Diagnosis of pancreatic cancer by pattern recognition methods using gene expression profiles

Abstract

Pancreatic cancer is the fourth most common cause of cancer-related deaths across the globe and it is one of the most difficult cancer types to recognize early. Early diagnosis of pancreatic cancer is crucial to increase survival for patients. In this study, it was tried to be estimated that persons were pancreatic cancer or healthy using microarray gene expression profile. In accordance with this purpose, Anova method was used to reduce the size of high-dimensional pancreatic cancer gene expression profile and eliminate redundant features. Reduced-size pancreas cancer gene expression profiles were classified by k-nearest neighbor (k-NN) and artificial neural network (ANN) algorithms. The classification accuracy is %82.7 and 84.6% with k-NN, ANN respectively. The promising results indicate that pancreatic cancer can be diagnosed with high accuracy.