Predicting Time-to-Relapse in Breast Cancer Using Neural Networks.
Abstract
Neural networks (NN) have become established as powerful tools for complex pattern recognition problems. One application which appears well suited to NN methods is the identification of prognostic groups, to be used for treatment planning. For many cancer studies of cancer cell biology have added many factors of potential prognostic value, but the way in which these interact with known factors is generally not well studied. The potential of NNs to model these data in a non-linear fashion has only begun to be explored. NNs are not part of standard statistical packages, making them relatively inaccessible to many statisticians. More importantly, current NN methods cannot accommodate censored outcome variables. This proposal is for application of several proposed methods for applying NNs to censored-data to the problem of predicting time-to-relapse for breast cancer patients. The methods will be evaluation in comparison to each other, and also to more conventional approaches such as Cox regression and recursive partitioning. The data on which the analyses will be conducted comes from the database of the NSABP.
Document Details
- Document Type
- Technical Report
- Publication Date
- Oct 01, 1995
- Accession Number
- ADA300396
Entities
People
- Jonathan D. Buckley
Organizations
- University of Southern California