Work

BoXHED2.0: Scalable Boosting of Dynamic Survival Analysis

Year: 2025

Type: article

Abstract: Modern applications of survival analysis increasingly involve time-dependent covariates.The Python package BoXHED2.0 (Boosted eXact Hazard Estimator with Dynamic covariates) is a tree-boosted hazard estimator that is fully nonparametric, and is applicable to survival settings far more general than right-censoring, including recurring events and competing risks. BoXHED2.0 is also scalable to the point of being on the same order of speed as parametric boosted survival models, in part because its core is written in C++ and it also supports the use of GPUs and multicore CPUs. BoXHED2.0 is available from PyPI and also from https://github.com/BoXHED.

Source: Journal of Statistical Software

DOI: 10.18637/jss.v113.i03

Authors: Arash Pakbin, Xiaochen Wang, Bobak J. Mortazavi, Donald K. K. Lee

Institutions: Texas A&M University, Yale University, Emory University

Language: English

Topic: Statistical Methods and Inference

Subfield: Statistics and Probability

Field: Mathematics

Domain: Physical Sciences

Open Access status: diamond

Funders: National Heart, Lung, and Blood Institute, National Institute of Biomedical Imaging and Bioengineering

Awards: G352855462, G516154015