Enhanced automatic classification of epilepsy diagnosis using ICD9 and SNOMED-CT

Abstract

Epilepsy is a group of neurological disorders characterized by epileptic seizures. The diagnosis of epilepsy is typically made based on the description of the seizures and the underlying cause. It is important that the diagnosis is correct. After the diagnosis process, physicians classify epilepsy according to the International Classification of Diseases (ICD), Ninth Revision (ICD-9). The classification process is time consuming and it demands the realization of integral exams. The existing system proposes an automatic process of classifying epileptic diagnoses based on ICD-9. A text mining approach, using preprocessed medical records is used to classify each instance mapping into the corresponding standard code. The proposed system contributes in enhancing the accuracy in the classification of the diagnosis by identifying the type of epilepsy and mapping it with the standard codes of ICD-9 and Systematized Nomenclature Of Medicine—Clinical Terms (SNOMED-CT). The paper discusses about the related works and proposed system. The experimental results, conclusion, and future work have been discussed in the subsequent topics.