HPCC: An Ensembled Framework for the Prediction of the onset of Diabetes

Abstract

Diabetes being one of the chronic diseases worldwide needs proper diagnosis and treatment since this is on the spread and is on the way of becoming the main cause of many other medical disorders. The advent of such a disease must be nipped in the bud if a person is found to be prone to it. Such an experiment has been done in this study which tells about the onset of diabetes in the females of Pima Indian origin of Arizona. Diagnosing Diabetes is one of the problems that require high level of accurate analysis and prediction. Data scientists have attempted several data analytics methods in order to improvise the examination of data sets. Previously, various data mining techniques have been implemented in the healthcare systems, however, the hybridization in addition to single technique in the identification of the disease shows promising outcomes, and can be useful in further investigating its treatment and can help in reducing the cost if the treatment. Traditional techniques which are used for clinical decision support systems are grounded on a single classifier or combination of various classifiers which are used for the diagnosis of the disease and its prediction. Recently much heed has been paid to improve the performance of disease prediction with the use of ensemble-based methods. Using ensemble methods in decision support systems assist in analyzing theses type of diseases more effectively. To improve the performance of weak classifiers boosting and bagging techniques can be used. These techniques are based on combining the outputs and functionality of the various classifiers used. A weighted majority vote or a simple majority vote which has been used in this study are the most common rules for the implementation of bagging and boosting. In this paper, we compare the performance of bagging and boosting with our hybrid approach called Hierarchical and Progressive Combination of Classifiers (HPCC) through the study of the famous Pima Indians Diabetes Dataset and the best classifier is chosen on the basis of the accuracy achieved.