DNNSurv: Deep Neural Networks for Survival Analysis Using Pseudo Values
This method addresses survival data modeling for medical researchers, offering a simplified and flexible approach, though it appears incremental as it builds on existing deep learning methods with a novel transformation step.
The paper tackles survival analysis in medical research by proposing a two-step method that transforms survival times into pseudo conditional survival probabilities, simplifying neural network construction. The approach is flexible for risk predictions and the source code is freely available.
There has been increasing interest in modelling survival data using deep learning methods in medical research. Current approaches have focused on designing special cost functions to handle censored survival data. We propose a very different method with two steps. In the first step, we transform each subject's survival time into a series of jackknife pseudo conditional survival probabilities and then use these pseudo probabilities as a quantitative response variable in the deep neural network model. By using the pseudo values, we reduce a complex survival analysis to a standard regression problem, which greatly simplifies the neural network construction. Our two-step approach is simple, yet very flexible in making risk predictions for survival data, which is very appealing from the practice point of view. The source code is freely available at http://github.com/lilizhaoUM/DNNSurv.