The counterfactual χ-GAN: Finding comparable cohorts in observational health data

Amelia J. Averitt, Natnicha Vanitchanant, Rajesh Ranganath, Adler J. Perotte

Research output: Contribution to journalArticlepeer-review

Abstract

Causal inference often relies on the counterfactual framework, which requires that treatment assignment is independent of the outcome, known as strong ignorability. Approaches to enforcing strong ignorability in causal analyses of observational data include weighting and matching methods. Effect estimates, such as the average treatment effect (ATE), are then estimated as expectations under the re-weighted or matched distribution, P. The choice of P is important and can impact the interpretation of the effect estimate and the variance of effect estimates. In this work, instead of specifying P, we learn a distribution that simultaneously maximizes coverage and minimizes variance of ATE estimates. In order to learn this distribution, this research proposes a generative adversarial network (GAN)-based model called the Counterfactual χ-GAN (cGAN), which also learns feature-balancing weights and supports unbiased causal estimation in the absence of unobserved confounding. Our model minimizes the Pearson χ2-divergence, which we show simultaneously maximizes coverage and minimizes the variance of importance sampling estimates. To our knowledge, this is the first such application of the Pearson χ2-divergence. We demonstrate the effectiveness of cGAN in achieving feature balance relative to established weighting methods in simulation and with real-world medical data.

Original languageEnglish (US)
Article number103515
JournalJournal of Biomedical Informatics
Volume109
DOIs
StatePublished - Sep 2020

Keywords

  • Causal inference
  • Deep learning
  • GANs
  • Health
  • Machine learning
  • Observational studies

ASJC Scopus subject areas

  • Computer Science Applications
  • Health Informatics

Fingerprint Dive into the research topics of 'The counterfactual χ-GAN: Finding comparable cohorts in observational health data'. Together they form a unique fingerprint.

Cite this