Pitfalls in Analyzing FHIR Data from Different University Hospitals

Abstract

The German Medical Informatics Initiative has agreed on a HL7 FHIR-based core data set as the common data model that all 37 university hospitals use for their patient's data. These data are stored locally at the site but are centrally queryable for researchers and accessible upon request. This infrastructure is currently under construction, and its functionality is being tested by so-called Projectathons. In the 6th Projectathon, a clinical hypothesis was formulated, executed in a multicenter scenario, and its results were analyzed. A number of oddities emerged in the analysis of data from different sites. Biometricians, who had previously performed analyses in prospective data collection settings such as clinical trials or cohorts, were not consistently aware of these idiosyncrasies. This field report describes data quality problems that have occurred, although not all are genuine errors. The aim is to point out such circumstances of data generation that may affect statistical analysis.