Title: Hybrid framework using data mining techniques for early detection and prevention of oral cancer

Authors: Neha Sharma; Hari Om

Addresses: Zeal Institute of Business Administration, Computer Application and Research, Savitribai Phule Pune University, Maharashtra, India ' Computer Science and Engineering Department, Indian School of Mines, Dhanbad, Jharkhand, India

Abstract: This paper presents the usage of classification and association data mining techniques for early detection and prevention of oral cancer. The indigenous dataset of 1,025 patients who visited a tertiary care centre during 2004 to 2009 was used for the research. Ten classification data mining models are designed using varied types of data mining techniques like regression analysis, classification trees and neural networks. Regression analysis models are linear regression model and logistic regression model; classification tree models are decision tree model, decision tree forest model and TreeBoost model and artificial neural networks are multilayer perceptron model, radial basis function model, group method of data handling model, cascade correlation model and probabilistic - general regression neural network model. Association rules are generated using apriori algorithm. The classification models and association rules are evaluated using various estimation parameters. Finally, a hybrid oral cancer management system is designed using the classification model and the association rules.

Keywords: oral cancer; regression analysis; linear regression; logistic regression; decision tree; decision tree forest; TreeBoost; artificial neural networks; multilayer perceptron; radial basis function; group method of data handling; GMDH; cascade correlationl probabilistic - general regression neural network; apriori; association rule mining.

DOI: 10.1504/IJAIP.2017.088153

International Journal of Advanced Intelligence Paradigms, 2017 Vol.9 No.5/6, pp.604 - 622

Received: 24 Sep 2015
Accepted: 04 Nov 2015
Published online: 27 Nov 2017 *

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