Automated data-adaptive analytics for electronic healthcare data to study causal treatment effects

Abstract

BackgroundDecision makers in health care increasingly rely on nonrandomized database analyses to assess the effectiveness, safety, and value of medical products. Health care data scientists use data-adaptive approaches that automatically optimize confounding control to study causal treatment effects. This article summarizes relevant experiences and extensions.MethodsThe literature was reviewed on the uses of high-dimensional propensity score (HDPS) and related approaches for health care database analyses, including methodological articles on their performance and improvement. Articles were grouped into applications, comparative performance studies, and statistical simulation experiments.ResultsThe HDPS algorithm has been referenced frequently with a variety of clinical applications and data sources from around the world. The appeal of HDPS for database research rests in 1) its superior performance in situations of unobserved confounding through proxy adjustment, 2) its predictable efficiency in extracting confounding information from a given data source, 3) its ability to automate estimation of causal treatment effects to the extent achievable in a given data source, and 4) its independence of data source and coding system. Extensions of the HDPS approach have focused on improving variable selection when exposure is sparse, using free text information and time-varying confounding adjustment.ConclusionSemiautomated and optimized confounding adjustment in health care database analyses has proven successful across a wide range of settings. Machine-learning extensions further automate its use in estimating causal treatment effects across a range of data scenarios.

Estimates of all cause mortality and cause specific mortality associated with proton pump inhibitors among US veterans: cohort study

“…Third, we applied inverse probability of treatment weighting based on high dimensional propensity scores to create a pseudo cohort whose treatment assignment was independent of measured confounders. 70 Fourth, to reduce the probability that an observed association between PPIs and causes of death is contributed by unmeasured confounding, we employed an instrumental variable method. 71 Results from two negative controls which showed no association between PPI use and transportation mortality, and no association between PPI use and death due to peptic ulcer disease, lessen concerns about unmeasured confounding and other biases.…”

Comparative Effectiveness and Safety of Standard or Reduced Dose Dabigatran vs. Rivaroxaban in Nonvalvular Atrial Fibrillation

“…The hdPS matching has already been used in many studies in the fields of pharmacoepidemiology, comparative effectiveness, and drug safety . Unmeasured confounders, such as smoking, obesity, etc., may be approached by various combinations of claims, such as visits, prescriptions, procedures, tests, and hospitalizations, which may collectively be a proxy for risk factors that are not present as such in the database …”

Implementing high‐dimensional propensity score principles to improve confounder adjustment in UK electronic health records

“…5 Some proxies may be strongly correlated with variables typically included in a traditional propensity score (PS) analysis; others may represent information about patients that is otherwise unmeasured, for example, frailty. 5 Despite application in various settings (including UK EHRs), [6][7][8][9] detailed guidance on how to apply the hd-PS outside US claims data is lacking. Important differences between data sources mean that careful consideration is needed when implementing hd-PS principles to ensure source-specific characteristics are handled appropriately.…”