ICD-9 Tagging of Clinical Notes Using Topical Word Embedding

摘要: Medical records, which contains text, has been dramatically increasing everyday. This means that there is a greater need of analyzing health information in better way. And this can be done through document classification natural language applications. In study, we describe tagging patient notes with ICD-9 codes topical word embedding deep learning called EnHANs. We formulate paper as multi-label, multi-class problem to categorize the dataset 400,000 critical care unit medical records. Knowing accurate diagnosis using vital for billing and insurance claims. demonstrate use model, learn classify their corresponding labels moderately well than single-label classification.