We consider a setting in which we have a treatment and a potentially large number of covariates for a set of observations, and wish to model their relationship with an outcome of interest. We propose a simple method for modeling interactions between the treatment and covariates. The idea is to modify the covariate in a simple way, and then fit a standard model using the modified covariates and no main effects. We show that coupled with an efficiency augmentation procedure, this method produces clinically meaningful estimators in a variety of settings. It can be useful for practicing personalized medicine: determining from a large set of biomarkers, the subset of patients that can potentially benefit from a treatment. We apply the method to both simulated datasets and real trial data. The modified covariates idea can be used for other purposes, for example, large scale hypothesis testing for determining which of a set of covariates interact with a treatment variable. Supplementary materials for this article are available online.

Immune aging results in progressive loss of both protective immunity and T cell–mediated suppression, thereby conferring susceptibility to a combination of immunodeficiency and chronic inflammatory disease. Here, we determined that older individuals fail to generate immunosuppressive CD8⁺CCR7⁺ Tregs, a defect that is even more pronounced in the age-related vasculitic syndrome giant cell arteritis. In young, healthy individuals, CD8⁺CCR7⁺ Tregs are localized in T cell zones of secondary lymphoid organs, suppress activation and expansion of CD4 T cells by inhibiting the phosphorylation of membrane-proximal signaling molecules, and effectively inhibit proliferative expansion of CD4 T cells in vitro and in vivo. We identified deficiency of NADPH oxidase 2 (NOX2) as the molecular underpinning of CD8 Treg failure in the older individuals and in patients with giant cell arteritis. CD8 Tregs suppress by releasing exosomes that carry preassembled NOX2 membrane clusters and are taken up by CD4 T cells. Overexpression of NOX2 in aged CD8 Tregs promptly restored suppressive function. Together, our data support NOX2 as a critical component of the suppressive machinery of CD8 Tregs and suggest that repairing NOX2 deficiency in these cells may protect older individuals from tissue-destructive inflammatory disease, such as large-vessel vasculitis.

Analysis of high-dimensional data often seeks to identify a subset of important features and to assess the effects of these features on outcomes. Traditional statistical inference procedures based ...

For observational studies, we study the sensitivity of causal inference when treatment assignments may depend on unobserved confounders. We develop a loss minimization approach for estimating bounds on the conditional average treatment effect (CATE) when unobserved confounders have a bounded effect on the odds ratio of treatment selection. Our approach is scalable and allows flexible use of model classes in estimation, including nonparametric and black-box machine learning methods. Based on these bounds for the CATE, we propose a sensitivity analysis for the average treatment effect (ATE). Our semiparametric estimator extends/bounds the augmented inverse propensity weighted (AIPW) estimator for the ATE under bounded unobserved confounding. By constructing a Neyman orthogonal score, our estimator of the bound for the ATE is a regular root-n estimator so long as the nuisance parameters are estimated at the op(n−1/4) rate. We complement our methodology with optimality results showing that our proposed bounds are tight in certain cases. We demonstrate our method on simulated and real data examples, and show accurate coverage of our confidence intervals in practical finite sample regimes with rich covariate information.