In many medical and business applications, researchers are interested in estimating individualized treatment effects using data from a randomized experiment. For example in medical applications, doctors learn the treatment effects from clinical trials and in technology companies, researchers learn them from A/B testing experiments. Although dozens of machine learning models have been proposed for this task, it is challenging to determine which model will be best for the problem at hand because ground-truth treatment effects are unobservable. In contrast to several recent papers proposing methods to select one of these competing models, we propose an algorithm for aggregating the estimates from a diverse library of models. We compare ensembling to model selection on 43 benchmark datasets, and find that ensembling wins almost every time. Theoretically, we prove that our ensemble model is (asymptotically) at least as accurate as the best model under consideration, even if the number of candidate models is allowed to grow with the sample size.
We propose a matching method for observational data that matches units with others in unit-specific, hyper-box-shaped regions of the covariate space. These regions are large enough that many matches are created for each unit and small enough that the treatment effect is roughly constant throughout. The regions are found as either the solution to a mixed integer program, or using a (fast) approximation algorithm. The result is an interpretable and tailored estimate of a causal effect for each unit.
Estimation and evaluation of individualized treatment rules have been studied extensively, but real-world treatment resource constraints have received limited attention in existing methods. We investigate a setting in which treatment is intervened upon based on covariates to optimize the mean counterfactual outcome under treatment cost constraints when the treatment cost is random. In a particularly interesting special case, an instrumental variable corresponding to encouragement to treatment is intervened upon with constraints on the proportion receiving treatment. For such settings, we first…
This note discusses two recent studies on identification of individualized treatment rules using instrumental variables---Cui and Tchetgen Tchetgen (2020) and Qiu et al. (2020). It also proposes identifying assumptions that are alternative to what is used in both studies.
Randomized trials typically estimate average relative treatment effects, but decisions on the benefit of a treatment are possibly better informed by more individualized predictions of the absolute treatment effect. In case of a binary outcome, these predictions of absolute individualized treatment effect require knowledge of the individual's risk without treatment and incorporation of a possibly differential treatment effect (i.e. varying with patient characteristics). In this paper we lay out the causal structure of individualized treatment effect in terms of potential outcomes and describe t…
With a large number of baseline covariates, we propose a new semi-parametric modeling strategy for heterogeneous treatment effect estimation and individualized treatment selection, which are two major goals in personalized medicine. We achieve the first goal through estimating a covariate-specific treatment effect (CSTE) curve modeled as an unknown function of a weighted linear combination of all baseline covariates. The weight or the coefficient for each covariate is estimated by fitting a sparse semi-parametric logistic single-index coefficient model. The CSTE curve is estimated by a spline-…
The George Washington University（乔治华盛顿大学）；University of California, Irvine（加州大学欧文分校）
Data-driven individualized decision making has recently received increasing research interests. Most existing methods rely on the assumption of no unmeasured confounding, which unfortunately cannot be ensured in practice especially in observational studies. Motivated by the recent proposed proximal causal inference, we develop several proximal learning approaches to estimating optimal individualized treatment regimes (ITRs) in the presence of unmeasured confounding. In particular, we establish several identification results for different classes of ITRs, exhibiting the trade-off between the ri…
To maximize clinical benefit, clinicians routinely tailor treatment to the individual characteristics of each patient, where individualized treatment rules are needed and are of significant research interest to statisticians. In the covariate-adjusted randomization clinical trial with many covariates, we model the treatment effect with an unspecified function of a single index of the covariates and leave the baseline response completely arbitrary. We devise a class of estimators to consistently estimate the treatment effect function and its associated index while bypassing the estimation of th…
Estimating heterogeneous treatment effects is a well-studied topic in the statistics literature. More recently, it has regained attention due to an increasing need for precision medicine as well as the increased use of state-of-art machine learning methods in the estimation. Furthermore, estimating heterogeneous treatment effects is directly related to building an individualized treatment rule, which is a decision rule of treatment according to patient characteristics. This paper examines the connection and disconnection between these two research problems. Notably, a better estimation of the …
Maximin Learning of Individualized Treatment Effect on Multi-Domain Outcomes
Department of Biostatistics, Columbia Mailman School of Public Health（哥伦比亚大学梅尔曼公共卫生学院生物统计系）；Department of Biostatistics, Peking University Health Science Center（北京大学医学部生物统计系）；Beijing International Center for Mathematical Research, Peking University（北京大学北京国际数学研究中心）
Global Average Treatment Effects for Individualized Randomization Experiments with Aggregate Data
Shanghai University of Finance and Economics（上海财经大学）；London School of Economics and Political Science（伦敦政治经济学院）；DiDi China Ride Hailing Business Group（滴滴中国网约车业务组）；University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）
Individualized treatment effect lies at the heart of precision medicine. Interpretable individualized treatment rules (ITRs) are desirable for clinicians or policymakers due to their intuitive appeal and transparency. The gold-standard approach to estimating the ITRs is randomized experiments, where subjects are randomized to different treatment groups and the bias is minimized to the extent possible. However, experimental data are limited in external validity because of their selection restrictions and therefore are not representative of the target real-world population. Conventional learning…
Estimating treatment effects, especially individualized treatment effects (ITE), using observational data is challenging due to the complex situations of confounding bias. Existing approaches for estimating treatment effects from longitudinal observational data are usually built upon a strong assumption of "unconfoundedness", which is hard to fulfill in real-world practice. In this paper, we propose the Variational Temporal Deconfounder (VTD), an approach that leverages deep variational embeddings in the longitudinal setting using proxies (i.e., surrogate variables that serve for unobservable …
Recent development in data-driven decision science has seen great advances in individualized decision making. Given data with individual covariates, treatment assignments and outcomes, researchers can search for the optimal individualized treatment rule (ITR) that maximizes the expected outcome. Existing methods typically require initial estimation of some nuisance models. The double robustness property that can protect from misspecification of either the treatment-free effect or the propensity score has been widely advocated. However, when model misspecification exists, a doubly robust estima…
Objective: To compare different risk-based methods for optimal prediction of treatment effects. Methods: We simulated RCT data using diverse assumptions for the average treatment effect, a baseline prognostic index of risk (PI), the shape of its interaction with treatment (none, linear, quadratic or non-monotonic), and the magnitude of treatment-related harms (none or constant independent of the PI). We predicted absolute benefit using: models with a constant relative treatment effect; stratification in quarters of the PI; models including a linear interaction of treatment with the PI; models …
Randomized controlled trials typically analyze the effectiveness of treatments with the goal of making treatment recommendations for patient subgroups. With the advance of electronic health records, a great variety of data has been collected in clinical practice, enabling the evaluation of treatments and treatment policies based on observational data. In this paper, we focus on learning individualized treatment rules (ITRs) to derive a treatment policy that is expected to generate a better outcome for an individual patient. In our framework, we cast ITRs learning as a contextual bandit problem…
Using Individualized Treatment Effects to Assess Treatment Effect Heterogeneity
Advanced Methodology and Data Science, Novartis Pharma AG（诺华制药AG高级方法与数据科学）；China Novartis Institutes for Bio-medical Research CO.（中国诺华生物医学研究院有限公司）；Advanced Methodology and Data Science, Novartis Pharmaceuticals Corporation（诺华制药有限公司高级方法与数据科学）；Department of Statistics, Stanford University（斯坦福大学统计学系）
University of Cambridge（剑桥大学）；The Alan Turing Institute（艾伦图灵研究所）；UCLA（加利福尼亚大学洛杉矶分校）
The choice of making an intervention depends on its potential benefit or harm in comparison to alternatives. Estimating the likely outcome of alternatives from observational data is a challenging problem as all outcomes are never observed, and selection bias precludes the direct comparison of differently intervened groups. Despite their empirical success, we show that algorithms that learn domain-invariant representations of inputs (on which to make predictions) are often inappropriate, and develop generalization bounds that demonstrate the dependence on domain overlap and highlight the need f…
Non-parametric assessment of the calibration of individualized treatment effects
University of British Columbia（不列颠哥伦比亚大学）；Amsterdam University Medical Centers（阿姆斯特丹大学医学中心）；Smart Data Analysis and Statistics B.V.（智能数据分析与统计有限公司）；University Medical Center Göttingen（哥廷根大学医学中心）
Covariate Balancing Value Estimation for Optimal Individualized Treatment Rules
School of Mathematical Sciences, Peking University（北京大学数学科学学院）；School of Mathematics and Statistics, Beijing Technology and Business University（北京工商大学数学与统计学院）
The effect of vigorous physical activity on mortality in the elderly is difficult to estimate using conventional approaches to causal inference that define this effect by comparing the mortality risks corresponding to hypothetical scenarios in which all subjects in the target population engage in a given level of vigorous physical activity. A causal effect defined on the basis of such a static treatment intervention can only be identified from observed data if all subjects in the target population have a positive probability of selecting each of the candidate treatment options, an assumption t…
Using observational data to estimate the effect of a treatment is a powerful tool for decision-making when randomized experiments are infeasible or costly. However, observational data often yields biased estimates of treatment effects, since treatment assignment can be confounded by unobserved variables. A remedy is offered by deconfounding methods that adjust for such unobserved confounders. In this paper, we develop the Sequential Deconfounder, a method that enables estimating individualized treatment effects over time in presence of unobserved confounders. This is the first deconfounding me…
Genito-Pelvic Pain/Penetration-Disorder (GPPPD) is a common disorder but rarely treated in routine care. Previous research documents that GPPPD symptoms can be treated effectively using internet-based psychological interventions. However, non-response remains common for all state-of-the-art treatments and it is unclear which patient groups are expected to benefit most from an internet-based intervention. Multivariable prediction models are increasingly used to identify predictors of heterogeneous treatment effects, and to allocate treatments with the greatest expected benefits. In this study, …
The Graduate University for Advanced Studies（综合研究大学院大学）；The Institute of Statistical Mathematics（统计数学研究所）
As an important problem in causal inference, we discuss the identification and estimation of treatment effects (TEs) under limited overlap; that is, when subjects with certain features belong to a single treatment group. We use a latent variable to model a prognostic score which is widely used in biostatistics and sufficient for TEs; i.e., we build a generative prognostic model. We prove that the latent variable recovers a prognostic score, and the model identifies individualized treatment effects. The model is then learned as β-Intact-VAE--a new type of variational autoencoder (VAE). We deriv…
Estimating Individualized Treatment Effects in Acute Ischemic Stroke with Causal Transformation Models (TRAM-DAG): A Multi-Centre Observational Study with External RCT Validation
Thurgau Institute for Digital Transformation (TIDIT)（图尔豪数字转型研究所）；HTWG Konstanz – University of Applied Sciences Konstanz（康斯坦茨应用科学大学）；Department of Neurology, University Hospital Zurich (USZ)（苏黎世大学神经科部）；University of Zurich (UZH)（苏黎世大学）
Unmeasured confounding is a threat to causal inference and individualized decision making. Similar to Cui and Tchetgen Tchetgen (2020); Qiu et al. (2020); Han (2020a), we consider the problem of identification of optimal individualized treatment regimes with a valid instrumental variable. Han (2020a) provided an alternative identifying condition of optimal treatment regimes using the conditional Wald estimand of Cui and Tchetgen Tchetgen (2020); Qiu et al. (2020) when treatment assignment is subject to endogeneity and a valid binary instrumental variable is available. In this note, we provide …
In randomized clinical trials with survival outcome, there has been an increasing interest in subgroup identification based on baseline genomic, proteomic markers or clinical characteristics. Some of the existing methods identify subgroups that benefit substantially from the experimental treatment by directly modeling outcomes or treatment effect. When the goal is to find an optimal treatment for a given patient rather than finding the right patient for a given treatment, methods under the individualized treatment regime framework estimate an individualized treatment rule that would lead to th…
Recent years have seen a swell in methods that focus on estimating "individual treatment effects". These methods are often focused on the estimation of heterogeneous treatment effects under ignorability assumptions. This paper hopes to draw attention to the fact that there is nothing necessarily "individual" about such effects under ignorability assumptions and isolating individual effects may require additional assumptions. Such individual effects, more often than not, are more precisely described as "conditional average treatment effects" and confusion between the two has the potential to hi…
Individualized Dynamic Mediation Analysis Using Latent Factor Models
University of Pennsylvania（宾夕法尼亚大学）；The Pennsylvania State University（宾夕法尼亚州立大学）；The University of Texas at San Antonio（圣安东尼奥德克萨斯大学）；Fudan University（复旦大学）；University of California, Santa Barbara（加利福尼亚大学圣巴巴拉分校）
Forest-based methods have recently gained in popularity for non-parametric treatment effect estimation. Building on this line of work, we introduce causal survival forests, which can be used to estimate heterogeneous treatment effects in a survival and observational setting where outcomes may be right-censored. Our approach relies on orthogonal estimating equations to robustly adjust for both censoring and selection effects under unconfoundedness. In our experiments, we find our approach to perform well relative to a number of baselines.
When comparing time-varying treatments in a non-randomised setting, one must often correct for time-dependent confounders that influence treatment choice over time and that are themselves influenced by treatment. We present a new two step procedure, based on additive hazard regression and linear increments models, for handling such confounding when estimating average treatment effects on the treated (ATT). The approach can also be used for mediation analysis. The method is applied to data from the Swiss HIV Cohort Study, estimating the effect of antiretroviral treatment on time to AIDS or deat…
We consider the problem of constructing diffusion operators high dimensional data $X$ to address counterfactual functions $F$, such as individualized treatment effectiveness. We propose and construct a new diffusion metric $K_F$ that captures both the local geometry of $X$ and the directions of variance of $F$. The resulting diffusion metric is then used to define a localized filtration of $F$ and answer counterfactual questions pointwise, particularly in situations such as drug trials where an individual patient's outcomes cannot be studied long term both taking and not taking a medication. W…
In this paper, we outline a principled approach to estimate an individualized treatment rule that is appropriate for data from observational studies where, in addition to treatment assignment not being independent of individual characteristics, some characteristics may affect treatment assignment in the current study but not be available in future clinical settings where the estimated rule would be applied. The estimation framework is quite flexible and accommodates any prediction method that uses observation weights, where the observation weights themselves are a ratio of two flexibly estimat…
We propose the instrumental variable regime (IVR) method to estimate the causal effects of multiple sequential treatments. This method serves to address the problem of endogenous selections of sequential treatments. An IVR is a sequence of instrumental variables in which each IV instruments for an endogenous treatment variable. Our proposed method generalizes the LATE model in Imbens and Angrist (1994) from a single treatment to many treatments applied sequentially. More precisely, with the IVR this model allows for estimating the local average treatment regime effects (LATRE), possibly condit…
Because different patients may response quite differently to the same drug or treatment, there is increasing interest in discovering individualized treatment rule. In particular, people are eager to find the optimal individualized treatment rules, which if followed by the whole patient population would lead to the "best" outcome. In this paper, we propose new estimators based on robust regression with general loss functions to estimate the optimal individualized treatment rules. The new estimators possess the following nice properties: first, they are robust against skewed, heterogeneous, heav…
Heterogeneous treatment effect models allow us to compare treatments at subgroup and individual levels, and are of increasing popularity in applications like personalized medicine, advertising, and education. In this talk, we first survey different causal estimands used in practice, which focus on estimating the difference in conditional means. We then propose DINA, the difference in natural parameters, to quantify heterogeneous treatment effect in exponential families and the Cox model. For binary outcomes and survival times, DINA is both convenient and more practical for modeling the influen…
