Oral
Adversarial Time-to-Event Modeling
Paidamoyo Chapfuwa · Chenyang Tao · Chunyuan Li · Courtney Page · Benjamin Goldstein · Lawrence Carin · Ricardo Henao

Thu Jul 12th 05:40 -- 05:50 PM @ A7

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 adversarial 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 information 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.

Author Information

Paidamoyo Chapfuwa (Duke University)
Chenyang Tao (Duke University)
Chunyuan Li (Duke University)
Courtney Page (Duke University)
Benjamin Goldstein
Lawrence Carin (Duke)
Ricardo Henao (Duke University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors