Analysis and Prediction of Diabetes Mellitus using Machine Learning: A Study on Diabetic Dataset
Abstract
Diabetes mellitus is a chronic metabolic disorder affecting millions of people worldwide. The increasing prevalence of diabetes poses significant challenges to healthcare systems and requires effective early detection and management strategies. This research paper explores the application of machine learning techniques for analyzing and predicting diabetes based on a comprehensive diabetic dataset. The dataset consists of various clinical and demographic features of patients, making it an ideal resource for building predictive models. Through the study, we aim to identify key factors contributing to diabetes and develop accurate models for early diagnosis. The dataset used in this study is sourced from the UCI Machine Learning Repository. Two machine learning algorithms, namely), Multilayer Perceptron (MLP) and Naïve Bayes classifiers, are employed to analyze the dataset and determine the most effective performance and accuracy. Among these classifiers, the MLP algorithm demonstrates the highest performance with an accuracy of 85.50%.
Keywords
Download Options
Introduction
Diabetes mellitus is a complex and progressive disease characterized by chronic hyperglycemia, resulting from the body's inability to produce or effectively utilize insulin. In this research, we leverage a comprehensive diabetic dataset to explore the use of machine learning algorithms for diabetes prediction and risk assessment. In recent literature, various AI algorithms have been employed for the detection of diabetic. Diabetes mellitus is the leading cause of blindness among a significant age group in Western countries and its prevalence is also increasing in developing nations. Individuals with diabetes are at a significantly higher risk of developing blindness compared to those without diabetes. Moderate diabetic and clinically significant macular edema can result in severe vision loss. Early detection through regular screening is crucial as it can be effectively treated in its initial stages. However, the cost and manual effort involved in screening are significant, making automated screening highly desirable. In diabetic, the blood vessels that nourish the retina start leaking fluid and blood, leading to characteristic visual features such as microaneurysms, hemorrhages, hard exudates, cotton wool spots, and vein occlusion [9].
Conclusion
Based on the experimental results, it can be observed that all Two machine learning algorithms achieved high accuracy in predicting diabetic. The MLP algorithm showed the highest overall performance, with an accuracy of 85.50%. The Naïve Bayes algorithm also performed well, with an accuracy of 83.47%. Naïve Bayes demonstrated good performance, albeit slightly lower than the other algorithm, with an accuracy of 83.47%.
These results indicate that machine learning models have the potential to effectively predict diabetic using the Diabetes dataset. The high accuracy, precision, and recall values achieved by the algorithms highlight their ability to accurately classify instances of diabetic. The findings of this study contribute to the development of AI-based models for the early detection and diagnosis of diabetic, which can aid in timely interventions and prevent vision loss in patients with diabetes. Further research and refinement of these algorithms can potentially improve their performance and expand their applications in the field of diabetic prediction.