Risk Assessment of Type 2 Diabetes Mellitus Prediction using an Improved Combination of NELM-PSO

Abstract

Risk Assessment of Diabetes Type-II is crucial in preventing it and reducing the risk of various comorbidities. There are many existing machine learning models for predicting iType-II diabetics in short term future or in unspecified future. But obtaining a model having optimal performance and predicting diabetes risk in long term future are the main problems. These problems are handled in this work by proposing a stacking based integrated KELM imodel to predict the risk of diabetes Type-II for a person within five years after assessment. The Pima Indian Diabetic Dataset (PIDD) and a Diabetic Research Center dataset are used in this study. A Min-Max normalization is used to pre-process the noisy datasets. The HAFPSO algorithm used in this work explores the best combination of Base learners by increasing the Classification Accuracy (CA) and decreasing the kernel complexity of the optimal learners. Finally, the model is integrated by utilizing the KELM as a meta-classifier that combines the predictions of the twenty Base Learners. The proposed method is assessed with different measures such as accuracy, sensitivity, specificity, Mathews Correlation Coefficient, and Kappa Statistics. The proposed KELM-HAFPSO approach has got better values of the considered metrics confirming its effectiveness in identifying type-II diabetes. The proposed method helps the clinicians to predict the patients who are at a high risk of Type-II diabetes in the future with the highest accuracy of 98.5%. The results obtained show that the KELM-HAFPSO approach is a promising new tool for identifying type-II diabetes.