Title: Predictive analysis for diabetes mellitus prediction using supervised techniques
Authors: Salliah Shafi Bhat; Madhina Banu; Gufran Ahmad Ansari
Addresses: B.S. Abdur Rahman Crescent Institute of Science and Technology, Chennai – 48, India ' B.S. Abdur Rahman Crescent Institute of Science and Technology, Chennai – 48, India ' Faculty of Science, Dr. Vishwanath Karth MIT World Peace University (MIT-WPU), Pune – 411038, India
Abstract: Diabetes mellitus is a silent disease. The worldwide prevalence of diabetes is rising quickly. Implementing lifestyle modifications and adopting necessary preventative measures for early detection of diabetes can help to avoid the development of diabetes. In this scenario, there is a need for simple, rapid, and accurate diagnostic methods. Various research is being carried out to increase the efficiency, effectiveness, dependability, and precision of these methods for identifying certain illnesses. Using diagnostic data from a dataset from the University of California Irvine (UCI) this research aims to examine whether a patient has diabetes or not. To predict diabetes four distinct machine learning algorithms (MLAs) have been used. With an accuracy rate of 98% the random forest was the most effective method. Other algorithms' accuracy rates range from 96% to 89% as well. In this paper machine learning prediction method for identifying diabetes patients is described. The author proposed a framework for early prediction of diabetes mellitus.
Keywords: diabetes mellitus; framework; machine learning; patient; accuracy.
DOI: 10.1504/IJBRA.2024.137380
International Journal of Bioinformatics Research and Applications, 2024 Vol.20 No.1, pp.78 - 96
Received: 16 Jun 2023
Accepted: 19 Jul 2023
Published online: 14 Mar 2024 *