Fine-grained Certainty Level Annotations Used for Coarser-grained E-health Scenarios: Certainty Classication of Diagnostic Statements in Swedish Clinical Text
2012 (English)In: Proceedings of the 13th international conference on Computational Linguistics and Intelligent Text Processing - Volume Part II / [ed] Alexander Gelbukh, Berlin/Heidelberg: Springer Berlin/Heidelberg, 2012, 450-461 p.Conference paper (Refereed)
An important task in information access methods is distinguishingfactual information from speculative or negated information.Fine-grained certainty levels of diagnostic statements in Swedish clinicaltext are annotated in a corpus from a medical university hospital.The annotation model has two polarities (positive and negative) andthree certainty levels. However, there are many e-health scenarios wheresuch ne-grained certainty levels are not practical for information extraction.Instead, more coarse-grained groups are needed. We presentthree scenarios: adverse event surveillance, decision support alerts andautomatic summaries and collapse the ne-grained certainty level classi-cations into coarser-grained groups. We build automatic classiers foreach scenario and analyze the results quantitatively. Annotation discrepanciesare analyzed qualitatively through manual corpus analysis. Ourmain ndings are that it is feasible to use a corpus of ne-grained certaintylevel annotations to build classiers for coarser-grained real-worldscenarios: 0.89, 0.91 and 0.8 F-score (overall average).
Place, publisher, year, edition, pages
Berlin/Heidelberg: Springer Berlin/Heidelberg, 2012. 450-461 p.
, Lecture Notes in Computer Science, ISSN 0302-9743 ; 7192
Clinical documentation, Certainty level classication, Annotation granularity, Automatic Summary, Decision Support Alerts, Adverse Event Surveillance, E-health
Information Systems, Social aspects
Research subject Computer Science; IT for health
IdentifiersURN: urn:nbn:se:su:diva-74810DOI: 10.1007/978-3-642-28601-8_38ISBN: 978-3-642-28600-1OAI: oai:DiVA.org:su-74810DiVA: diva2:512161
CICLing 2012, New Delhi, India, March 11–17, 2012