Expert System for Early Diagnosis of Epilepsy Using the Web-Based Dempster Shafer Method

Abstract

The development of information and communication technology is currently very extensive in its use, especially technology in the field of computers. Expert Systems are one of the sciences in the field of computers that can help in diagnosing various diseases, one of which is epilepsy. The estimated number of epilepsy sufferers in Indonesia is 1.5 million with a prevalence of 0.5-0.6% of the Indonesian population. The expert system method used to diagnose epilepsy early is the Dempster Shafer method. The Dempster Shafer method is used to combine separate pieces of information or evidence to calculate the probability of an event. This study used 7 types of epilepsy, including in the Focal Epilepsy category consisting of Simple Partial and Complex Partial, while in the General Epilepsy category consisting of Absence, Atonic, Myoclonic, Tonic-Clonic, and Clonic. This study produces a website-based application for early diagnosis of epilepsy using the Dempster Shafer method with the PHP programming language and MySQL database. By using this application, it can provide convenience to the medical community and patients in early diagnosis of epilepsy experienced by sufferers. From the results of this study, it was found that the highest level of accuracy was found in Tonic-Clonic seizures which are included in the General Epilepsy category, namely 92.78%.