Deriving a test collection for clinical information retrieval from systematic reviews

Authors:
Florian Boudin;Jian-Yun Nie;Martin Dawes
Affiliations:
Université de Montreal, Montreal, PQ, Canada;Université de Montreal, Montreal, PQ, Canada;McGill University, Montreal, PQ, Canada
Venue:
DTMBIO '10 Proceedings of the ACM fourth international workshop on Data and text mining in biomedical informatics
Year:
2010

Citing 7
Cited 1

OHSUMED: an interactive retrieval evaluation and new large test collection for research

SIGIR '94 Proceedings of the 17th annual international ACM SIGIR conference on Research and development in information retrieval
A Markov random field model for term dependencies

Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval
Answering Clinical Questions with Knowledge-Based and Statistical Techniques

Computational Linguistics
TREC: Continuing information retrieval's tradition of experimentation

Communications of the ACM
Introduction to Information Retrieval

Introduction to Information Retrieval
Clinical information retrieval using document and PICO structure

HLT '10 Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics
MedEval: a Swedish medical test collection with doctors and patients user groups

Louhi '10 Proceedings of the NAACL HLT 2010 Second Louhi Workshop on Text and Data Mining of Health Documents

Protocol-driven searches for medical and health-sciences systematic reviews

ICTIR'11 Proceedings of the Third international conference on Advances in information retrieval theory

Quantified Score

Hi-index	0.01

Visualization

Abstract

In this paper, we describe the construction of a test collection for evaluating clinical information retrieval. The purpose of this test collection is to provide a basis for researchers to experiment with PECO-structured queries. Systematic reviews are used as a starting point for generating queries and relevance judgments. We give some details on the difficulties encountered in building this resource and report the results achieved by current state-of-the-art approaches.