Self-Consistent Equation-guided Neural Networks for Interval Censored Time-to-Event Data

The code includes the implementation of the Self-Consistent Equation-guided Neural Networks for Interval-Censored data (SCENIC) by Lee Ding, Sehwan Kim, Rui Wang and Wenbin Lu. We propose a novel deep learning approach to non-parametric estimation of the conditional survival functions using the generative adversarial networks leveraging self-consistent equations for interval-censored data. The proposed method is model-free and does not require any parametric assumptions on the structure of the conditional survival function.