Background Electronic health record (EHR) systems contain large volumes of novel heterogeneous data that can be linked to trauma registry data to enable innovative research not possible with either data source alone.
Objective This article describes an approach for linking electronically extracted EHR data to trauma registry data at the institutional level and assesses the value of probabilistic linkage.
Methods Encounter data were independently obtained from the EHR data warehouse (n = 1,632) and the pediatric trauma registry (n = 1,829) at a Level I pediatric trauma center. Deterministic linkage was attempted using nine different combinations of medical record number (MRN), encounter identity (ID) (visit ID), age, gender, and emergency department (ED) arrival date. True matches from the best performing variable combination were used to create a gold standard, which was used to evaluate the performance of each variable combination, and to train a probabilistic algorithm that was separately used to link records unmatched by deterministic linkage and the entire cohort. Additional records that matched probabilistically were investigated via chart review and compared against records that matched deterministically.
Results Deterministic linkage with exact matching on any three of MRN, encounter ID, age, gender, and ED arrival date gave the best yield of 1,276 true matches while an additional probabilistic linkage step following deterministic linkage yielded 110 true matches. These records contained a significantly higher number of boys compared to records that matched deterministically and etiology was attributable to mismatch between MRNs in the two data sets. Probabilistic linkage of the entire cohort yielded 1,363 true matches.
Conclusion The combination of deterministic and an additional probabilistic method represents a robust approach for linking EHR data to trauma registry data. This approach may be generalizable to studies involving other registries and databases.
Linking Electronic Health Record and Trauma Registry Data: Assessing the Value of Probabilistic Linkage
