A genetic programming approach to oral cancer prognosis.

Mei Sze Tan,Sameem Abdul Kareem,Jing Wei Tan,Hwa Jen Yap,Siow-Wee Chang,Rosnah Binti Zain

doi:10.7717/peerj.2482

Abstract

BackgroundThe potential of genetic programming (GP) on various fields has been attained in recent years. In bio-medical field, many researches in GP are focused on the recognition of cancerous cells and also on gene expression profiling data. In this research, the aim is to study the performance of GP on the survival prediction of a small sample size of oral cancer prognosis dataset, which is the first study in the field of oral cancer prognosis.MethodGP is applied on an oral cancer dataset that contains 31 cases collected from the Malaysia Oral Cancer Database and Tissue Bank System (MOCDTBS). The feature subsets that is automatically selected through GP were noted and the influences of this subset on the results of GP were recorded. In addition, a comparison between the GP performance and that of the Support Vector Machine (SVM) and logistic regression (LR) are also done in order to verify the predictive capabilities of the GP.ResultThe result shows that GP performed the best (average accuracy of 83.87% and average AUROC of 0.8341) when the features selected are smoking, drinking, chewing, histological differentiation of SCC, and oncogene p63. In addition, based on the comparison results, we found that the GP outperformed the SVM and LR in oral cancer prognosis.DiscussionSome of the features in the dataset are found to be statistically co-related. This is because the accuracy of the GP prediction drops when one of the feature in the best feature subset is excluded. Thus, GP provides an automatic feature selection function, which chooses features that are highly correlated to the prognosis of oral cancer. This makes GP an ideal prediction model for cancer clinical and genomic data that can be used to aid physicians in their decision making stage of diagnosis or prognosis.

Highlights

Oral cancer, commonly known as mouth cancer, is the abnormal growth of cells found in the different regions of the mouth including the tongue, floor of the mouth, buccal mucosaHow to cite this article Tan et al (2016), A genetic programming approach to oral cancer prognosis
The genetic programming (GP) was tested for 20 times using all the features in the dataset and the frequency of the feature selected in 20 runs was calculated
Higher frequency of features selected by GP in 20 runs indicates that the features hold a more important rank in the prediction compared to the others

Summary

Introduction

Commonly known as mouth cancer, is the abnormal growth of cells found in the different regions of the mouth including the tongue, floor of the mouth, buccal mucosaHow to cite this article Tan et al (2016), A genetic programming approach to oral cancer prognosis. GP provides an automatic feature selection function, which chooses features that are highly correlated to the prognosis of oral cancer. This makes GP an ideal prediction model for cancer clinical and genomic data that can be used to aid physicians in their decision making stage of diagnosis or prognosis. According to Koza, GP reformulated the process of solving the problems of other machine learning methods by searching a highly fit individual program in a population of candidate programs. This space of searching consists of many functions and terminals, relevant to the problem domain.

Objectives

Methods

Results

Conclusion