TY - JOUR
T1 - Vaidurya
T2 - A multiple-ontology, concept-based, context-sensitive clinical-guideline search engine
AU - Moskovitch, Robert
AU - Shahar, Yuval
N1 - Funding Information:
This research was supported in part by NIH Award No. LM-06806. We thank S. Tu and Dr. Peleg,, for useful discussions regarding the need for supporting the use of multiple guideline ontologies. Drs. Shiffman and Karras assisted us in using their GEM ontology. Drs. Goldstein, Basso, Kaizer, Advani, and Lunenfeld, were extremely helpful in assessing the various interfaces and search. We thank all the graduate students in the Medical Informatics Lab, Especially A. Hessing and O. Young, in their contribution to the creation of Vaidurya’s interfaces. We thank A. Litmanovitz, O. Bohanna, and C. Sasson, who worked on the IR and HCI evaluation tools; S. Nave, L. Bar-on, A. Efrati and S. Hatan, and O. Perets, and Y. Schlamm, who developed the new framework of customized and template-based query interfaces; and I. Dahari, D. Pretselman, and U. Gobi, who developed the CPGs web wrappers. We thank Dr. Kumar for his contribution in the extraction rules and the assessment of the query interfaces. We also thank T. Lavie for her contribution in the HCI aspects of the query interfaces and Dr. Leibowitz for his contribution in designing and assessing several template-based query interfaces.
PY - 2009/2/1
Y1 - 2009/2/1
N2 - We designed and implemented a generic search engine (Vaidurya), as part of our Digital clinical-Guideline Library (DeGeL) framework. Two search methods were implemented in addition to full-text search: (1) concept-based search, which relies on pre-indexing the guidelines in a clinically meaningful fashion, and (2) context-sensitive search, which relies on first semi-structuring the guidelines according to a given ontology, then searching for terms within specific labeled text segments. The Vaidurya engine is fully functional and is used within the DeGeL system. We describe the Vaidurya ontological and algorithmic framework; we also briefly summarize the results of a detailed evaluation in the clinical-guideline domain, demonstrating that both concept-based and context-sensitive ontology-independent search are highly feasible and significantly improve on free text search retrieval performance. We conclude by analyzing the limitations and advantages of the approach, and the steps that we have started to take to extend it based on user feedback.
AB - We designed and implemented a generic search engine (Vaidurya), as part of our Digital clinical-Guideline Library (DeGeL) framework. Two search methods were implemented in addition to full-text search: (1) concept-based search, which relies on pre-indexing the guidelines in a clinically meaningful fashion, and (2) context-sensitive search, which relies on first semi-structuring the guidelines according to a given ontology, then searching for terms within specific labeled text segments. The Vaidurya engine is fully functional and is used within the DeGeL system. We describe the Vaidurya ontological and algorithmic framework; we also briefly summarize the results of a detailed evaluation in the clinical-guideline domain, demonstrating that both concept-based and context-sensitive ontology-independent search are highly feasible and significantly improve on free text search retrieval performance. We conclude by analyzing the limitations and advantages of the approach, and the steps that we have started to take to extend it based on user feedback.
KW - Clinical practice guidelines
KW - Concept-based search
KW - Context-sensitive search
KW - Digital libraries
KW - Information retrieval
KW - Medical informatics
UR - http://www.scopus.com/inward/record.url?scp=60049093635&partnerID=8YFLogxK
U2 - 10.1016/j.jbi.2008.07.003
DO - 10.1016/j.jbi.2008.07.003
M3 - Article
AN - SCOPUS:60049093635
SN - 1532-0464
VL - 42
SP - 11
EP - 21
JO - Journal of Biomedical Informatics
JF - Journal of Biomedical Informatics
IS - 1
ER -