From indexing the biomedical literature to coding clinical text: experience with MTI and machine learning approaches

Authors:
Alan R. Aronson;Olivier Bodenreider;Dina Demner-Fushman;Kin Wah Fung;Vivian K. Lee;James G. Mork;Aurélie Névéol;Lee Peters;Willie J. Rogers
Affiliations:
Lister Hill Center, Bethesda, MD;Lister Hill Center, Bethesda, MD;Lister Hill Center, Bethesda, MD;Lister Hill Center, Bethesda, MD;Lister Hill Center, Bethesda, MD and Vanderbilt University, Nashville, TN;Lister Hill Center, Bethesda, MD;Lister Hill Center, Bethesda, MD;Lister Hill Center, Bethesda, MD;Lister Hill Center, Bethesda, MD
Venue:
BioNLP '07 Proceedings of the Workshop on BioNLP 2007: Biological, Translational, and Clinical Language Processing
Year:
2007

Citing 1
Cited 7

Stacking Bagged and Dagged Models

ICML '97 Proceedings of the Fourteenth International Conference on Machine Learning

Clinical text classification under the Open and Closed Topic Assumptions

International Journal of Data Mining and Bioinformatics
A hierarchical approach to encoding medical concepts for clinical notes

HLT-SRWS '08 Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies: Student Research Workshop
Exploring two biomedical text genres for disease recognition

BioNLP '09 Proceedings of the Workshop on Current Trends in Biomedical Natural Language Processing
A recent advance in the automatic indexing of the biomedical literature

Journal of Biomedical Informatics
Comparing a rule-based versus statistical system for automatic categorization of MEDLINE documents according to biomedical specialty

Journal of the American Society for Information Science and Technology
lexically-triggered hidden Markov models for clinical document coding

HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1
Linking multiple disease-related resources through UMLS

Proceedings of the 2nd ACM SIGHIT International Health Informatics Symposium

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes the application of an ensemble of indexing and classification systems, which have been shown to be successful in information retrieval and classification of medical literature, to a new task of assigning ICD-9-CM codes to the clinical history and impression sections of radiology reports. The basic methods used are: a modification of the NLM Medical Text Indexer system, SVM, k-NN and a simple pattern-matching method. The basic methods are combined using a variant of stacking. Evaluated in the context of a Medical NLP Challenge, fusion produced an F-score of 0.85 on the Challenge test set, which is considerably above the mean Challenge F-score of 0.77 for 44 participating groups.