G-Net: A Deep Learning Approach to G-computation for Counterfactual Outcome Prediction Under Dynamic Treatment Regimes
This work addresses counterfactual prediction for decision-making in dynamic settings, representing an incremental advancement by applying deep learning to an existing method.
The paper tackled the problem of estimating counterfactual outcomes under dynamic treatment regimes by introducing G-Net, a deep learning framework that improved upon classical regression models, achieving better performance in handling complex temporal data as demonstrated on simulated cardiovascular data.
Counterfactual prediction is a fundamental task in decision-making. G-computation is a method for estimating expected counterfactual outcomes under dynamic time-varying treatment strategies. Existing G-computation implementations have mostly employed classical regression models with limited capacity to capture complex temporal and nonlinear dependence structures. This paper introduces G-Net, a novel sequential deep learning framework for G-computation that can handle complex time series data while imposing minimal modeling assumptions and provide estimates of individual or population-level time varying treatment effects. We evaluate alternative G-Net implementations using realistically complex temporal simulated data obtained from CVSim, a mechanistic model of the cardiovascular system.