Abstract
Diabetes is a chronic condition that results from the body's resistance to or the pancreas' inability to effectively use the insulin it produces. Insulin, a peptide hormone, was responsible for regulating blood sugar. Repeated episodes of hyperglycemia, also known as high blood glucose or elevated blood sugar, are caused by hysterical diabetes and may cause severe damage to a variety of unique human body systems, including the nervous and cardiovascular systems. Long-term diabetic nerve, eye, renal, vascular, cardiovascular, and visual impairments are real. Adults with diabetes are two to three times more likely to have a heart attack or stroke. The likelihood of a negative result from several viral infections, including COVID-19, is raised in people with diabetes. One in five of the more than 58 million persons who live with diabetes are unaware of their condition. Different diseases are identified using machine learning methods, including Decision Trees (DT), Support Vector Machines (SVM), and K-Nearest Neighbors (KNN). The use of machine learning algorithms can result in quick and accurate disease prediction. One of the well-liked machine learning techniques in the medical industry is the decision tree, which has strong categorization capabilities. The most important risk factors for prediabetes were discovered to be age, waist-hip ratio (WHR), BMI, systolic and diastolic blood pressure, and a family history of diabetes. While the classification accuracy of the images produced by both methods is satisfactory, the SVM greatly outperforms the KNN in terms of classification speed and accuracy. SVM offered 98% accuracy, which is higher than DT (92.4%) and KNN (93.94%). Glucose plays a major role in diabetes.
.
Keyword
Prediction, Diabetes, Machine Learning.
PDF Download (click here)
|