Grading the quality of medical evidence

  • Authors:

  • Binod Gyawali;Thamar Solorio;Yassine Benajiba

  • Affiliations:

  • University of Alabama at Birmingham, AL;University of Alabama at Birmingham, AL;Philips Research North America, Briarcliff Manor, NY

  • Venue:
  • BioNLP '12 Proceedings of the 2012 Workshop on Biomedical Natural Language Processing
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Evidence Based Medicine (EBM) is the practice of using the knowledge gained from the best medical evidence to make decisions in the effective care of patients. This medical evidence is extracted from medical documents such as research papers. The increasing number of available medical documents has imposed a challenge to identify the appropriate evidence and to access the quality of the evidence. In this paper, we present an approach for the automatic grading of evidence using the dataset provided by the 2011 Australian Language Technology Association (ALTA) shared task competition. With the feature sets extracted from publication types, Medical Subject Headings (MeSH), title, and body of the abstracts, we obtain a 73.77% grading accuracy with a stacking based approach, a considerable improvement over previous work.