SCouT: Synthetic Counterfactuals via Spatiotemporal Transformers for Actionable Healthcare
This work addresses the challenge of accurate counterfactual estimation in healthcare for policymakers and clinicians, though it appears incremental as it builds on existing synthetic control methods with a novel model.
The authors tackled the problem of estimating counterfactual outcomes in healthcare by proposing SCouT, a Transformer-based method that captures spatiotemporal dynamics, and demonstrated its efficacy on synthetic data with robustness against noise, generating actionable insights for public health policies and personalized therapies.
The Synthetic Control method has pioneered a class of powerful data-driven techniques to estimate the counterfactual reality of a unit from donor units. At its core, the technique involves a linear model fitted on the pre-intervention period that combines donor outcomes to yield the counterfactual. However, linearly combining spatial information at each time instance using time-agnostic weights fails to capture important inter-unit and intra-unit temporal contexts and complex nonlinear dynamics of real data. We instead propose an approach to use local spatiotemporal information before the onset of the intervention as a promising way to estimate the counterfactual sequence. To this end, we suggest a Transformer model that leverages particular positional embeddings, a modified decoder attention mask, and a novel pre-training task to perform spatiotemporal sequence-to-sequence modeling. Our experiments on synthetic data demonstrate the efficacy of our method in the typical small donor pool setting and its robustness against noise. We also generate actionable healthcare insights at the population and patient levels by simulating a state-wide public health policy to evaluate its effectiveness, an in silico trial for asthma medications to support randomized controlled trials, and a medical intervention for patients with Friedreich's ataxia to improve clinical decision-making and promote personalized therapy.