Theory and software for boosted nonparametric hazard estimation

Donald Lee, Ningyuan Chen, Hemant Ishwaran, Xiaochen Wang, Arash Pakbin, Bobak Mortazavi, Hongyu Zhao
Proceedings of AAAI Spring Symposium on Survival Prediction - Algorithms, Challenges, and Applications 2021, PMLR 146:149-158, 2021.

Abstract

Nonparametric approaches for analyzing survival data in the presence of time-dependent covariates is a timely topic, given the availability of high frequency data capture systems in healthcare and beyond. We present a theoretically justified gradient boosted hazard estimator for this setting, and describe a tree-based implementation called BoXHED (pronounced ‘box-head’) that is available from GitHub:www.github.com/BoXHED. Our numerical study demonstrates that there is a place in the machine learning toolbox for a nonparametric method like BoXHED that can flexibly handle time-dependent covariates. The results presented here are distilled from the recent works of Lee et al. (2021) and Wang et al. (2020).

Cite this Paper

BibTeX
@InProceedings{pmlr-v146-lee21a, title = {Theory and software for boosted nonparametric hazard estimation}, author = {Lee, Donald and Chen, Ningyuan and Ishwaran, Hemant and Wang, Xiaochen and Pakbin, Arash and Mortazavi, Bobak and Zhao, Hongyu}, booktitle = {Proceedings of AAAI Spring Symposium on Survival Prediction - Algorithms, Challenges, and Applications 2021}, pages = {149--158}, year = {2021}, editor = {Greiner, Russell and Kumar, Neeraj and Gerds, Thomas Alexander and van der Schaar, Mihaela}, volume = {146}, series = {Proceedings of Machine Learning Research}, month = {22--24 Mar}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v146/lee21a/lee21a.pdf}, url = {https://proceedings.mlr.press/v146/lee21a.html}, abstract = {Nonparametric approaches for analyzing survival data in the presence of time-dependent covariates is a timely topic, given the availability of high frequency data capture systems in healthcare and beyond. We present a theoretically justified gradient boosted hazard estimator for this setting, and describe a tree-based implementation called BoXHED (pronounced ‘box-head’) that is available from GitHub:www.github.com/BoXHED. Our numerical study demonstrates that there is a place in the machine learning toolbox for a nonparametric method like BoXHED that can flexibly handle time-dependent covariates. The results presented here are distilled from the recent works of Lee et al. (2021) and Wang et al. (2020).} }
Endnote
%0 Conference Paper %T Theory and software for boosted nonparametric hazard estimation %A Donald Lee %A Ningyuan Chen %A Hemant Ishwaran %A Xiaochen Wang %A Arash Pakbin %A Bobak Mortazavi %A Hongyu Zhao %B Proceedings of AAAI Spring Symposium on Survival Prediction - Algorithms, Challenges, and Applications 2021 %C Proceedings of Machine Learning Research %D 2021 %E Russell Greiner %E Neeraj Kumar %E Thomas Alexander Gerds %E Mihaela van der Schaar %F pmlr-v146-lee21a %I PMLR %P 149--158 %U https://proceedings.mlr.press/v146/lee21a.html %V 146 %X Nonparametric approaches for analyzing survival data in the presence of time-dependent covariates is a timely topic, given the availability of high frequency data capture systems in healthcare and beyond. We present a theoretically justified gradient boosted hazard estimator for this setting, and describe a tree-based implementation called BoXHED (pronounced ‘box-head’) that is available from GitHub:www.github.com/BoXHED. Our numerical study demonstrates that there is a place in the machine learning toolbox for a nonparametric method like BoXHED that can flexibly handle time-dependent covariates. The results presented here are distilled from the recent works of Lee et al. (2021) and Wang et al. (2020).
APA
Lee, D., Chen, N., Ishwaran, H., Wang, X., Pakbin, A., Mortazavi, B. & Zhao, H.. (2021). Theory and software for boosted nonparametric hazard estimation. Proceedings of AAAI Spring Symposium on Survival Prediction - Algorithms, Challenges, and Applications 2021, in Proceedings of Machine Learning Research 146:149-158 Available from https://proceedings.mlr.press/v146/lee21a.html.

Related Material