EUVIMEDDescubrir EUVIMED
Crossref

A DNN‐Based Weighted Partial Likelihood for Partially Linear Subdistribution Hazard Model

Nengjie Zhu iD, Zhangsheng Yu iD

Statistics in Medicine · 2026

DOI: 10.1002/sim.70397 ↗

At a glance

Journal article in Statistics in Medicine, 2026. Written by Nengjie Zhu and 1 co-authors. Institution: Department of Statistics, Shanghai Jiao Tong University, Shanghai, China. Major MEDLINE topics: Deep Learning, Neural Networks, Computer. 34 references. Funded by: National Natural Science Foundation of China, Shanghai Science and Technology Commission, Medical Engineering Cross Fund of Shanghai Jiao Tong University.

ResumenSubjectsDatos bibliográficosCiteRelated studies

Abstract (original language)

Deep learning has excelled in the field of statistical learning. In the field of survival analysis, some studies have combined deep learning methods with partially linear structures to propose deep partially linear structures. We extend it to the field of competing risks and propose the deep partially linear subdistribution hazard model (DPLSHM). To evaluate the predictive performance of the model, we further develop a time‐dependent AUC method specifically tailored for competing risks data and provide an estimator for AUC. Theoretical results for the proposed model demonstrate the asymptotic normality of the parameter component at a rate of and provide the convergence rate of the nonparametric component, which achieves the minimal limit convergence rate (multiplicative logarithmic factors). The theory of consistency and rate of convergence of AUC‐related estimates is also developed, while we prove that the regression component of DPLSHM maximizes theoretical AUC asymptotically. Subsequently, the paper validates the excellent performance of DPLSHM in estimation and prediction through numerical simulations and real‐world datasets.

Subjects

MeSH terms (MEDLINE)

Deep LearningNeural Networks, ComputerHumansLikelihood FunctionsComputer SimulationArea Under CurveProportional Hazards ModelsSurvival AnalysisLinear ModelsModels, Statistical

Author keywords

competing risksdeep learningsemi‐parametric modeltime‐dependent receiver operating characteristic

Authors and institutions

  • Department of Statistics, Shanghai Jiao Tong University, Shanghai, China.

ORCID profiles: Nengjie Zhu, Zhangsheng Yu

Funding

  • National Natural Science Foundation of China
  • Shanghai Science and Technology Commission
  • Medical Engineering Cross Fund of Shanghai Jiao Tong University

Cite

APA

Zhu, N., & Yu, Z. (2026). A DNN‐Based Weighted Partial Likelihood for Partially Linear Subdistribution Hazard Model. Statistics in Medicine. https://doi.org/10.1002/sim.70397

Vancouver

Zhu N, Yu Z. A DNN‐Based Weighted Partial Likelihood for Partially Linear Subdistribution Hazard Model. Statistics in Medicine. 2026. doi:10.1002/sim.70397

BibTeX
@article{Zhu2026,
  author = {Zhu, Nengjie and Yu, Zhangsheng},
  title = {A DNN‐Based Weighted Partial Likelihood for Partially Linear Subdistribution Hazard Model},
  journal = {Statistics in Medicine},
  year = {2026},
  doi = {10.1002/sim.70397}
}
Start for free →