research-article

Extracting PICO Elements From RCT Abstracts Using 1-2gram Analysis And Multitask Classification

Authors:

Li KeAuthors Info & Claims

ICMHI '19: Proceedings of the 3rd International Conference on Medical and Health Informatics

Pages 194 - 199

https://doi.org/10.1145/3340037.3340043

Published: 17 May 2019 Publication History

Abstract

The core of evidence-based medicine is to read and analyze numerous papers in the medical literature on a specific clinical problem and summarize the authoritative answers to that problem. Currently, to formulate a clear and focused clinical problem, the popular PICO framework is usually adopted, in which each clinical problem is considered to consist of four parts: patient/problem (P), intervention (I), comparison (C) and outcome (O). In this study, we compared several classification models that are commonly used in traditional machine learning. Next, we developed a multitask classification model based on a soft-margin SVM with a specialized feature engineering method that combines 1-2gram analysis with TF-IDF analysis. Finally, we trained and tested several generic models on an open-source data set from BioNLP 2018. The results show that the proposed multitask SVM classification model based on 1-2gram TF-IDF features exhibits the best performance among the tested models.

References

[1]

David L. Sackett, W. Scott Richardson, William Rosenberg R. Brian Haynes Churchill Livingstone." Evidence-based Medicine How to practice and teach EBM". WB Saunders Company.1997.

[2]

Sackett DL, Rosenberg WMC, Gray JAM, Haynes RB, Richardson WS." Evidence based medicine: what it is and what it isn't". Br Med J 1996;312(7023):71--2.

[3]

Lin J, Demner-Fushman D." The role of knowledge in conceptual retrieval". In: Proceedings of the 29th annual international ACM SIGIR conference on research and development in information retrieval -- SIGIR '06. Seattle, Washington, USA; 2006, p. 99--106.

Digital Library

[4]

W Scott Richardson, Mark C Wilson, Jim Nishikawa, and Robert SA Hayward." The well-built clinical question: a key to evidence-based decisions". ACP journal club, 123(3):A12--A12. 1995.

[5]

Abigail M Methley, Stephen Campbell, Carolyn Chew-Graham." PICO, PICOS and SPIDER: a comparison study of specificity and sensitivity in three search tools for qualitative systematic reviews". BMC Health Services Research (2014) 14:579.

[6]

John Rathbone, Loai Albarqouni, Mina Bakhit." Expediting citation screening using PICobased title-only screening for identifying studies in scoping searches and rapid reviews". Systematic Reviews (2017) 6:233.

[7]

L. M. Md, P. Srinivasan, and P. D." Categorization of Sentence Types in Medical Abstracts". In Proceeding of the 2003 Annual Symposium of the American Medical Informatics Association (AMIA), p. 440--444, 2003.

[8]

Boser, BE, Guyon, IM, Vapnik, VN." A training algorithm for optimal margin classifiers". In: Proceedings of the Annual Workshop on Computational Learning Theory. ACM 2010. 144--152.

Digital Library

[9]

Caruana, R." Multitask learning". Springer US, 1998, p 65--78.

[10]

Connie Schardt, Martha B Adams, Thomas Owens,Sheri Keitz, and Paul Fontelo." Utilization of the pico framework to improve searching for clinical questions". BMC medical informatics and decision making, 7(1):16. 2007.

[11]

Florian Boudin, Jian-Yun Nie, Joan C Bartlett, Roland Grad, Pierre Pluye, and Martin Dawes." Combining classifiers for robust pico element detection". BMC medical informatics and decision making, 10(1):29. 2010.

[12]

Huang X, Lin J, Demner-Fushman D." Evaluation of PICO as a knowledge representation for clinical questions". AMIA Annu Symp Proc 2006; 2006:359--63.

[13]

Demner-Fushman D, Lin J." Knowledge extraction for clinical question answering: preliminary results". Assoc Adv Artif Intell 2005:1--9.

[14]

Grace Yuet-Chee Chung." Towards identifying intervention arms in randomized controlled trials: Extracting coordinating constructions". Journal of Biomedical Informatics 42 (2009) 790--800.

Digital Library

[15]

Grace Y Chung." Sentence retrieval for abstracts of randomized controlled trials". BMC medical informatics and decision making, 9(1):10. 2009.

[16]

Di Jin, Peter Szolovits." PICO Element Detection in Medical Text via Long Short-Term Memory Neural Networks". Proceedings of the BioNLP 2018 workshop. 2018.

[17]

Ke-Chun Huang, I-Jen Chiang, Furen Xiao, Chun-Chih Liao, Charles Chih-Ho Liu, and Jau-Min Wong. "Pico element detection in medical text without metadata: Are first sentences enough?". Journal of biomedical informatics, 46(2013):940--946. 2013.

Digital Library

[18]

Haibo He, and Edwardo A. Garcia." Learning from Imbalanced Data". 2009. in IEEE Transactions on Knowledge & Data Engineering, vol. 21, no., pp. 1263--1284, 2008.

Digital Library

[19]

Oded Maimon · Lior Rokach." Data Mining and Knowledge Discovery Handbook". Springer New York Dordrecht Heidelberg London,2010.

Digital Library

[20]

Ke-Chun Huang1, Charles Chih-Ho Liu1,Shung-Shiang Yang." Classification of PICO Elements by Text Features Systematically Extracted from Abstracts". IEEE International Conference on Granular Computing,2011.

[21]

Varantola K." Special Language and General Language". ALSED2LSP Newsletter,1986,9 (2): 10220

[22]

Rosita B. Maglie." Understanding the Language of Medicine". Springer Aracne; 2009. p.12--25.

[23]

Franck Dernoncourt, Ji Young Lee." 200k RCT: a Dataset for Sequential Sentence Classification in Medical Abstracts". IJCNLP 2017.

Cited By

Witte CSchmidt DCimiano P(2024)Comparing generative and extractive approaches to information extraction from abstracts describing randomized clinical trialsJournal of Biomedical Semantics10.1186/s13326-024-00305-215:1Online publication date: 23-Apr-2024
https://doi.org/10.1186/s13326-024-00305-2
Schmidt LFinnerty Mutlu AElmore ROlorisade BThomas JHiggins J(2023)Data extraction methods for systematic review (semi)automation: Update of a living systematic reviewF1000Research10.12688/f1000research.51117.210(401)Online publication date: 9-Oct-2023
https://doi.org/10.12688/f1000research.51117.2
Yang FXu XWu MWang XShen LQian QLi J(2023)Identifying key elements for evidence-base medicine using pretrained model and graph convolution networkProcedia Computer Science10.1016/j.procs.2023.08.022221:C(557-564)Online publication date: 1-Jan-2023
https://dl.acm.org/doi/10.1016/j.procs.2023.08.022
Show More Cited By

Index Terms

Extracting PICO Elements From RCT Abstracts Using 1-2gram Analysis And Multitask Classification
1. Computing methodologies
  1. Artificial intelligence
    1. Natural language processing
      1. Information extraction

Recommendations

PICO element detection in medical text without metadata

Graphical AbstractDisplay Omitted Two sets of naive Bayes classifiers were developed for PICO detection.We trained one set with first sentences and the other with all sentences.The first-sentence classifier performs slightly better for patient (P) ...
Extracting Clinical Trial Design Information from MEDLINE Abstracts
Abstract
Evidence-based medicine (EBM) requires medical practitioners to select appropriate treatments for individual patients based on the current best evidence, and the results of phase III clinical trials are the major source of such evidence. In this ...
Electronic health record phenotyping improves detection and screening of type 2 diabetes in the general United States population

Display Omitted We extracted features from electronic health records (EHR) to predict diagnosed type 2 diabetes.We predicted a patient's diabetes diagnosis using 9948 clinical-quality electronic health records.EHR phenotyping out-performed conventional ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

ICMHI '19: Proceedings of the 3rd International Conference on Medical and Health Informatics

May 2019

207 pages

ISBN:9781450371995

DOI:10.1145/3340037

Copyright © 2019 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

In-Cooperation

University of Electronic Science and Technology of China: University of Electronic Science and Technology of China

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 17 May 2019

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

ICMHI 2019

ICMHI 2019: The third International Conference on Medical and Health Informatics 2019

May 17 - 19, 2019

Xiamen, China

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

7
Total Citations
View Citations
169
Total Downloads

Downloads (Last 12 months)26
Downloads (Last 6 weeks)3

Reflects downloads up to 02 Sep 2024

Other Metrics

View Author Metrics

Citations

Cited By

Witte CSchmidt DCimiano P(2024)Comparing generative and extractive approaches to information extraction from abstracts describing randomized clinical trialsJournal of Biomedical Semantics10.1186/s13326-024-00305-215:1Online publication date: 23-Apr-2024
https://doi.org/10.1186/s13326-024-00305-2
Schmidt LFinnerty Mutlu AElmore ROlorisade BThomas JHiggins J(2023)Data extraction methods for systematic review (semi)automation: Update of a living systematic reviewF1000Research10.12688/f1000research.51117.210(401)Online publication date: 9-Oct-2023
https://doi.org/10.12688/f1000research.51117.2
Yang FXu XWu MWang XShen LQian QLi J(2023)Identifying key elements for evidence-base medicine using pretrained model and graph convolution networkProcedia Computer Science10.1016/j.procs.2023.08.022221:C(557-564)Online publication date: 1-Jan-2023
https://dl.acm.org/doi/10.1016/j.procs.2023.08.022
Santos Áda Silva ECouto LReis GBelo V(2023)The use of artificial intelligence for automating or semi-automating biomedical literature analyses: A scoping reviewJournal of Biomedical Informatics10.1016/j.jbi.2023.104389142(104389)Online publication date: Jun-2023
https://doi.org/10.1016/j.jbi.2023.104389
Schmidt LOlorisade BMcGuinness LThomas JHiggins J(2021)Data extraction methods for systematic review (semi)automation: A living systematic reviewF1000Research10.12688/f1000research.51117.110(401)Online publication date: 19-May-2021
https://doi.org/10.12688/f1000research.51117.1
Yang YCao ZZhao PZeng DZhang QLuo Y(2021)Extracting Impacts of Non-pharmacological Interventions for COVID-19 From Modelling Study2021 IEEE International Conference on Intelligence and Security Informatics (ISI)10.1109/ISI53945.2021.9624840(1-6)Online publication date: 2-Nov-2021
https://dl.acm.org/doi/10.1109/ISI53945.2021.9624840
Gonçalves SCortez PMoro S(2019)A deep learning classifier for sentence classification in biomedical and computer science abstractsNeural Computing and Applications10.1007/s00521-019-04334-232:11(6793-6807)Online publication date: 10-Jul-2019
https://dl.acm.org/doi/10.1007/s00521-019-04334-2

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents