A Bayesian Nonparametric Approach for Estimating Individualized Treatment-Response Curves

By Yanbo Xu, Yanxun Xu, Suchi Saria. 2016

42 citations recorded by the source corpus.

We study the problem of estimating the continuous response over time to interventions using observational time series---a retrospective dataset where the policy by which the data are generated is unknown to the learner. We are motivated by applications where response varies by individuals and therefore, estimating responses at the individual-level is valuable for personalizing decision-making. We refer to this as the problem of estimating individualized treatment response (ITR) curves. In statistics, G-computation formula (Robins, 1986) has been commonly used for estimating treatment responses from observational data containing sequential treatment assignments. However, past studies have focused predominantly on obtaining point-in-time estimates at the population level. We leverage the G-computation formula and develop a novel Bayesian nonparametric (BNP) method that can flexibly model functional data and provide posterior inference over the treatment response curves at both the individual and population level. On a challenging dataset containing time series from patients admitted to a hospital, we estimate responses to treatments used in managing kidney function and show that the resulting fits are more accurate than alternative approaches. Accurate methods for obtaining ITRs from observational data can dramatically accelerate the pace at which personalized treatment plans become possible.

Subfields: Artificial Intelligence, Statistics and Probability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Statistics and Probability

Citations in the corpus

Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounders (2019, methodology): “Several methods using Bayesian nonparametrics have been proposed for estimating the treatment responses in continuous time (Xu et al., 2016; Soleimani et al., 2017; Schulam & Saria, 2017), again assuming that there are no hidden confounders.”
Estimating Counterfactual Treatment Outcomes over Time Through Adversarially Balanced Representations (2020, methodology): “Soleimani et al. (2017) extend the approach in Xu et al. (2016) to the continuous time-setting and model treatment responses using linear time-invariant dynamical systems.”
Deep Counterfactual Networks with Propensity-Dropout (2017, methodology): “: X × {0, 1} → R that treats the treatment assignment Wi ∈ {0, 1} as an input feature is used to estimate the two potential outcomes, i.e. T̃ (x) = f(x, 1) − f(x, 0) (Shalit et al., 2017; Wager & Athey, 2015; Xu et al., 2016; Hill, 2012; Johansson et al., 2016).”
From Real‐World Patient Data to Individualized Treatment Effects Using Machine Learning: Current and Future Methods to Address Underlying Challenges (2020, background): “To begin with, Xu et al .”