Estimating Counterfactual Treatment Outcomes over Time Through Adversarially Balanced Representations

Abstract

Identifying when to give treatments to patients and how to select among multiple treatments over time are important medical problems with a few existing solutions. In this paper, we introduce the Counterfactual Recurrent Network (CRN), a novel sequence-to-sequence model that leverages the increasingly available patient observational data to estimate treatment effects over time and answer such medical questions. To handle the bias from time-varying confounders, covariates affecting the treatment assignment policy in the observational data, CRN uses domain adversarial training to build balancing representations of the patient history. At each timestep, CRN constructs a treatment invariant representation which removes the association between patient history and treatment assignments and thus can be reliably used for making counterfactual predictions. On a simulated model of tumour growth, with varying degree of time-dependent confounding, we show how our model achieves lower error in estimating counterfactuals and in choosing the correct treatment and timing of treatment than current state-of-the-art methods.

References in corpus (5)

• Reliable Decision Support using Counterfactual Models
• Treatment-Response Models for Counterfactual Reasoning with Continuous-time, Continuous-valued Interventions
• Using Options and Covariance Testing for Long Horizon Off-Policy Policy Evaluation
• Multi-Domain Adversarial Learning
• Learning Optimal Policies from Observational Data

Cited by in corpus (8)

• Time Series Forecasting With Deep Learning: A Survey
• Estimating the Effects of Continuous-valued Interventions using Generative Adversarial Networks
• Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounders
• Learning "What-if" Explanations for Sequential Decision-Making
• Neural Pharmacodynamic State Space Modeling
• A scoping review of causal methods enabling predictions under hypothetical interventions
• Counterfactual Prediction Under Selective Confounding
• Adaptive Multi-Source Causal Inference