Machine Learning based Early Prediction of Type 2 Diabetes: A New Hybrid Feature Selection Approach using Correlation Matrix with Heatmap and SFS

Authors : Selim BUYRUKOĞLU, Ayhan AKBAŞ

Pages : 110-117

Doi:10.17694/bajece.973129

View : 19 | Download : 8

Publication Date : 2022-04-30

Article Type : Research Paper

Abstract :A new hybrid machine learning method for the prediction of type 2 diabetes is introduced and explained in detail. Also, outcomes are compared with similar researches. Early prediction of diabetes is crucial to take necessary measures insert ignore into journalissuearticles values(i.e. changing eating habits, patient weight control etc.);, to defer the emergence of diabetes and to reduce the death rate to some extent and ease medical care professionals’ decision-making in preventing and managing diabetes mellitus. The purpose of this study is the creation of a new hybrid feature selection approach combination of Correlation Matrix with Heatmap and Sequential forward selection insert ignore into journalissuearticles values(SFS); to reveal the most effective features in the detection of diabetes. A diabetes data set with 520 instances and seven features were studied with the application of the proposed hybrid feature selection approach. The evaluation of the selected optimal features was measured by applying Support Vector Machinesinsert ignore into journalissuearticles values(SVM);, Random Forestinsert ignore into journalissuearticles values(RF);, and Artificial Neural Networksinsert ignore into journalissuearticles values(ANN); classifiers. Five evaluation metrics, namely, Accuracy, F-measure, Precision, Recall, and AUC showed the best performance with ANN insert ignore into journalissuearticles values(99.1%);, F-measure insert ignore into journalissuearticles values(99.1%);, Precision insert ignore into journalissuearticles values(99.3%);, Recall insert ignore into journalissuearticles values(99.1%);, and AUC insert ignore into journalissuearticles values(99.2%);. Our proposed hybrid feature selection model provided a more promising performance with ANN compared to other machine learning algorithms.
Keywords : Artificial Neural Network, Correlation Matrix, Sequential Forward Selection, Diabetes Mellitus, Hybrid Feature Selection