Detection of evidence in clinical research papers

Patrick Davis-Desmond, Diego Mollá

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

Abstract

When appraising published clinical research, medical doctors and researchers often need to know whether the clinical outcomes presented had statistical evidence. In this paper we present a study for the detection of expressions of such statistical evidence. An effective rule-based classifier has been developed that uses regular expressions and a list of negation phrases to automatically classify documents as either showing evidence of effect in the results or not. The classifier performed with an accuracy between 88% and 98% at 95% confidence intervals, and it also outperformed a set of baselines using bag-of-word features in several statistical classifiers. The rule-based system is written in Python and is available as open-source code.
Original languageEnglish
Title of host publicationProceedings of the Fifth Australasian Workshop on Health Informatics and Knowledge Management (HIKM 2012), Melbourne, Australia, 31 January - 3 February 2012
EditorsKerryn Butler-Henderson, Kathleen Gray
Place of PublicationSydney
PublisherAustralian Computer Society
Pages13-20
Number of pages8
ISBN (Print)9781921770104
Publication statusPublished - 2012
EventAustralasian Workshop on Health Informatics and Knowledge Management (5th : 2012) - Melbourne, VIC
Duration: 30 Jan 20123 Feb 2012

Publication series

NameConferneces in research and practice in information technology
PublisherAustralian Computer Society
Volume129
ISSN (Print)1445-1336

Workshop

WorkshopAustralasian Workshop on Health Informatics and Knowledge Management (5th : 2012)
CityMelbourne, VIC
Period30/01/123/02/12

Keywords

  • evidence-based medicine
  • appraisal
  • text classification

Fingerprint Dive into the research topics of 'Detection of evidence in clinical research papers'. Together they form a unique fingerprint.

Cite this