Automatic identification of comparative effectiveness research from medline citations to support clinicians' treatment information needs

Mingyuan Zhang, Guilherme Del Fiol, Randall W. Grout, Siddhartha Jonnalagadda, Richard Medlin, Rashmi Mishra, Charlene Weir, Hongfang D Liu, Javed Mostafa, Marcelo Fiszman

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Online knowledge resources such as Medline can address most clinicians' patient care information needs. Yet, significant barriers, notably lack of time, limit the use of these sources at the point of care. The most common information needs raised by clinicians are treatment-related. Comparative effectiveness studies allow clinicians to consider multiple treatment alternatives for a particular problem. Still, solutions are needed to enable efficient and effective consumption of comparative effectiveness research at the point of care. Objective: Design and assess an algorithm for automatically identifying comparative effectiveness studies and extracting the interventions investigated in these studies. Methods: The algorithm combines semantic natural language processing, Medline citation metadata, and machine learning techniques. We assessed the algorithm in a case study of treatment alternatives for depression. Results: Both precision and recall for identifying comparative studies was 0.83. A total of 86% of the interventions extracted perfectly or partially matched the gold standard. Conclusion: Overall, the algorithm achieved reasonable performance. The method provides building blocks for the automatic summarization of comparative effectiveness research to inform point of care decision-making.

Original languageEnglish (US)
Title of host publicationStudies in Health Technology and Informatics
Pages846-850
Number of pages5
Volume192
Edition1-2
DOIs
StatePublished - 2013
Event14th World Congress on Medical and Health Informatics, MEDINFO 2013 - Copenhagen, Denmark
Duration: Aug 20 2013Aug 23 2013

Other

Other14th World Congress on Medical and Health Informatics, MEDINFO 2013
CountryDenmark
CityCopenhagen
Period8/20/138/23/13

Fingerprint

Comparative Effectiveness Research
Point-of-Care Systems
Natural Language Processing
Therapeutics
Metadata
Semantics
Learning systems
Decision Making
Patient Care
Decision making
Depression
Processing

Keywords

  • Comparative effectiveness research
  • computer assisted decision making
  • information needs
  • machine learning

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Informatics
  • Health Information Management

Cite this

Zhang, M., Del Fiol, G., Grout, R. W., Jonnalagadda, S., Medlin, R., Mishra, R., ... Fiszman, M. (2013). Automatic identification of comparative effectiveness research from medline citations to support clinicians' treatment information needs. In Studies in Health Technology and Informatics (1-2 ed., Vol. 192, pp. 846-850) https://doi.org/10.3233/978-1-61499-289-9-846

Automatic identification of comparative effectiveness research from medline citations to support clinicians' treatment information needs. / Zhang, Mingyuan; Del Fiol, Guilherme; Grout, Randall W.; Jonnalagadda, Siddhartha; Medlin, Richard; Mishra, Rashmi; Weir, Charlene; Liu, Hongfang D; Mostafa, Javed; Fiszman, Marcelo.

Studies in Health Technology and Informatics. Vol. 192 1-2. ed. 2013. p. 846-850.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zhang, M, Del Fiol, G, Grout, RW, Jonnalagadda, S, Medlin, R, Mishra, R, Weir, C, Liu, HD, Mostafa, J & Fiszman, M 2013, Automatic identification of comparative effectiveness research from medline citations to support clinicians' treatment information needs. in Studies in Health Technology and Informatics. 1-2 edn, vol. 192, pp. 846-850, 14th World Congress on Medical and Health Informatics, MEDINFO 2013, Copenhagen, Denmark, 8/20/13. https://doi.org/10.3233/978-1-61499-289-9-846
Zhang M, Del Fiol G, Grout RW, Jonnalagadda S, Medlin R, Mishra R et al. Automatic identification of comparative effectiveness research from medline citations to support clinicians' treatment information needs. In Studies in Health Technology and Informatics. 1-2 ed. Vol. 192. 2013. p. 846-850 https://doi.org/10.3233/978-1-61499-289-9-846
Zhang, Mingyuan ; Del Fiol, Guilherme ; Grout, Randall W. ; Jonnalagadda, Siddhartha ; Medlin, Richard ; Mishra, Rashmi ; Weir, Charlene ; Liu, Hongfang D ; Mostafa, Javed ; Fiszman, Marcelo. / Automatic identification of comparative effectiveness research from medline citations to support clinicians' treatment information needs. Studies in Health Technology and Informatics. Vol. 192 1-2. ed. 2013. pp. 846-850
@inproceedings{a216aec59e0249d6b02ce95035200b73,
title = "Automatic identification of comparative effectiveness research from medline citations to support clinicians' treatment information needs",
abstract = "Online knowledge resources such as Medline can address most clinicians' patient care information needs. Yet, significant barriers, notably lack of time, limit the use of these sources at the point of care. The most common information needs raised by clinicians are treatment-related. Comparative effectiveness studies allow clinicians to consider multiple treatment alternatives for a particular problem. Still, solutions are needed to enable efficient and effective consumption of comparative effectiveness research at the point of care. Objective: Design and assess an algorithm for automatically identifying comparative effectiveness studies and extracting the interventions investigated in these studies. Methods: The algorithm combines semantic natural language processing, Medline citation metadata, and machine learning techniques. We assessed the algorithm in a case study of treatment alternatives for depression. Results: Both precision and recall for identifying comparative studies was 0.83. A total of 86{\%} of the interventions extracted perfectly or partially matched the gold standard. Conclusion: Overall, the algorithm achieved reasonable performance. The method provides building blocks for the automatic summarization of comparative effectiveness research to inform point of care decision-making.",
keywords = "Comparative effectiveness research, computer assisted decision making, information needs, machine learning",
author = "Mingyuan Zhang and {Del Fiol}, Guilherme and Grout, {Randall W.} and Siddhartha Jonnalagadda and Richard Medlin and Rashmi Mishra and Charlene Weir and Liu, {Hongfang D} and Javed Mostafa and Marcelo Fiszman",
year = "2013",
doi = "10.3233/978-1-61499-289-9-846",
language = "English (US)",
isbn = "9781614992882",
volume = "192",
pages = "846--850",
booktitle = "Studies in Health Technology and Informatics",
edition = "1-2",

}

TY - GEN

T1 - Automatic identification of comparative effectiveness research from medline citations to support clinicians' treatment information needs

AU - Zhang, Mingyuan

AU - Del Fiol, Guilherme

AU - Grout, Randall W.

AU - Jonnalagadda, Siddhartha

AU - Medlin, Richard

AU - Mishra, Rashmi

AU - Weir, Charlene

AU - Liu, Hongfang D

AU - Mostafa, Javed

AU - Fiszman, Marcelo

PY - 2013

Y1 - 2013

N2 - Online knowledge resources such as Medline can address most clinicians' patient care information needs. Yet, significant barriers, notably lack of time, limit the use of these sources at the point of care. The most common information needs raised by clinicians are treatment-related. Comparative effectiveness studies allow clinicians to consider multiple treatment alternatives for a particular problem. Still, solutions are needed to enable efficient and effective consumption of comparative effectiveness research at the point of care. Objective: Design and assess an algorithm for automatically identifying comparative effectiveness studies and extracting the interventions investigated in these studies. Methods: The algorithm combines semantic natural language processing, Medline citation metadata, and machine learning techniques. We assessed the algorithm in a case study of treatment alternatives for depression. Results: Both precision and recall for identifying comparative studies was 0.83. A total of 86% of the interventions extracted perfectly or partially matched the gold standard. Conclusion: Overall, the algorithm achieved reasonable performance. The method provides building blocks for the automatic summarization of comparative effectiveness research to inform point of care decision-making.

AB - Online knowledge resources such as Medline can address most clinicians' patient care information needs. Yet, significant barriers, notably lack of time, limit the use of these sources at the point of care. The most common information needs raised by clinicians are treatment-related. Comparative effectiveness studies allow clinicians to consider multiple treatment alternatives for a particular problem. Still, solutions are needed to enable efficient and effective consumption of comparative effectiveness research at the point of care. Objective: Design and assess an algorithm for automatically identifying comparative effectiveness studies and extracting the interventions investigated in these studies. Methods: The algorithm combines semantic natural language processing, Medline citation metadata, and machine learning techniques. We assessed the algorithm in a case study of treatment alternatives for depression. Results: Both precision and recall for identifying comparative studies was 0.83. A total of 86% of the interventions extracted perfectly or partially matched the gold standard. Conclusion: Overall, the algorithm achieved reasonable performance. The method provides building blocks for the automatic summarization of comparative effectiveness research to inform point of care decision-making.

KW - Comparative effectiveness research

KW - computer assisted decision making

KW - information needs

KW - machine learning

UR - http://www.scopus.com/inward/record.url?scp=84894356704&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84894356704&partnerID=8YFLogxK

U2 - 10.3233/978-1-61499-289-9-846

DO - 10.3233/978-1-61499-289-9-846

M3 - Conference contribution

C2 - 23920677

AN - SCOPUS:84894356704

SN - 9781614992882

VL - 192

SP - 846

EP - 850

BT - Studies in Health Technology and Informatics

ER -