A semiparametric instrumental variable approach to optimal treatment regimes under endogeneity

Individualized treatment rule characterization via a value function surrogate

Precision medicine is a promising framework for generating evidence to improve health and health care. Yet, a gap persists between the ever-growing number of statistical precision medicine strategies for evidence generation and implementation in real-world clinical settings, and the strategies for closing this gap will likely be context-dependent. In this paper, we consider the specific context of partial compliance to wound management among patients with peripheral artery disease. Using a Gaussian process surrogate for the value function, we show the feasibility of using Bayesian optimization to learn optimal individualized treatment rules. Further, we expand beyond the common precision medicine task of learning an optimal individualized treatment rule to the characterization of classes of individualized treatment rules and show how those findings can be translated into clinical contexts.

Nonparametric Bayesian Q-learning for optimization of dynamic treatment regimes in the presence of partial compliance

Existing methods for estimation of dynamic treatment regimes are mostly limited to intention-to-treat analyses-which estimate the effect of randomization to a particular treatment regime without considering the compliance behavior of patients. In this article, we propose a novel nonparametric Bayesian Q-learning approach to construct optimal sequential treatment regimes that adjust for partial compliance. We consider the popular potential compliance framework, where some potential compliances are latent and need to be imputed. The key challenge is learning the joint distribution of the potential compliances, which we accomplish using a Dirichlet process mixture model. Our approach provides two kinds of treatment regimes: (1) conditional regimes that depend on the potential compliance values; and (2) marginal regimes where the potential compliances are marginalized. Extensive simulation studies highlight the usefulness of our method compared to intention-to-treat analyses. We apply our method to the Adaptive Treatment for Alcohol and Cocaine Dependence (ENGAGE) study , where the goal is to construct optimal treatment regimes to engage patients in therapy.

Discussion on "Instrumented difference-in-differences" by Ye, Ertefaie, Flory, Hennessy, Small

Ye, Ertefaie, Flory, Hennessy, and Small (YEFHS) proposed a new method, instrumented difference-in-differences, for dealing with unmeasured confounding. In this note, I connect and compare assumptions and identifications in instrumental variable (IV) and difference-in-differences (DID) methods with those in YEFHS, derive new identification results, and discuss different choices when extending such results to adjust for covariates.

Instrumented difference-in-differences

Unmeasured confounding is a key threat to reliable causal inference based on observational studies. Motivated from two powerful natural experiment devices, the instrumental variables and difference-in-differences, we propose a new method called instrumented difference-in-differences that explicitly leverages exogenous randomness in an exposure trend to estimate the average and conditional average treatment effect in the presence of unmeasured confounding. We develop the identification assumptions using the potential outcomes framework. We propose a Wald estimator and a class of multiply robust and efficient semiparametric estimators, with provable consistency and asymptotic normality. In addition, we extend the instrumented difference-in-differences to a two-sample design to facilitate investigations of delayed treatment effect and provide a measure of weak identification. We demonstrate our results in simulated and real datasets.

Monte Carlo sensitivity analysis for unmeasured confounding in dynamic treatment regimes

Data-driven methods for personalizing treatment assignment have garnered much attention from clinicians and researchers. Dynamic treatment regimes formalize this through a sequence of decision rules that map individual patient characteristics to a recommended treatment. Observational studies are commonly used for estimating dynamic treatment regimes due to the potentially prohibitive costs of conducting sequential multiple assignment randomized trials. However, estimating a dynamic treatment regime from observational data can lead to bias in the estimated regime due to unmeasured confounding. Sensitivity analyses are useful for assessing how robust the conclusions of the study are to a potential unmeasured confounder. A Monte Carlo sensitivity analysis is a probabilistic approach that involves positing and sampling from distributions for the parameters governing the bias. We propose a method for performing a Monte Carlo sensitivity analysis of the bias due to unmeasured confounding in the estimation of dynamic treatment regimes. We demonstrate the performance of the proposed procedure with a simulation study and apply it to an observational study examining tailoring the use of antidepressant medication for reducing symptoms of depression using data from Kaiser Permanente Washington.

Average Causal Effect Estimation Via Instrumental Variables: the No Simultaneous Heterogeneity Assumption

BACKGROUND

Instrumental variables (IVs) can be used to provide evidence as to whether a treatment has a causal effect on an outcome . Even if the instrument satisfies the three core IV assumptions of relevance, independence, and exclusion restriction, further assumptions are required to identify the average causal effect (ACE) of on . Sufficient assumptions for this include homogeneity in the causal effect of on ; homogeneity in the association of with ; and no effect modification.

METHODS

We describe the no simultaneous heterogeneity assumption, which requires the heterogeneity in the - causal effect to be mean independent of (i.e., uncorrelated with) both and heterogeneity in the - association. This happens, for example, if there are no common modifiers of the - effect and the - association, and the - effect is additive linear. We illustrate the assumption of no simultaneous heterogeneity using simulations and by re-examining selected published studies.

RESULTS

Under no simultaneous heterogeneity, the Wald estimand equals the ACE even if both homogeneity assumptions and no effect modification (which we demonstrate to be special cases of-and therefore stronger than-no simultaneous heterogeneity) are violated.

CONCLUSIONS

The assumption of no simultaneous heterogeneity is sufficient for identifying the ACE using IVs. Since this assumption is weaker than existing assumptions for ACE identification, doing so may be more plausible than previously anticipated.

Accountable survival contrast-learning for optimal dynamic treatment regimes

Dynamic treatment regime (DTR) is an emerging paradigm in recent medical studies, which searches a series of decision rules to assign optimal treatments to each patient by taking into account individual features such as genetic, environmental, and social factors. Although there is a large and growing literature on statistical methods to estimate optimal treatment regimes, most methodologies focused on complete data. In this article, we propose an accountable contrast-learning algorithm for optimal dynamic treatment regime with survival endpoints. Our estimating procedure is originated from a doubly-robust weighted classification scheme, which is a model-based contrast-learning method that directly characterizes the interaction terms between predictors and treatments without main effects. To reflect the censorship, we adopt the pseudo-value approach that replaces survival quantities with pseudo-observations for the time-to-event outcome. Unlike many existing approaches, mostly based on complicated outcome regression modeling or inverse-probability weighting schemes, the pseudo-value approach greatly simplifies the estimating procedure for optimal treatment regime by allowing investigators to conveniently apply standard machine learning techniques to censored survival data without losing much efficiency. We further explore a SCAD-penalization to find informative clinical variables and modified algorithms to handle multiple treatment options by searching upper and lower bounds of the objective function. We demonstrate the utility of our proposal via extensive simulations and application to AIDS data.

Meta-analysis of individualized treatment rules via sign-coherency

Medical treatments tailored to a patient's baseline characteristics hold the potential of improving patient outcomes while reducing negative side effects. Learning individualized treatment rules (ITRs) often requires aggregation of multiple datasets(sites); however, current ITR methodology does not take between-site heterogeneity into account, which can hurt model generalizability when deploying back to each site. To address this problem, we develop a method for individual-level meta-analysis of ITRs, which jointly learns site-specific ITRs while borrowing information about feature sign-coherency via a scientifically-motivated directionality principle. We also develop an adaptive procedure for model tuning, using information criteria tailored to the ITR learning problem. We study the proposed methods through numerical experiments to understand their performance under different levels of between-site heterogeneity and apply the methodology to estimate ITRs in a large multi-center database of electronic health records. This work extends several popular methodologies for estimating ITRs (A-learning, weighted learning) to the multiple-sites setting.

Machine intelligence for individualized decision making under a counterfactual world: A rejoinder

This JASA rejoinder concerns the problem of individualized decision making under point, sign, and partial identification. The paper unifies various classical decision making strategies through a lower bound perspective proposed in Cui and Tchetgen Tchetgen (2020b) in the context of optimal treatment regimes under uncertainty due to unmeasured confounding. Building on this unified framework, the paper also provides a novel minimax solution (i.e., a rule that minimizes the maximum regret for so-called opportunists) for individualized decision making/policy assignment.