A novel approach to predict diabetes by Cascading Clustering and Classification

Abstract

Knowledge of incidence and prevalence of a disease is vital in Community Medicine to control a disease. It is important in Internal Medicine for clinical diagnosis and presumptive treatment on a probability model. Prevalence informs the total case load at a given time. Incidence yields a pointer to extent of attention required and choice of measures. In itially K-means clustering is used to group the disease related data into clusters and ass igns classes to dusters. Subsequently multiple different classification algorithms are trained on the result set to build the final classifier model based on K fold cross validation method. This methodology is evaluated using 768 raw diabetes data obtained from a city hospital. The best accuracy fo r the given dataset is achieved in bagging algorithm compared to other classifiers. The proposed approach helps do ctors in their diagnosis de cisions and also in their treatment planning procedures for different categories.

A Survey on Data-Mining Technologies for Prediction and Diagnosis of Diabetes

“…As a result of this study among 10,192,166 records it includes 163,045 diabetes patients , the prevalence of Diabetes Mellitus will increase with age and the aging effect on female is more apparent. Through the mining of Apriori, a strong relation between the diabetes and a lot of oral diseases like Dental caries, Pulpitis, Acute Gingivitis etc is found.…”

“…It classifies or maps a data item into any one of many predefined classes. Palivela Hemant at [10] combines K-means clustering with various different classification algorithms like SMO, Naive Bayes, Bagging, AdaBoost, J48, Rotation Forest and Random Forest to predict the positive and negative of disease. The data consists of 768 different entries in accordance with attributes like Skin , Mass , Age , Insulin , pregnant etc are used .…”