UNIGE document Scientific Article
previous document  unige:28897  next document
add to browser collection
Title

Automatic medical knowledge acquisition using question-answering

Authors
Published in Studies in Health Technology and Informatics. 2009, vol. 150, p. 569-73
Abstract We aim at proposing a rule generation approach to automatically acquire structured rules that can be used in decision support systems for drug prescription. We apply a question-answering engine to answer specific information requests. The rule generation is seen as an equation problem, where the factors are known items of the rule (e.g., an infectious disease, caused by a given bacteria) and solutions are answered by the engine (e.g., some antibiotics). A top precision of 0.64 is reported, which means, for about two third of the knowledge rules of the benchmark, one of the recommended antibiotic was automatically acquired by the rule generation method. These results suggest that a significant fraction of the medical knowledge can be obtained by such an automatic text mining approach.
Keywords Anti-Bacterial Agents/therapeutic useAutomatic Data ProcessingCommunicable DiseasesDecision Support Systems, ClinicalHumansPractice Guidelines as Topic
Identifiers
PMID: 19745375
Full text
Article (Published version) (76 Kb) - document accessible for UNIGE members only Limited access to UNIGE
Structures
Research group Interfaces Homme-machine en milieu clinique (610)
Project FP7: DebugIT
Citation
(ISO format)
PASCHE, Emilie et al. Automatic medical knowledge acquisition using question-answering. In: Studies in Health Technology and Informatics, 2009, vol. 150, p. 569-73. https://archive-ouverte.unige.ch/unige:28897

215 hits

1 download

Update

Deposited on : 2013-07-12

Export document
Format :
Citation style :