论文标题
深层生存分析：条件生存功能的非参数估计
Deep Generative Survival Analysis: Nonparametric Estimation of Conditional Survival Function
论文作者
论文摘要
我们提出了一种深入的生成方法，用于对条件生存和危害功能的非参数估计，并使用右审查的数据进行危害函数。提出方法的关键思想是首先学习一个条件发生器，以鉴于协变量，观察到的时间和检查指标的联合条件分布，然后基于该条件发生器的条件危险和存活函数构建Kaplan-Meier和Nelson-Aalen估计器。我们的方法结合了最近开发的深层生成学习和经典非参数估计的思想。我们分析了所提出的方法的收敛特性，并建立了条件生存和危害功能的生成非参数估计量的一致性。我们的数值实验验证了所提出的方法，并在一系列模型中证明了其出色的性能。我们还说明了所提出的方法在用PBC（原发性胆道炎）和支持（了解预后和治疗风险的预后和偏好的研究）数据集中构建生存时间的预测间隔时的应用。
We propose a deep generative approach to nonparametric estimation of conditional survival and hazard functions with right-censored data. The key idea of the proposed method is to first learn a conditional generator for the joint conditional distribution of the observed time and censoring indicator given the covariates, and then construct the Kaplan-Meier and Nelson-Aalen estimators based on this conditional generator for the conditional hazard and survival functions. Our method combines ideas from the recently developed deep generative learning and classical nonparametric estimation in survival analysis. We analyze the convergence properties of the proposed method and establish the consistency of the generative nonparametric estimators of the conditional survival and hazard functions. Our numerical experiments validate the proposed method and demonstrate its superior performance in a range of simulated models. We also illustrate the applications of the proposed method in constructing prediction intervals for survival times with the PBC (Primary Biliary Cholangitis) and SUPPORT (Study to Understand Prognoses and Preferences for Outcomes and Risks of Treatments) datasets.
