Title | ||
---|---|---|
From indexing the biomedical literature to coding clinical text: experience with MTI and machine learning approaches |
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. |
Year | Venue | Keywords |
---|---|---|
2007 | BioNLP@ACL | classification system,nlm medical text indexer,clinical history,information retrieval,mean challenge f-score,biomedical literature,challenge test set,icd-9-cm code,impression section,basic method,clinical text,medical nlp challenge,machine learning,indexation,pattern matching |
Field | DocType | Citations |
Information retrieval,Indexer,Computer science,Support vector machine,Search engine indexing,Coding (social sciences),Natural language processing,Artificial intelligence,Medical literature,Machine learning,Test set | Conference | 24 |
PageRank | References | Authors |
1.71 | 10 | 9 |
Name | Order | Citations | PageRank |
---|---|---|---|
Alan R. Aronson | 1 | 2551 | 260.67 |
Olivier Bodenreider | 2 | 2715 | 226.05 |
Dina Demner Fushman | 3 | 1717 | 147.70 |
Kin Wah Fung | 4 | 126 | 20.25 |
Vivian K. Lee | 5 | 24 | 2.05 |
James G. Mork | 6 | 647 | 65.22 |
Aurélie Névéol | 7 | 565 | 50.50 |
Lee Peters | 8 | 43 | 6.21 |
Willie J. Rogers | 9 | 118 | 7.85 |