Predictive analysis for diabetes mellitus prediction using supervised techniques
by Salliah Shafi Bhat; Madhina Banu; Gufran Ahmad Ansari
International Journal of Bioinformatics Research and Applications (IJBRA), Vol. 20, No. 1, 2024

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.

Online publication date: Thu, 14-Mar-2024

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Bioinformatics Research and Applications (IJBRA):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com