Publication

Abstract : Diabetes mellitus, a chronic metabolic disorder, poses a growing global health challenge with profound societal and economic implications. This article presents a comprehensive comparative analysis of multiple machine learning (ML) algorithms for early diabetes prediction, harnessing the power of ML. Utilizing a diverse dataset that encompasses demographic, clinical, and lifestyle factors, the study aims to develop an accurate and efficient predictive model. The performance of various ML techniques, including logistic regression, decision trees, support vector machines, random forests, k-nearest neighbors, and the xgboost classifier, is thoroughly explored in terms of accuracy, sensitivity, and specificity. This comparative analysis sheds light on the strengths and weaknesses of each algorithm, providing valuable insights for healthcare practitioners and researchers in selecting the most appropriate approach for diabetes prediction. The findings underscore the immense potential of ML-based systems in improving diabetes risk assessment, facilitating timely interventions, and enabling personalized healthcare strategies. This research makes a significant contribution to the ongoing efforts to combat the diabetes epidemic and enhance public health outcomes through innovative applications of machine learning.