Detecting Intuitive Mentions of Diseases in Narrative Clinical Text

Authors:
Stéphane M. Meystre
Affiliations:
Department of Biomedical Informatics, University of Utah, Salt Lake City, Utah, USA
Venue:
AIME '09 Proceedings of the 12th Conference on Artificial Intelligence in Medicine: Artificial Intelligence in Medicine
Year:
2009

Citing 6
Cited 0

An Evaluation of Statistical Approaches to Text Categorization

Information Retrieval
Information Retrieval

Information Retrieval
Towards linking patients and clinical information: detecting UMLS concepts in e-mail

Journal of Biomedical Informatics - Special issue: Building nursing knowledge through infomatics: from concept representation to data mining
A temporal constraint structure for extracting temporal information from clinical narrative

Journal of Biomedical Informatics
Natural language processing to extract medical problems from electronic clinical documents: Performance evaluation

Journal of Biomedical Informatics
ConText: an algorithm for identifying contextual features from clinical text

BioNLP '07 Proceedings of the Workshop on BioNLP 2007: Biological, Translational, and Clinical Language Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

A significant portion of the clinical information content of narrative text documents in the medical record is only mentioned intuitively, but automated information extraction systems typically focus on explicitly mentioned concepts only. To extend the extraction of clinical information to intuitively mentioned diseases, we have developed a natural language processing application based on MMTx and on context analysis algorithms, enhanced with the detection of disease-specific concepts (e.g. medications used only for this disease), and values of some specific biomarkers. This application was developed for the i2b2 obesity challenge, a competition focused on the detection of patients with obesity or common comorbidities.