Affiliation:
1. Department of Biostatistics, School of Public Health, University of Michigan, Ann Arbor, MI 48105, USA
Abstract
Abstract
Summary
Restricted mean survival time (RMST) is a useful summary measurement of the time-to-event data, and it has attracted great attention for its straightforward clinical interpretation. In this article, I propose a deep neural network model that directly relates the RMST to its baseline covariates for simultaneous prediction of RSMT at multiple times. Each subject’s survival time is transformed into a series of jackknife pseudo observations and then used as quantitative response variables in a deep neural network model. By using the pseudo values, a complex survival analysis is reduced to a standard regression problem, which greatly simplifies the neural network construction. By jointly modeling RMST at multiple times, the neural network model gains prediction accuracy by information sharing across times. The proposed network model was evaluated by extensive simulation studies and was further illustrated on three real datasets. In real data analyses, I also used methods to open the blackbox by identifying subject-specific predictors and their importance in contributing to the risk prediction.
Availability and implementation
The source code is freely available at http://github.com/lilizhaoUM/DnnRMST.
Supplementary information
Supplementary data are available at Bioinformatics online.
Funder
National Heart, Lung, and Blood Institute
NHLBI
The Nephrotic Syndrome Study Network Consortium
National Institutes of Health
Rare Disease Clinical Research Network
National Institute of Diabetes, Digestive, and Kidney Diseases
NephCure Kidney International
Halpin Foundation
Organ Procurement and Transplantation Network
Michigan Institute for Clinical and Health Research
Publisher
Oxford University Press (OUP)
Subject
Computational Mathematics,Computational Theory and Mathematics,Computer Science Applications,Molecular Biology,Biochemistry,Statistics and Probability
Reference40 articles.
1. TensorFlow: Large-scale machine learning on heterogeneous systems. Software available from tensorflow.org;Abadi,2015
2. Pseudo-observations in survival analysis;Andersen;Stat. Methods Med. Res,2010
3. Generalised linear models for correlated pseudo-observations, with applications to multistate models;Andersen;Biometrika,2003
4. Regression analysis of restricted mean survival time based on pseudo-observations;Andersen;Lifetime Data Anal,2004
5. Random search for hyper-parameter optimization;Bergstra;J. Mach. Learn. Res,2012
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献