Measuring Patient Data Density in EHRs to Understand Bias
The EHR Density Index (EDI), a covariate that quantifies how far a patient's documentation deviates from that of clinically similar patients, developed and validated on approximately 25,000 UNC Health patients as an adjustment for documentation-density bias in electronic health record (EHR) studies.
Patients vary widely in how much data their electronic health records contain: sicker patients accumulate more. Comorbidity indices like Charlson and Elixhauser measure mortality risk, not documentation density. This project, with Emily Pfaff at the NC TraCS Institute, develops a covariate that lets analyses adjust for that uneven documentation.
A first manuscript is under review at the Journal of the American Medical Informatics Association. It introduces the EHR Density Index (EDI), which pairs utilization clusters from a Gaussian mixture model with within-cluster residuals across four OMOP domains (conditions, drugs, measurements, and procedures) to characterize how a patient’s documentation deviates from others with similar care patterns. The index was developed and validated on ~25,000 UNC Health patients.