Medical diagnosis lost in translation: analysis of uncertainty and negation expressions in English and Swedish clinical texts

Authors:
Danielle L. Mowery;Sumithra Velupillai;Wendy W. Chapman
Affiliations:
University of Pittsburgh, Pittsburgh, PA;Stockholm University, Stockholm, Sweden;University of California San Diego, La Jolla, CA
Venue:
BioNLP '12 Proceedings of the 2012 Workshop on Biomedical Natural Language Processing
Year:
2012

Citing 3
Cited 0

A corpus study of evaluative and speculative language

SIGDIAL '01 Proceedings of the Second SIGdial Workshop on Discourse and Dialogue - Volume 16
ConText: An algorithm for determining negation, experiencer, and temporal status from clinical reports

Journal of Biomedical Informatics
Document-level classification of CT pulmonary angiography reports based on an extension of the ConText algorithm

Journal of Biomedical Informatics

Quantified Score

Hi-index	0.00

Visualization

Abstract

In the English clinical and biomedical text domains, negation and certainty usage are two well-studied phenomena. However, few studies have made an in-depth characterization of uncertainties expressed in a clinical setting, and compared this between different annotation efforts. This preliminary, qualitative study attempts to 1) create a clinical uncertainty and negation taxonomy, 2) develop a translation map to convert annotation labels from an English schema into a Swedish schema, and 3) characterize and compare two data sets using this taxonomy. We define a clinical uncertainty and negation taxonomy and a translation map for converting annotation labels between two schemas and report observed similarities and differences between the two data sets.