Fig. 1
From: Bayesian parametric models for survival prediction in medical applications
Overview of Bayesian approach to survival prediction. a data pipeline with tabular input, Bayesian model for survival times, and individualized survival prediction with uncertainty; b Intrinsic properties of Bayesian models that are essential in medical applications: Regularization through non-informative priors, model updating using Bayes rule through informative priors from previous model, estimation of uncertainty through full posterior probability distributions of each parameter