High-dimensional, massive sample-size Cox proportional hazards regression for survival analysis

Authors

Sushil Mittal, Columbia University in the City of New York
David Madigan, Columbia University in the City of New York
Randall S. Burd, Childrens National Health System
Marc A. Suchard, David Geffen School of Medicine at UCLA

Document Type

Journal Article

Publication Date

4-1-2014

Journal

Biostatistics

Volume

15

Issue

2

DOI

10.1093/biostatistics/kxt043

Keywords

Big data; Cox proportional hazards; Regularized regression; Survival analysis

Abstract

Survival analysis endures as an old, yet active research field with applications that spread across many domains. Continuing improvements in data acquisition techniques pose constant challenges in applying existing survival analysis methods to these emerging data sets. In this paper, we present tools for fitting regularized Cox survival analysis models on high-dimensional, massive sample-size (HDMSS) data using a variant of the cyclic coordinate descent optimization technique tailored for the sparsity that HDMSS data often present. Experiments on two real data examples demonstrate that efficient analyses of HDMSS data using these tools result in improved predictive performance and calibration. © 2013 The Author 2013.

APA Citation

Mittal, S., Madigan, D., Burd, R., & Suchard, M. (2014). High-dimensional, massive sample-size Cox proportional hazards regression for survival analysis. Biostatistics, 15 (2). http://dx.doi.org/10.1093/biostatistics/kxt043