Material Information

Survival Prediction of Breast Cancer Patient from Gene Methylation Data with Deep LSTM Network and Ordinal Cox model
Guanghui Liu
Chris Bartlett
Isabelle Bichindaritz
Publication Date:


Subjects / Keywords:


Survival analysis has currently become a hot topic because it has been proven to be useful for understanding the relationships between patients’ variables and covariates (e.g. clinical and genetic features) and the effectiveness of various treatment options. In this study, we study survival analysis of breast cancer patient with gene methylation data and clinical data. We propose a novel method for survival prediction using bidirectional LSTM network and ordinal Cox model. First, gene methylation expression data and clinical data are merged and filtered. To reduce the gene expression features dimension, a weighted gene co-expression network analysis (WGCNA) algorithm is used to obtain cluster eigengenes. Then, the eigengenes serve as input features for a machine learning network. We build a cox proportional hazards model for survival analysis and use LSTM method to predict patient survival risk. We use the leave-one-out method for cross validation and the concordance index (C-index) to evaluate the prediction performance. Stringent cross-validation tests on the benchmark dataset demonstrates the efficacy of the proposed method, which achieves very competitive performance with existing state-of-the-art methods.
Collected for SUNY Oswego Institutional Repository by the online self-submittal tool. Submitted by Isabelle Bichindaritz.

Record Information

Source Institution:
SUNY Oswego Institutional Repository
Holding Location:
SUNY Oswego Institution
Rights Management:
All applicable rights reserved by the source institution and holding location.