Title: Early knowledge-driven prognostic reasoning model using effective data analytics approach

Authors: Rithesh Pakkala PermankiGuthu; Shamantha Rai Bellipady; Srinidhi Rai; Tirthal Rai

Addresses: Sahyadri College of Engineering and Management, Mangaluru, Karnataka, India; Affiliated to: Visvesvaraya Technological University, Belagavi, Karnataka, India ' Sahyadri College of Engineering and Management, Mangaluru, Karnataka, India; Affiliated to: Visvesvaraya Technological University, Belagavi, Karnataka, India ' KS Hegde Medical Academy, NITTE (Deemed to be University), Mangaluru, Karnataka, India ' KS Hegde Medical Academy, NITTE (Deemed to be University), Mangaluru, Karnataka, India

Abstract: Diabetes is a lifestyle disorder. The accomplishment of early knowledge of diabetes can enhance the treatment effectiveness. Data analytics techniques are widely used to gain early knowledge of the disease. In this research, the prognostic reasoning model is designed to identify the significant features that lead to the detection of early knowledge on diabetes using an effective data analytics approach. For the analysis of diabetic knowledge, different classifiers, namely decision tree, support vector machine, neural network, and random forest are used. The experiment depicts that random forest performs superior to other classifiers in the early prediction of diabetes with an accuracy of 96% and thus may be valuable in assisting doctors in making patient care.

Keywords: early knowledge; prognostic reasoning; data analytics; diabetes.

DOI: 10.1504/IJMEI.2023.132605

International Journal of Medical Engineering and Informatics, 2023 Vol.15 No.4, pp.389 - 401

Received: 12 Feb 2021
Accepted: 05 Jun 2021
Published online: 30 Jul 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article