Performance Comparison of Machine Learning Techniques on Diabetes Disease Detection

In this paper, the performance comparison of the machine learning techniques on diabetes disease detection is carried out. Diabetes disease attracts great attention in the machine learning community. Because diabetes is a chronic disease and needs to be detected at an early stage in order to deal with the correct medication. A series of machine learning techniques are used in the work such as Decision Trees (DT), Logistic Regressions (LR), Discriminant Analysis (DA), Support Vector Machines (SVM), k-Nearest Neighbors (k-NN) and ensemble learners. MATLAB software is considered. Especially, the MATLAB Classification Learner Tool (MCLT) is used. The MCLT covers the mentioned machine learning techniques and their various variants. Thus, a totally 24 classifiers are used in the presented work. The results are evaluated according to the 10-fold cross-validation criteria and average classification accuracy is used for performance measure. The obtained average accuracy scores are in the range of 65.5% and 77.9%. The best accuracy score 77.9% is produced by the LR method and the worst one 65.5% is produced by the Coarse Gaussian SVM technique.