Disentangled representation for sequential treatment effect estimation.

Journal: Computer methods and programs in biomedicine
Published Date:

Abstract

BACKGROUND AND OBJECTIVE: Treatment effect estimation, as a fundamental problem in causal inference, focuses on estimating the outcome difference between different treatments. However, in clinical observational data, some patient covariates (such as gender, age) not only affect the outcomes but also affect the treatment assignment. Such covariates, named as confounders, produce distribution discrepancies between different treatment groups, thereby introducing the selection bias for the estimation of treatment effects. The situation is even more complicated in longitudinal data, because the confounders are time-varying that are subject to patient history and meanwhile affect the future outcomes and treatment assignments. Existing methods mainly work on cross-sectional data obtained at a specific time point, but cannot process the time-varying confounders hidden in the longitudinal data.

Authors

  • Jiebin Chu
    College of Biomedical Engineering and Instrument Science, Zhejiang University, PR China.
  • Yaoyun Zhang
    Alibaba Damo Academy, 969 West Wen Yi Road, Yu Hang District, Hangzhou, Zhejiang, China.
  • Fei Huang
    Alibaba Damo Academy, 969 West Wen Yi Road, Yu Hang District, Hangzhou, Zhejiang, China.
  • Luo Si
    Alibaba Group, Hangzhou, Zhejiang Province, China.
  • Songfang Huang
    Alibaba Damo Academy, 969 West Wen Yi Road, Yu Hang District, Hangzhou, Zhejiang, China.
  • Zhengxing Huang
    College of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou, Zhejiang, China.