xliu-stat/SAT: Surrogate Assisted Two-wave Case Boosting Sampling

Electronic health records (EHR) enable investigation of the association between phenotypes and risk factors. However, studies solely relying on potentially error-prone EHR-derived phenotypes (i.e., surrogates) are subject to bias. Analyses of low prevalence phenotypes may also suffer from poor efficiency. For analyzing rare diseases, we develop a Surrogate Assisted Two-wave (SAT) sampling method to select a subsample for outcome validation through manual chart review subject to budget constraints. A model is then fitted based on the subsample. The subsample selected with the proposed method contains informative observations that effectively reduce the mean squared error (MSE) of the resultant estimator of the association.

install.packages("remotes")
remotes::install_github("xliu-stat/SAT")