方法对比

	DeepSurv	加速失效时间 (AFT) 模型	威布尔参数生存回归
领域	生存分析	生存分析	生存分析
方法族	Survival analysis	Survival analysis	Survival analysis
起源年份	2018	1992	1951
提出者	Jared Katzman	Wei, L. J. (seminal review 1992); origins in parametric survival literature	Waloddi Weibull
类型	Neural network-based survival model	Parametric survival regression model	Fully parametric survival regression model
开创性文献	Faraggi, D., & Simon, R. (1995). A neural network model for survival data. Statistics in Medicine, 14(1), 73–82.	Wei, L. J. (1992). The Accelerated Failure Time Model: A Useful Alternative to the Cox Regression Model in Survival Analysis. Statistics in Medicine, 11(14–15), 1871–1879.	Kalbfleisch, J. D. & Prentice, R. L. (2002). The Statistical Analysis of Failure Time Data (2nd ed.). Wiley.
别名	Neural network survival, DL survival model	AFT model, parametric survival regression, Hızlandırılmış Başarısızlık Zamanı Modeli (AFT)	weibull aft model, weibull survival model, parametric survival regression, Weibull Regresyonu — Parametrik Hayatta Kalma
相关	3	3	4
摘要	DeepSurv is a deep neural network approach to survival analysis that learns personalized survival distributions directly from data. Introduced by Katzman et al. in 2018, it extends the Cox proportional hazards model using deep learning to capture complex, nonlinear relationships between covariates and survival outcomes. It solves the problem of modeling heterogeneous treatment effects and time-to-event predictions in high-dimensional settings.	The Accelerated Failure Time model is a parametric regression approach to survival analysis — formally reviewed and advocated by L. J. Wei in 1992 — in which covariates act as multiplicative factors that directly stretch or compress the time-to-event scale. Unlike the Cox proportional-hazards model, which models how covariates shift the hazard rate, AFT models express the covariate effect as an acceleration or deceleration of the time axis itself.	Weibull regression is a fully parametric survival model, formalised by Kalbfleisch and Prentice, that assumes survival times follow a Weibull distribution. A shape parameter controls whether the hazard increases, decreases, or remains constant over time, while covariates shift the scale of the distribution to express how predictors affect survival.