and Teach EBM
Jones, K. (1996) · BMJ · doi:10.1136/bmj.313.7069.1410 · Cited by 525
Answering Clinical Questions with Knowledge-Based and Statistical Techniques
Demner-Fushman, D., & Lin, J. (2007) · Computational Linguistics · doi:10.1162/coli.2007.33.1.63 · Cited by 296 · cited 4×
“These limitations were resolved by working directly on the labels of interest for EBM, allowing multilabel classification instead of binary and allowing sentences that are unrelated to labels of interest to be labeled as an ”Other” category (Kim et al., 2011; Demner-Fushman and Lin, 2007).”
BackgroundMethodInfluentialAutomatic 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 · cited 5×
“In all previous works, the only dataset used for training and test and made public is from (Kim et al., 2011).”
BackgroundMethodInfluentialCombining classifiers for robust PICO element detection.
Boudin, F., Nie, J.-Y., Bartlett, J. C., Grad, R., Pluye, P., & Dawes, M. (2010) · BMC Medical Informatics and Decision Making · doi:10.1186/1472-6947-10-29 · Cited by 131 · cited 13×
“By incorporating the surrounding sentences, the CRF baseline performs even better than MLP system, which verifies that context information is quite useful in sequential classification problems.”
BackgroundMethodInfluentialSentence retrieval for abstracts of randomized controlled trials.
Chung, G. Y. (2009) · BMC Medical Informatics and Decision Making · doi:10.1186/1472-6947-9-10 · Cited by 83
Neural Networks for Joint Sentence Classification in Medical Paper Abstracts
Dernoncourt, F., Lee, J. Y., & Szolovits, P. (2017) · Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers · doi:10.18653/v1/e17-2110 · Cited by 68
PICO element detection in medical text without metadata: are first sentences enough?
Huang, K.-C., Chiang, I.-J., Xiao, F., Liao, C.-C., Liu, C. C.-H., & Wong, J.-M. (2013) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2013.07.009 · Cited by 52 · cited 5×
“Many well-known machine learning techniques have been proposed to build stronger models for this task, including Nave Bayes (NB) (Huang et al., 2013; Boudin et al., 2010a; Demner-Fushman and Lin, 2007), Random Forest (RF) (Boudin et al., 2010a), Support Vector Machine (SVM) (Boudin et al., 2010a;…”
MethodInfluentialClinical Information Retrieval using Document and PICO Structure
Boudin, F., Nie, J., & Dawes, M. G. (2010) · North American Chapter of the Association for Computational Linguistics · Cited by 48
Dawes, M., Pluye, P., Shea, L., Grad, R., Greenberg, A., & Nie, J.-Y. (2007) · Journal of Innovation in Health Informatics · doi:10.14236/jhi.v15i1.640 · Cited by 47 · cited 1×
“To generate the datasets for both training and test, earlier works mainly relied on manual annotation, which resulted in small corpora on the order of hundreds of abstracts (Demner-Fushman and Lin, 2007; Dawes et al., 2007; Chung, 2009; Kim et al., 2011).”
MethodHansen, M. J., Rasmussen, N. Ø., & Chung, G. (2008) · Journal of Telemedicine and Telecare · doi:10.1258/jtt.2008.007007 · Cited by 38 · cited 1×
“…Boudin et al., 2010a; Demner-Fushman and Lin, 2007), Random Forest (RF) (Boudin et al., 2010a), Support Vector Machine (SVM) (Boudin et al., 2010a; Hansen et al., 2008), Conditional Random Field (CRF) (Kim et al., 2011; Chung, 2009; Chung and Coiera, 2007) and Multi-Layer Perceptron (MLP) (Boudin…”
BackgroundClassification of PICO elements by text features systematically extracted from PubMed abstracts.
Huang, K.-C., Liu, C. C.-H., Yang, S.-S., Xiao, F., Wong, J.-M., Liao, C.-C., & Chiang, I.-J. (2011) · 2011 IEEE International Conference on Granular Computing · doi:10.1109/grc.2011.6122608 · Cited by 26 · cited 7×
“, 2011; Chung, 2009; Chung and Coiera, 2007) and Multi-Layer Perceptron (MLP) (Boudin et al., 2010a; Huang et al., 2011).”
BackgroundMethodInfluentialA study of structured clinical abstracts and the semantic classification of sentences
Chung, G. Y., & Coiera, E. (2007) · Proceedings of the Workshop on BioNLP 2007 Biological, Translational, and Clinical Language Processing - BioNLP '07 · doi:10.3115/1572392.1572415 · Cited by 22 · cited 8×
“On the other hand, the third baseline is a CRF model that also uses n-grams as features (only the first 100 tokens were used for each sentence since most sentences are shorter than 100 tokens) and outputs the most probable label sequence for the whole abstract.”
InfluentialImproving Medical Information Retrieval with PICO Element Detection.
Boudin, F., Shi, L., & Nie, J.-Y. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-12275-0_8 · Cited by 21 · cited 13×
“Many well-known machine learning techniques have been proposed to build stronger models for this task, including Nave Bayes (NB) (Huang et al., 2013; Boudin et al., 2010a; Demner-Fushman and Lin, 2007), Random Forest (RF) (Boudin et al., 2010a), Support Vector Machine (SVM) (Boudin et al., 2010a;…”
BackgroundMethodInfluentialAnswering PICO Clinical Questions: A Semantic Graph-Based Approach
Znaidi, E., Tamine, L., & Latiri, C. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-19551-3_30 · Cited by 7 · cited 1×
“In many previous user studies, the generalized use of the PICO framework or similar schema by clinicians has been validated for its performance improvement on searching literature for clinical questions (Schardt et al., 2007; Boudin et al., 2010c; Znaidi et al., 2015).”
Method
Research works printed but not linked: 1
- Martin Dawes, Pierre Pluye, Laura Shea, Roland Grad, Arlene Greenberg, and Jian-Yun Nie. 2007. The identification of clinically important elements within medical journal abstracts:
Cited by
Transformers and large language models in healthcare: A review
Nerella, S., Bandyopadhyay, S., Zhang, J., Contreras, M., Siegel, S., Bumin, A., Silva, B., Sena, J., Shickel, B., Bihorac, A., et al. (2024) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2024.102900 · Cited by 197
“The PICO element dataset [142] was combined with SQuAD datasets [108, 109] to increase the generalizability and flexibility of the”
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
MSˆ2: Multi-Document Summarization of Medical Studies
DeYoung, J., Beltagy, I., van Zuylen, M., Kuehl, B., & Wang, L. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.594 · Cited by 83
“Jin and Szolovits (2018) provides a large-scale dataset of sentence-level PICO labels that are automatically derived using the structured abstract headers in PubMed abstracts.”
BackgroundAfzal, M., Alam, F., Malik, K. M., & Malik, G. M. (2020) · Journal of Medical Internet Research · doi:10.2196/19810 · Cited by 65
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
“Instead of classifying each sentence independently, the structured form of abstracts can be exploited by identifying PICO sentences simultaneously with rhetorical types (aim, method, results, and conclusions) in the abstract [57–60].”
Metadata
- Authors
- Jin, D., & Szolovits, P.
- Affiliations
- Massachusetts Institute of Technology (US)
- ORCID
- Jin, Di
- Venue
- Proceedings of the BioNLP 2018 workshop
- Published
- 2018
- Pages
- 67-75
- OpenAlex
- W2885925344
- Cited by
- 61
- References
- 26
- Citations by year
- 2026: 1 · 2025: 2 · 2024: 11 · 2023: 14 · 2022: 8 · 2021: 6 · 2020: 12 · 2019: 7
- FWCI
- 26.33
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Workshop on Biomedical Language Processing (BioNLP) (publishedVersion, cc-by)
- Funders
- National Human Genome Research Institute (U54HG007963)
- 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
- PICO framework, clinical question formulation, evidence-based medicine, clinical text classification, long short-term memory networks, sentence-level classification, benchmark dataset
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.