KMID : 1155220090340010073
|
|
Journal of the Korean Society of Health Information and Health Statistics 2009 Volume.34 No. 1 p.73 ~ p.86
|
|
Tree Structured Prognostic Survival Model for Hepatocellular Carcinoma using Gene Expression Data
|
|
Lee Tae-Rim
Lee Hyo-Suk
|
|
Abstract
|
|
|
A tree-structured method for analyzing censored survival data is attractive for several reasons. The association between survival time and covariates is easy to interpret even if the covariates are numerous and there are interactions among them. Moreover a tree-structured method using gene expression data gives additional insight into the role of the covariates. Recent SNP data analysis makes it possible to find out large numbers of gene related with human cancers and to support accurate diagnosis of human cancers according to their several pathological judgements. The purpose of this study was designed to evaluate the prognosis of HCC in relation to treatment methods and their affecting gene and clinical factors by tree structured model. We could identify a feature set of 44 genes to distinguish the status of HCC and non-tumor liver tissues. Our proposed survival tree model shows the genes related with clinical, pathological data and risk factors of HCC. These findings could be available to predict prognosis of HCC and give valuable information to justify the treatment strategy for clinician.
|
|
KEYWORD
|
|
Hepatocellular Carcinoma, Snp Data, Tree Structured Survival Model
|
|
FullTexts / Linksout information
|
|
|
|
Listed journal information
|
|
|