Accession Number:

AD1004863

Title:

WaterlooClarke: TREC 2015 Clinical Decision Support Track

Descriptive Note:

Conference Paper

Corporate Author:

University of Waterloo Waterloo, ON Canada

Personal Author(s):

• Ghenai,Amira
• Khalilov,Eldar
• Valov,Pavel
• Clarke,Charles L.

Report Date:

2015-11-20

Pagination or Media Count:

6.0

Abstract:

Clinical decision support systems help physicians with finding additional information about a particular medical case. In this paper, we develop a clinical decision support system that, based on a short medical case description, can recommend research articles to answer some common medical questions diagnosis, test and treatment articles. The two different full-text search engines we adopted in order to search over the collection of articles are Terrier and Apache Solr. We test each search engine with different settings and retrieval algorithms. Additionally, we combine the results of the two different search engines using reciprocal rank fusion. The evaluation of the submitted runs using partially marked results of Text Retrieval Conference TREC from the previous year shows that the methodologies are promising.

Descriptors:

• decision support systems
• medical services
• information retrieval
• algorithms
• clinical medicine
• indexing

Subject Categories:

Distribution Statement:

APPROVED FOR PUBLIC RELEASE