Survival analysis via transduction for semi-supervised neural networks in medical prognosis

Faisal M. Khan, Casimir A. Kulikowski

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Scopus citations

Abstract

The central challenge in predictive modeling for survival analysis in medical prognostics is managing censored observations. Traditional regression techniques are challenged by these censored samples. In such problems the true target times of a majority of instances are unknown; what is known is a censored target representing some earlier indeterminate time. Such censored samples can be considered as semi-supervised targets; however most efforts in semi-supervised regression do not take into account the partial nature of unsupervised information; samples are treated as either fully labelled or unlabeled. In this work we extend a novel transduction approach for semi-supervised survival analysis to neural networks. The true target times are approximated from the censored times through transduction. For prostate and breast cancer applications, this semi-supervised regression framework yields a significant improvement in performance.

Original languageEnglish (US)
Title of host publicationProceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015
Editorslng. Matthieu Schapranow, Jiayu Zhou, Xiaohua Tony Hu, Bin Ma, Sanguthevar Rajasekaran, Satoru Miyano, Illhoi Yoo, Brian Pierce, Amarda Shehu, Vijay K. Gombar, Brian Chen, Vinay Pai, Jun Huan
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages433-437
Number of pages5
ISBN (Electronic)9781467367981
DOIs
StatePublished - Dec 16 2015
EventIEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015 - Washington, United States
Duration: Nov 9 2015Nov 12 2015

Publication series

NameProceedings - 2015 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015

Other

OtherIEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015
Country/TerritoryUnited States
CityWashington
Period11/9/1511/12/15

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Health Informatics
  • Biomedical Engineering

Keywords

  • cancer prognosis
  • neural networks
  • regression
  • semi-supervised
  • survival analysis
  • transduction

Fingerprint

Dive into the research topics of 'Survival analysis via transduction for semi-supervised neural networks in medical prognosis'. Together they form a unique fingerprint.

Cite this