An Accurate Clinical Implication Assessment for Diabetes Mellitus Prevalence Based on a Study from Nigeria

Abstract

The increasing rate of diabetes is found across the planet. Therefore, the diagnosis of pre-diabetes and diabetes is important in populations with extreme diabetes risk. In this study, a machine learning technique was implemented over a data mining platform by employing Rule classifiers (PART and Decision table) to measure the accuracy and logistic regression on the classification results for forecasting the prevalence in diabetes mellitus patients suffering simultaneously from other chronic disease symptoms. The real-life data was collected in Nigeria between December 2017 and February 2019 by applying ten non-intrusive and easily available clinical variables. The results disclosed that the Rule classifiers achieved a mean accuracy of 98.75%. The error rate, precision, recall, F-measure, and Matthew’s correlation coefficient MCC were 0.02%, 0.98%, 0.98%, 0.98%, and 0.97%, respectively. The forecast decision, achieved by employing a set of 23 decision rules (DR), indicates that age, gender, glucose level, and body mass are fundamental reasons for diabetes, followed by work stress, diet, family diabetes history, physical exercise, and cardiovascular stroke history. The study validated that the proposed set of DR is practical for quick screening of diabetes mellitus patients at the initial stage without intrusive medical tests and was found to be effective in the initial diagnosis of diabetes.