SCouT: Synthetic Counterfactuals via Spatiotemporal Transformers for Actionable Healthcare

TL;DR

This paper introduces SCouT, a spatiotemporal Transformer-based method for more accurately estimating counterfactual outcomes in healthcare, capturing complex dynamics and providing actionable insights for policy and clinical decisions.

Contribution

It proposes a novel Transformer model with specialized embeddings and training tasks to improve counterfactual estimation over traditional linear methods.

Findings

Effective on synthetic data with small donor pools

Robust against noise in counterfactual estimation

Provides actionable healthcare insights through simulations

Abstract

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.