Classifying Supporting, Refuting, or Uncertain Evidence for Pneumonia Case Review
Authors:
Open Access
- 2 February 2015
- journal article
- Published by University of Illinois Libraries in Online Journal of Public Health Informatics
- Vol. 7 (1)
Abstract
We found substantial annotator variability in identifying supporting, refuting, or uncertain evidence for the diagnosis of pneumonia in clinical text. Future work will expand these methods to a larger case sample and incorporate a more formal linguistic analysis to identify specific lexical cues thereby extending existing taxonomies of uncertainty and improving automated NLP algorithms.Keywords
This publication has 1 reference indexed in Scilit:
- Varieties of Uncertainty in Health CareMedical Decision Making, 2011