On learning disentangled representations for individual treatment effect estimation.

Journal: Journal of biomedical informatics
PMID: 34728379

Abstract

OBJECTIVE: Estimating the individualized treatment effect (ITE) from observational data is a challenging task due to selection bias, which results from the distributional discrepancy between different treatment groups caused by the dependence between features and assigned treatments. This dependence is induced by the factors related to the treatment assignment. We hypothesize that features consist of three types of latent factors: outcome-specific factors, treatment-specific factors and confounders. Then, we aim to reduce the influence of treatment-related factors, i.e., treatment-specific factors and confounders, on outcome prediction to mitigate the effects of selection bias.

Authors

  • Jiebin Chu
    College of Biomedical Engineering and Instrument Science, Zhejiang University, PR China.
  • Zhoujian Sun
    College of Biomedical Engineering and Instrument Science, Zhejiang University, Key Lab for Biomedical Engineering of Ministry of Education, Zheda Road, Hangzhou, China.
  • Wei Dong
    Department of Cardiology, Chinese PLA General Hospital, Beijing, China.
  • Jinlong Shi
    Department of Medical Innovation Research, Medical Big Data Center, Chinese PLA General Hospital, Beijing, China.
  • Zhengxing Huang
    College of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou, Zhejiang, China.

Keywords

External Resources

Popular Topics
Recent Journals