Robust Causal Inference for EHR-based Studies of Point Exposures with Missingness in Eligibility Criteria

Abstract

Missingness in variables that define study eligibility criteria is a seldom addressed challenge in electronic health record (EHR)-based settings. Patients with incomplete eligibility information are typically excluded from analysis without consideration of the (implicit) assumptions being made, leaving study conclusions subject to potential selection bias. In an effort to ascertain eligibility for more patients, researchers may look back further in time prior to study baseline, inappropriately including individuals who, unbeknownst to the researcher, would fail to meet eligibility at baseline. To the best of our knowledge, however, little work has been done to mitigate these concerns. We propose a robust and efficient estimator of the causal average treatment effect on the treated, defined in the study-eligible population, where eligibility-defining covariates are missing at random. The approach facilitates flexible machine-learning strategies for component nuisance functions while maintaining valid asymptotic inference. This method is applied to EHR data from Kaiser Permanente on 14,809 patients undergoing bariatric surgery, comparing two surgical interventions for long-term weight and glycemic outcomes among severely obese patients with type II diabetes mellitus. Our results confirm a weight-loss advantage for Roux-en-Y gastric bypass over sleeve gastrectomy, but are less suggestive of a diabetes remission advantage than complete-case analyses indicate.