Neural interval-censored survival regression with feature selection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Meixide, Carlos García, Matabuena, Marcos, Abraham, Louis, Kosorok, Michael R.
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909293127663616
author Meixide, Carlos García
Matabuena, Marcos
Abraham, Louis
Kosorok, Michael R.
author_facet Meixide, Carlos García
Matabuena, Marcos
Abraham, Louis
Kosorok, Michael R.
contents Survival analysis is a fundamental area of focus in biomedical research, particularly in the context of personalized medicine. This prominence is due to the increasing prevalence of large and high-dimensional datasets, such as omics and medical image data. However, the literature on non-linear regression algorithms and variable selection techniques for interval-censoring is either limited or non-existent, particularly in the context of neural networks. Our objective is to introduce a novel predictive framework tailored for interval-censored regression tasks, rooted in Accelerated Failure Time (AFT) models. Our strategy comprises two key components: i) a variable selection phase leveraging recent advances on sparse neural network architectures, ii) a regression model targeting prediction of the interval-censored response. To assess the performance of our novel algorithm, we conducted a comprehensive evaluation through both numerical experiments and real-world applications that encompass scenarios related to diabetes and physical activity. Our results outperform traditional AFT algorithms, particularly in scenarios featuring non-linear relationships.
format Preprint
id arxiv_https___arxiv_org_abs_2206_06885
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Neural interval-censored survival regression with feature selection
Meixide, Carlos García
Matabuena, Marcos
Abraham, Louis
Kosorok, Michael R.
Machine Learning
Methodology
Survival analysis is a fundamental area of focus in biomedical research, particularly in the context of personalized medicine. This prominence is due to the increasing prevalence of large and high-dimensional datasets, such as omics and medical image data. However, the literature on non-linear regression algorithms and variable selection techniques for interval-censoring is either limited or non-existent, particularly in the context of neural networks. Our objective is to introduce a novel predictive framework tailored for interval-censored regression tasks, rooted in Accelerated Failure Time (AFT) models. Our strategy comprises two key components: i) a variable selection phase leveraging recent advances on sparse neural network architectures, ii) a regression model targeting prediction of the interval-censored response. To assess the performance of our novel algorithm, we conducted a comprehensive evaluation through both numerical experiments and real-world applications that encompass scenarios related to diabetes and physical activity. Our results outperform traditional AFT algorithms, particularly in scenarios featuring non-linear relationships.
title Neural interval-censored survival regression with feature selection
topic Machine Learning
Methodology
url https://arxiv.org/abs/2206.06885