Article: Indexing ICD-9 codes for free-textual clinical diagnosis records by a new ensemble classifier Journal: International Journal of Computational Intelligence in Bioinformatics and Systems Biology (IJCIBSB) 2009 Vol.1 No.2 pp.177 - 192 Abstract: An expert system which can support in indexing automatically an ICD-9 code for a clinical diagnosis record is necessary and in great demand for hospitals. The ICD-9 code determines reimbursement amount and an incorrect code may result in fining. In this paper we present a new expert system to index automatically an ICD-9 code with respect to two perspectives. First, the system analyses the free-textual medical documents as would be necessary to activate the uses of natural language process and text mining. A free-textual document has to be represented by a large number of vocabulary words as analogy with a high dimensional data vector. Second, we drive a new ensemble classifier which combines the uses of the majority voting approach with multiple learning algorithms and the boosting approach at the same time. The motivation is stimulated in that when a predicted ICD-9 code of a majority voting of a clinical diagnosis record is incorrect, the record needs to be trained more often. The experimental results show that the proposed ensemble technique is able to achieve simultaneously stability and performance in terms of classification accuracy. Inderscience Publishers - linking academia, business and industry through research

Title: Indexing ICD-9 codes for free-textual clinical diagnosis records by a new ensemble classifier

Authors: Chien-Hsing Chen, Chung-Chian Hsu

Addresses: National Yunlin University of Science and Technology, 123 University Road, Section 3, Douliou, Yunlin 64002, Taiwan, ROC. ' National Yunlin University of Science and Technology, 123 University Road, Section 3, Douliou, Yunlin 64002, Taiwan, ROC

Abstract: An expert system which can support in indexing automatically an ICD-9 code for a clinical diagnosis record is necessary and in great demand for hospitals. The ICD-9 code determines reimbursement amount and an incorrect code may result in fining. In this paper we present a new expert system to index automatically an ICD-9 code with respect to two perspectives. First, the system analyses the free-textual medical documents as would be necessary to activate the uses of natural language process and text mining. A free-textual document has to be represented by a large number of vocabulary words as analogy with a high dimensional data vector. Second, we drive a new ensemble classifier which combines the uses of the majority voting approach with multiple learning algorithms and the boosting approach at the same time. The motivation is stimulated in that when a predicted ICD-9 code of a majority voting of a clinical diagnosis record is incorrect, the record needs to be trained more often. The experimental results show that the proposed ensemble technique is able to achieve simultaneously stability and performance in terms of classification accuracy.

Keywords: clinical diagnosis records; ICD-9; ensemble classifiers; majority voting; boosting voting; expert systems; natural language processing; NLP; text mining; medical documents; classification accuracy; International Classification of Diseases; reimbursement; medical fees.

DOI: 10.1504/IJCIBSB.2009.030648

International Journal of Computational Intelligence in Bioinformatics and Systems Biology, 2009 Vol.1 No.2, pp.177 - 192

Published online: 29 Dec 2009 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Indexing ICD-9 codes for free-textual clinical diagnosis records by a new ensemble classifier

Keep up-to-date