Data Mining in Dermatological Diagnosis: A Method for Severity Prediction

Abstract

Medical diagnosis is an important but complicated task that should be performed with great accuracy and efficiency. In dermatology there are a lot of diseases which shows similar pattern in appearance and symptoms. So diagnosis of a single patient can differ significantly if he is examined by different physicians. So we need a standard format for predicting such a disease. Today, automated medical analysis help doctors to diagnose and predict diseases, at a very fast pace. This study goes through different dermatological diseases with similar symptoms which may even prove fatal if left unattended at exact time. Medical dataset used for this work contain 230 instances with 22 attributes. In this paper we have experimented on data gathered from the southern part of Kerala, India. For better prediction calculation of accuracy of mining algorithm is important. Two data mining classification algorithm Naive Bayes’(NB) and J48 was used for data analysis. Weka Open Source Software, a build in software tool for data mining was used. The GUI, developed in Java, reveals the chances of different dermatological disease and also finds out the probabilities of occurrence of each disease.