手法を比較

	DeepSurv	Cox比例ハザード回帰	ワイブル生存回帰 (Weibull Parametric Survival Regression)
分野	生存時間解析	生存時間解析	生存時間解析
系統	Survival analysis	Survival analysis	Survival analysis
提唱年	2018	1972	1951
提唱者	Jared Katzman	Cox, D. R.	Waloddi Weibull
種類	Neural network-based survival model	Semi-parametric hazard regression model	Fully parametric survival regression model
原典	Faraggi, D., & Simon, R. (1995). A neural network model for survival data. Statistics in Medicine, 14(1), 73–82.	Cox, D. R. (1972). Regression Models and Life-Tables. Journal of the Royal Statistical Society: Series B, 34(2), 187–202.	Kalbfleisch, J. D. & Prentice, R. L. (2002). The Statistical Analysis of Failure Time Data (2nd ed.). Wiley.
別名	Neural network survival, DL survival model	cox ph model, proportional hazards model, cox ph regression, Cox Orantılı Tehlikeler Regresyonu	weibull aft model, weibull survival model, parametric survival regression, Weibull Regresyonu — Parametrik Hayatta Kalma
関連	3	3	4
概要	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.	Cox proportional hazards regression, introduced by D. R. Cox in 1972, is a semi-parametric model that estimates how one or more covariates affect the hazard — the instantaneous rate of experiencing an event — while leaving the baseline hazard function unspecified. It is the standard multivariable method in survival analysis and produces hazard ratios that quantify the relative risk associated with each predictor.	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.