Adversarial time-to-event modeling

Published

Journal Article

© 2018 by the Authors. All rights reserved. Modern health data science applications leverage abundant molecular and electronic health data; providing opportunities for machine learning to build statistical models to support clinical practice. Time-to-event analysis, also called survival analysis, stands as one of the most representative examples of such statistical models. We present a deep-network-based approach that leverages ad-versarial learning to address a key challenge in modern time-to-event modeling: nonparametric estimation of event-time distributions. We also introduce a principled cost function to exploit in-formation from censored events (events that occur subsequent to the observation window). Unlike most time-to-event models, we focus on the estimation of time-to-event distributions, rather than time ordering. We validate our model on both benchmark and real datasets, demonstrating that the proposed formulation yields significant performance gains relative to a parametric alternative, which we also propose.

Duke Authors

Cited Authors

  • Chapfuwa, P; Tao, C; Li, C; Page, C; Goldstein, B; Carin, L; Henao, R

Published Date

  • January 1, 2018

Published In

  • 35th International Conference on Machine Learning, Icml 2018

Volume / Issue

  • 2 /

Start / End Page

  • 1143 - 1156

Citation Source

  • Scopus