Estimating the treatment effect over time under general interference through deep learner integrated TMLE

TL;DR

DeepNetTMLE is a novel deep learning-enhanced TMLE method that accurately estimates time-sensitive treatment effects in social networks with interference, improving bias reduction and confidence interval precision for public health policy decisions.

Contribution

The paper introduces DeepNetTMLE, integrating deep learning with TMLE to handle interference and time-varying confounders in causal inference, which is a significant advancement over existing methods.

Findings

DeepNetTMLE outperforms state-of-the-art methods in simulations.

It achieves lower bias and more precise confidence intervals.

Enables better quarantine policy recommendations.

Abstract

Understanding the effects of quarantine policies in populations with underlying social networks is crucial for public health, yet most causal inference methods fail here due to their assumption of independent individuals. We introduce DeepNetTMLE, a deep-learning-enhanced Targeted Maximum Likelihood Estimation (TMLE) method designed to estimate time-sensitive treatment effects in observational data. DeepNetTMLE mitigates bias from time-varying confounders under general interference by incorporating a temporal module and domain adversarial training to build intervention-invariant representations. This process removes associations between current treatments and historical variables, while the targeting step maintains the bias-variance trade-off, enhancing the reliability of counterfactual predictions. Using simulations of a ``Susceptible-Infected-Recovered'' model with varied quarantine coverages, we show that DeepNetTMLE achieves lower bias and more precise confidence intervals in counterfactual estimates, enabling optimal quarantine recommendations within budget constraints, surpassing state-of-the-art methods.