Saved in:
Bibliographic Details
Main Authors: Safari, Abdollah, Halisaz, Hamed, Loewen, Peter
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.16687
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914323621740544
author Safari, Abdollah
Halisaz, Hamed
Loewen, Peter
author_facet Safari, Abdollah
Halisaz, Hamed
Loewen, Peter
contents We present biniLasso and its sparse variant (sparse biniLasso), novel methods for prognostic analysis of high-dimensional survival data that enable detection of multiple cut-points per feature. Our approach leverages the Cox proportional hazards model with two key innovations: (1) a cumulative binarization scheme with $L_1$-penalized coefficients operating on context-dependent cut-point candidates, and (2) for sparse biniLasso, additional uniLasso regularization to enforce sparsity while preserving univariate coefficient patterns. These innovations yield substantially improved interpretability, computational efficiency (4-11x faster than existing approaches), and prediction performance. Through extensive simulations, we demonstrate superior performance in cut-point detection, particularly in high-dimensional settings. Application to three genomic cancer datasets from TCGA confirms the methods' practical utility, with both variants showing enhanced risk prediction accuracy compared to conventional techniques.
format Preprint
id arxiv_https___arxiv_org_abs_2503_16687
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle biniLasso: Automated cut-point detection via sparse cumulative binarization
Safari, Abdollah
Halisaz, Hamed
Loewen, Peter
Methodology
We present biniLasso and its sparse variant (sparse biniLasso), novel methods for prognostic analysis of high-dimensional survival data that enable detection of multiple cut-points per feature. Our approach leverages the Cox proportional hazards model with two key innovations: (1) a cumulative binarization scheme with $L_1$-penalized coefficients operating on context-dependent cut-point candidates, and (2) for sparse biniLasso, additional uniLasso regularization to enforce sparsity while preserving univariate coefficient patterns. These innovations yield substantially improved interpretability, computational efficiency (4-11x faster than existing approaches), and prediction performance. Through extensive simulations, we demonstrate superior performance in cut-point detection, particularly in high-dimensional settings. Application to three genomic cancer datasets from TCGA confirms the methods' practical utility, with both variants showing enhanced risk prediction accuracy compared to conventional techniques.
title biniLasso: Automated cut-point detection via sparse cumulative binarization
topic Methodology
url https://arxiv.org/abs/2503.16687