Title: Diabetic deduction through non-parametric analysis

Authors: Gunasekar Thangarasu; P.D.D. Dominic

Addresses: Department of Computer and Information Science, Universiti Teknologi Petronas, Bandar Seri Iskandar, Tronoh Perak, Malaysia ' Department of Computer and Information Science, Universiti Teknologi Petronas, Bandar Seri Iskandar, Tronoh Perak, Malaysia

Abstract: Data mining has become one of the most valuable tools for extracting and manipulating data with established patterns in order to produce useful information for decision-making in medical diagnosis. It provides a convenient method of mining clinical databases which are too complex and uncertain. This research proposed combinations of four different data mining techniques, which are neural network, fuzzy logic, hybrid genetic algorithm and clustering techniques for predicting diabetes diseases, types and its various complications. Diabetes occurs when the body is unable to produce or respond properly to insulin which is needed to regulate glucose. Diabetes disease has increased the risks of developing kidney disease, blindness, nerve damage and blood vessel damage. The result of the research is focusing on diabetes disease diagnosis from the clinical database purely based on the people physical symptoms and their family history details. This innovative methodology help to increase the number of people saves from critical risks by early prediction of the diabetes disease and also this will be one of the best and cost effective diagnosing methods for the people.

Keywords: neural networks; fuzzy logic; hybrid genetic algorithms; clustering techniques; diabetic deduction; non-parametric analysis; data mining; decision making; medical diagnosis; clinical databases; diabetes prediction; diabetes diagnosis; early diagnosis; physical symptoms; family history.

DOI: 10.1504/IJBIS.2015.072252

International Journal of Business Information Systems, 2015 Vol.20 No.3, pp.325 - 347

Published online: 06 Oct 2015 *

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