A novel approach to cancer staging: Application to esophageal cancer

Hemant Ishwaran, Eugene H. Blackstone, Carolyn Apperson-Hansen, Thomas W. Rice

Research output: Contribution to journalArticle

52 Scopus citations

Abstract

A novel 3-step random forests methodology involving survival data (survival forests), ordinal data (multiclass forests), and continuous data (regression forests) is introduced for cancer staging. The methodology is illustrated for esophageal cancer using worldwide esophageal cancer collaboration data involving 4627 patients.

Original languageEnglish (US)
Pages (from-to)603-620
Number of pages18
JournalBiostatistics
Volume10
Issue number4
DOIs
StatePublished - Oct 1 2009
Externally publishedYes

    Fingerprint

Keywords

  • Predicted survival
  • Random forests
  • Survival curves
  • TNM

ASJC Scopus subject areas

  • Medicine(all)
  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this