A0604
Title: Self-consistent equation-guided neural networks for censored time-to-event data
Authors: Sehwan Kim - Ewha Womans University (Korea, South) [presenting]
Rui Wang - Harvard Pilgrim Health Care (United States)
Wenbin Lu - North Carolina State University (United States)
Abstract: In survival analysis, estimating the conditional survival function given predictors is often of interest. There is a growing trend in the development of deep learning methods for analyzing censored time-to-event data, especially when dealing with high-dimensional predictors that are complexly interrelated. Many existing deep learning approaches for estimating the conditional survival functions extend the Cox regression models by replacing the linear function of predictor effects by a shallow feed-forward neural network while maintaining the proportional hazards assumption. Their implementation can be computationally intensive due to the use of the full dataset at each iteration, because the use of batch data may distort the at-risk set of the partial likelihood function. To overcome these limitations, a novel deep learning approach is proposed for non-parametric estimation of the conditional survival functions using the generative adversarial networks, leveraging self-consistent equations. The proposed method is model-free and does not require any parametric assumptions on the structure of the conditional survival function. The convergence rate of the proposed estimator of the conditional survival function is established. In addition, the performance of the proposed method is evaluated through simulation studies, and its application on a real-world dataset is demonstrated.
