Performance Analysis of Machine Learning Techniques to Predict Diabetes\n Mellitus

2019/01/10 by Md Faruque, Faruque, Md. Faisal, Asaduzzaman Asaduzzaman +3 · 1 citation
Health Professions · #Artificial Intelligence in Healthcare

paper · pdf · doi:10.48550/arxiv.1902.10028

Abstract

Diabetes mellitus is a common disease of human body caused by a group of\nmetabolic disorders where the sugar levels over a prolonged period is very\nhigh. It affects different organs of the human body which thus harm a large\nnumber of the body's system, in particular the blood veins and nerves. Early\nprediction in such disease can be controlled and save human life. To achieve\nthe goal, this research work mainly explores various risk factors related to\nthis disease using machine learning techniques. Machine learning techniques\nprovide efficient result to extract knowledge by constructing predicting models\nfrom diagnostic medical datasets collected from the diabetic patients.\nExtracting knowledge from such data can be useful to predict diabetic patients.\nIn this work, we employ four popular machine learning algorithms, namely\nSupport Vector Machine (SVM), Naive Bayes (NB), K-Nearest Neighbor (KNN) and\nC4.5 Decision Tree, on adult population data to predict diabetic mellitus. Our\nexperimental results show that C4.5 decision tree achieved higher accuracy\ncompared to other machine learning techniques.\n

Cited by

• Performance Analysis of Machine Learning Algorithms in Chronic Kidney Disease Prediction

Related

• A Comparative Study of Machine Learning Techniques for Early Prediction of Diabetes
• Diabetes Prediction and Management Using Machine Learning Approaches
• Explainable predictions of different machine learning algorithms used to predict Early Stage diabetes
• Diabetes mellitus prediction and diagnosis from a data preprocessing and machine learning perspective
• Using Machine Learning Techniques to Identify Key Risk Factors for Diabetes and Undiagnosed Diabetes