Year: 2024
Type: article
Abstract: Diabetes mellitus is a chronic metabolic disease that has grown to be a major global health issue. Effective treatment and the avoidance of serious consequences depend on an early and precise diagnosis. A promising method for automated and precise diabetes detection in recent years has been machine learning (ML) approaches. The use of supervised machine learning techniques, such as Logistic Regression, Support Vector Machine (SVM), K-Nearest Neighbours (KNN), and Random Forest, for diabetes detection is examined in this study. A popular benchmark dataset in the field of diabetes research, the Pima Indian Diabetes Dataset, is used to assess the efficacy of these algorithms. With Logistic Regression obtaining the best accuracy, experimental results demonstrate the effectiveness of machine learning algorithms to predict diabetes. The study's conclusions demonstrate ML's potential as a valuable tool for early detection and prevention of diabetes. Key Words: Machine learning, Diabetes detection, Support vector machine, Logistic regression, Random forest
DOI: 10.55041/ijsrem39969
Author: Neelam Barak
Institution: Maharaja Surajmal Institute of Technology
Language: English
Subfield: Health Information Management
Field: Health Professions
Domain: Health Sciences
Open Access status: bronze
OpenAlex ID: W4405728124