Year: 2007 |
Download Free Adobe Acrobat Reader |
LHNCBC-2007-040 |
From Indexing the Biomedical Literature to Coding Clinical Text: Experience with MTI and Machine Learning Approaches |
Aronson AR, Bodenreider O, Demner-Fushman D, Fung KW, Lee VK, Mork JG, Neveol A, Peters L, Rogers WJ |
Proc. 2007 Workshop on Biomedical Natural Language Processing (BioNL'07), June 2007, pp. 105-112, Prague, Czech Republic. |
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. |
PDF |