Survival analysis of censored data: Neural network analysis detection of complex interactions between variables

Michele De Laurentiis, Peter M. Ravdin

Research output: Contribution to journalArticlepeer-review

Abstract

Neural networks can be used as pattern recognition systems in complex data sets. We are exploring their utility in performing survival analysis to predict time to relapse or death. This technique has the potential to find easily some types of very complex interactions in data that would not be easily recognized by conventional statistical methods. In this paper we demonstrate that there are several ways neural networks can be used to find three-way interactions among variables. Thus, in data sets where such complex interactions exist, neural networks may find utility in detecting such interactions and in helping to produce predictive models.

Original languageEnglish
Pages (from-to)113-118
Number of pages6
JournalBreast Cancer Research and Treatment
Volume32
Issue number1
DOIs
Publication statusPublished - Jan 1994

Keywords

  • axillary nodal status
  • breast cancer
  • neural networks
  • prognostic markers
  • staging
  • survival analysis

ASJC Scopus subject areas

  • Oncology
  • Cancer Research

Fingerprint Dive into the research topics of 'Survival analysis of censored data: Neural network analysis detection of complex interactions between variables'. Together they form a unique fingerprint.

Cite this