An efficient diabetes prediction system for better diagnosis. (8th September 2022)

• Record Type: Journal Article
• Authors: Murthy, T. Satyanarayana
• Is Part Of: International journal of intelligent enterprise. Volume 9:Number 4(2022)
• Page Start: 408
• Page End: 421
• Publication Date: 2022-09-08
• Subjects: diabetes mellitus -- metabolic -- knowledge-based DSS -- PIMA Indian Heritage -- WEKA; Organizational learning -- Periodicals; Knowledge management -- Periodicals; Business intelligence -- Periodicals; Business enterprises -- Design -- Periodicals; Organizational effectiveness -- Periodicals; 658.005
• Languages: English
• ISSNs: 1745-3232

Abstract

An unreasonable increase of glucose in blood results in diabetes. In recent times this problem is often seen in many people around the world. Having an efficient medical diagnosis of diabetic prevention is essential. In this context, healthcare professionals have come up with different solutions, but none of them have taken shape. Considering these facts, we have proposed an integrated diabetic prediction system with the inclusions of un-supervised K-means clustering and naive Bayes classification. In this context, random attribute selection is used as the initial centroid selection method for K-means clustering. Significant work is compared with traditional classification algorithms like naive Bayes, SVM, etc., in terms of accuracy along with additional performance parameters like sensitivity, specificity, precision, and F-measure. As a result, it is determined that the proposed algorithm with 99.42%, which is higher than any other recently proposed classification technique, is achieved.