Bayesian Inference of Individualized Treatment Effects using Multi-task Gaussian Processes

Abstract

Predicated on the increasing abundance of electronic health records, we investi- gate the problem of inferring individualized treatment effects using observational data. Stemming from the potential outcomes model, we propose a novel multi- task learning framework in which factual and counterfactual outcomes are mod- eled as the outputs of a function in a vector-valued reproducing kernel Hilbert space (vvRKHS). We develop a nonparametric Bayesian method for learning the treatment effects using a multi-task Gaussian process (GP) with a linear coregion- alization kernel as a prior over the vvRKHS. The Bayesian approach allows us to compute individualized measures of confidence in our estimates via pointwise credible intervals, which are crucial for realizing the full potential of precision medicine. The impact of selection bias is alleviated via a risk-based empirical Bayes method for adapting the multi-task GP prior, which jointly minimizes the empirical error in factual outcomes and the uncertainty in (unobserved) counter- factual outcomes. We conduct experiments on observational datasets for an inter- ventional social program applied to premature infants, and a left ventricular assist device applied to cardiac patients wait-listed for a heart transplant. In both experi- ments, we show that our method significantly outperforms the state-of-the-art.

References in corpus (9)

• Adam: A Method for Stochastic Optimization
• Matching Methods for Causal Inference: A Review and a Look Forward
• Recursive Partitioning for Heterogeneous Causal Effects
• Doubly Robust Policy Evaluation and Learning
• Estimating individual treatment effect: generalization bounds and algorithms
• Double/Debiased Machine Learning for Treatment and Causal Parameters
• Counterfactual Prediction with Deep Instrumental Variables Networks
• A Bayesian Nonparametric Approach for Estimating Individualized Treatment-Response Curves
• Model Criticism for Bayesian Causal Inference

Cited by in corpus (10)

• Learning Counterfactual Representations for Estimating Individual Dose-Response Curves
• What if? Causal Machine Learning in Supply Chain Risk Management
• Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confounding
• NCoRE: Neural Counterfactual Representation Learning for Combinations of Treatments
• Analyzing Population-Level Trials as N-of-1 Trials: an Application to Gait
• MultiMBNN: Matched and Balanced Causal Inference with Neural Networks
• Graph-Driven Generative Models for Heterogeneous Multi-Task Learning
• Combining Incomplete Observational and Randomized Data for Heterogeneous Treatment Effects
• Doing Great at Estimating CATE? On the Neglected Assumptions in Benchmark Comparisons of Treatment Effect Estimators
• Nonstationary Multivariate Gaussian Processes for Electronic Health Records