An Information Retrieval Approach to ICD-10 Classification

ICD-10 (International Classification of Diseases 10th revision) is a classification code for diseases, signs and symptoms, abnormal findings, complaints, social circumstances, and external causes of injury or diseases. This paper describes an automatic information retrieval approach to map free-text disease descriptions to ICD-10 codes. We use the Hospital Italiano de Buenos Aires (HIBA) terminology data mapped to ICD-10 codes as indexed data to find an appropriate ICD-10 code using search engine similarity metrics.