Treatment-Response Models for Counterfactual Reasoning with Continuous-time, Continuous-valued Interventions
arXiv:1704.02038
Abstract
Treatment effects can be estimated from observational data as the difference in potential outcomes. In this paper, we address the challenge of estimating the potential outcome when treatment-dose levels can vary continuously over time. Further, the outcome variable may not be measured at a regular frequency. Our proposed solution represents the treatment response curves using linear time-invariant dynamical systems---this provides a flexible means for modeling response over time to highly variable dose curves. Moreover, for multivariate data, the proposed method: uncovers shared structure in treatment response and the baseline across multiple markers; and, flexibly models challenging correlation structure both across and within signals over time. For this, we build upon the framework of multiple-output Gaussian Processes. On simulated and a challenging clinical dataset, we show significant gains in accuracy over state-of-the-art models.
In Proceedings of the Thirty-Third Conference on Uncertainty in Artificial Intelligence (UAI-2017), Sydney, Australia, August 2017. The first two authors contributed equally to this work
References in corpus (2)
Cited by in corpus (9)
- Neural Ordinary Differential Equations
- Deconfounding Reinforcement Learning in Observational Settings
- Estimating Counterfactual Treatment Outcomes over Time Through Adversarially Balanced Representations
- Causal Inference for Time series Analysis: Problems, Methods and Evaluation
- Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounders
- Dynamic Measurement Scheduling for Event Forecasting using Deep RL
- Policy Analysis using Synthetic Controls in Continuous-Time
- Weighted Tensor Completion for Time-Series Causal Inference
- Errors-in-variables Modeling of Personalized Treatment-Response Trajectories