Regression Imputation and Optimized Gaussian Naïve Bayes Algorithm for an Enhanced Diabetes Mellitus Prediction Model

Abstract

Diabetes mellitus (DM) is a category of metabolic disorders caused by high blood sugar. The DM affects human metabolism, and this disease causes many complications like Heart disease, Neuropathy, Diabetic retinopathy, kidney problems, skin disorder and slow healing. It is therefore essential to predict the presence of DM using an automated diabetes diagnosis system, which can be implemented using machine learning algorithms. A variety of automated diabetes prediction systems have been proposed in previous studies. Even so, the low prediction accuracy of DM prediction systems is a major issue. This proposed work developed a diabetes mellitus prediction system to improve the diabetes mellitus prediction accuracy using Optimized Gaussian Naive Bayes algorithm. This proposed model using the Pima Indians diabetes dataset as an input to build the DM predictive model. The missing values of an input dataset are imputed using regression imputation method. The sequential backward feature elimination method is used in this proposed model for selecting the relevant risk factors of diabetes disease. The proposed machine learning classifier named Optimized Gaussian Naïve Bayes (OGNB) is applied to the selected risk factors to create an enhanced Diabetes diagnostic system which predicts Diabetes in an individual. The performance analysis of this prediction architecture shows that, over other traditional machine learning classifiers, the Optimized Gaussian Naïve Bayes achieves an 81.85% classifier accuracy. This proposed DM prediction system is effective as compared to other diabetes prediction systems found in the literature. According to our HIGHLIGHTS The aim of this study is to build a diabetes mellitus disease prediction model using machine learning algorithms. To build a diabetes mellitus model for diabetes early prediction, the optimized gaussian naive bayes algorithm is proposed and used as a classifier. 2 Mohammed Mohideen, D.F.; et al.

Investigating Role of Supervised Machine Learning Approach in Classification of Diabetic Patient

“…• Reinforcement Learning: Entities participate in reinforcement learning when they take in data from their actions and change their behavior based on that data. Incentives, such as praise for good conduct and reprimand for bad, serve as reinforcement for the entity's actions [12]. There is zero oversight of the representative.…”

“…Acquisition of more accurate along with trustworthy results is one aim of the study [11]. Researchers D. F. M. Mohideen et al (2021) used a combination of regression imputation and a Gaussian Naive Bayes algorithm to accurately forecast occurrence of diabetes mellitus [12].…”

“…Accuracy Decision Tree [6] 86% Gaussian NB [12] 93% LDA [18] 94% SVC [18] 60% Random Forest [1] 91% Extra Trees [13] 91% AdaBoost [18] 93% Perceptron [18] 76% Logistic Regression [5] 96% Gradient Boost Classifier [18] 93% Bagging [18] 90% KNN [2] 90% Table 3 shows that numerous classifiers are compared using the same datasets, which are diabetes datasets. In that comparison, the accuracy scores of SVM, Decision Tree, KNN, ANN, and Logistic Regression were 84%, 86%, 90%, 96%, and 97%, respectively.…”

Chronic Diseases Prediction Using Machine Learning With Data Preprocessing Handling: A Critical Review

“…The optimization method researchers often use to predict chronic disease is PSO. Most researchers also perform optimizations based on single machine learning algorithms, such as Optimized Gaussian Naïve Bayes (OGNB) [176]. The OGNB classifier blends Gaussian naive Bayes, Adaboost, and the random search method to construct a proficient classifier that optimizes prediction scores while mitigating overfitting concerns.…”

“…Mohideen [176] study also handled data preprocessing, including imputing missing values using regression, normalization using min-max, and Sequential Backward Feature Elimination (SBFE). The study analyzed the implementation of regression values as missing value imputation, where the application of regression values resulted in an increase in accuracy by 1.6% to 78.74%.…”