Deep Learning Text Classification for Medical Diagnosis

The ICD coding is the international standard for the classification of diseases and related disorders, drawn up by the World Health Organization. It was introduced to simplify the exchange of medical data, to speed up statistical analyzes and to make insurance reimbursements efficient. The manual classification of ICD-9-CM codes still requires a human effort that implies a considerable waste of resources and for this reason several methods have been presented over the years to automate the process. In this thesis an approach is proposed for the automatic classification of medical diagnoses in ICD-9-CM codes using the Recurrent Neural Networks, in particular the LSTM module, and exploiting the word embedding. The results were satisfactory as we were able to obtain better accuracy than Support Vector Machines, the most used traditional method. Furthermore, we have shown the effectiveness of specific domain embedding models compared to general ones.