Multiwave validation sampling for error-prone electronic health records
Bryan Shepherd, PhD Vice Chair of Faculty Affairs, Department of BiostatisticsProfessor of Biostatistics and Biomedical InformaticsVanderbilt University Medical Center
Electronic health record (EHR) data are increasingly used for biomedical research, but these data have recognized data quality challenges. Data validation is necessary to use EHR data with confidence, but limited resources typically make complete data validation impossible. Using EHR data, we illustrate prospective, multiwave, two-phase validation sampling to estimate the association between maternal weight gain during pregnancy and the risks of her child developing obesity. Our analysis approach, referred to as generalized raking, combines validated data with the error-prone data to efficiently and accurately estimate parameters of interest. The optimal validation sampling design for this analysis depends on the unknown efficient influence functions of regression coefficients of interest. In the first wave of our multiwave validation design, we estimate the influence function using the unvalidated (phase 1) data to determine our validation sample; then in subsequent waves, we re-estimate the influence function using validated (phase 2) data and update our sampling. We validated 996 of 10,335 mother-child EHR dyads in six sampling waves. Estimated associations between childhood obesity and maternal weight gain, as well as other covariates, are compared to naïve estimates that only use unvalidated data. In some cases, estimates markedly differ, underscoring the importance of efficient validation sampling to obtain accurate estimates incorporating validated data.