Indexing and retrieval of medical resources for a telemedical platform

Authors:
Bartosz Kukawka;Szymon Wilk
Affiliations:
Poznań University of Technology, Poznań, Poland;Poznań University of Technology, Poznań, Poland
Venue:
ITIB'12 Proceedings of the Third international conference on Information Technologies in Biomedicine
Year:
2012

Citing 7
Cited 0

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
The TREC-9 filtering track

ACM SIGIR Forum
Accurately and reliably extracting data from the Web: a machine learning approach

Intelligent exploration of the web
BiRD: A Strategy to Autonomously Supplement Clinical Practice Guidelines with Related Clinical Studies

HICSS '05 Proceedings of the Proceedings of the 38th Annual Hawaii International Conference on System Sciences (HICSS'05) - Track 6 - Volume 06
User performance versus precision measures for simple search tasks

SIGIR '06 Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval
Evaluation of query expansion using MeSH in PubMed

Information Retrieval
Automatic indexing and retrieval of encounter-specific evidence for point-of-care support

Journal of Biomedical Informatics

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we present an indexing and retrieval service for a telemedical platform. While the service has been deployed in the Wielkopolska Center of Telemedicine (WCT) --- a platform to facilitate teleconsultations and education in the field of traumatology, it is general enough to be used in other settings. The service is composed of loosely coupled modules and implemented with open source frameworks and systems (e.g., Heritrix, MetaMap and Lucence). It automatically extracts medical resources from selected web-based repositories, indexes them using MeSH terms and finally retrieves resources relevant in the current context (e.g., the currently consulted case) without a need to formulate a query by the user. We also report results of a computational experiment conducted to help make specific implementation decisions for selected modules of the described service.