Prediction of lymph node metastasis and perineural invasion of biliary tract cancer by selected features from cDNA array data 1

Abstract

To better understand the nature of the malignancy of biliary tract carcinoma and evaluate the feasibility of its prediction by gene expression profiles. We explored the gene expression profiles characteristic of progression and invasiveness in the cDNA array data obtained from 37 biliary tract carcinomas (15 bile duct, 11 gallbladder, 11 of ampulla of Vater). We pre-selected 51 and 100 genes for the presence versus absence of lymph node metastasis and perineural invasion on the basis of statistical difference. To search optimized sets of genes for prediction, we applied a sequential forward feature selection, minimizing leave-one-out error rates on a k-nearest neighbor classifier. We could predict lymph node metastasis and perineural invasion with an accuracy of 94 and 100%, respectively. When the 6-stage IA cancers without perineural invasion were precluded, a marked difference in gene expression (147 gene), discriminable with 100% accuracy, was noted between positive versus negative perineural invasion, suggesting that the acquisition of invasive character is rather a later molecular pathological event in biliary tract cancer. The present method provides a powerful means of classifying biliary tract carcinomas. We also suggest that perineural invasion is an important target of array databased pattern classification, which may predict patient outcomes and facilitate the determination of the extent of surgery to minimize the risk of recurrence.