Modelling of Diabetic Cases for Effective Prevalence Classification

Abstract

INTRODUCTION: This study compares and contrasts various machine learning algorithms for predicting diabetes. The study of current research work is to analyse the effectiveness of various machine learning algorithms for diabetes prediction.
 OBJECTIVES: To compare the efficacy of various machine learning algorithms for diabetic prediction.
 METHODS: For the same, a diabetic dataset was subjected to the application of various well-known machine learning algorithms. Unbalanced data was handled by pre-processing the dataset. The models were subsequently trained and assessed using different performance metrics namely F1-score, accuracy, sensitivity, and specificity.
 RESULTS: The experimental results show that the Decision Tree and ensemble model outperforms all other comparative models in terms of accuracy and other evaluation metrics.
 CONCLUSION: This study can help healthcare practitioners and researchers to choose the best machine learning model for diabetes prediction based on their specific needs and available data.