Real-time data in cancer registries: Validation of an automated data extraction system

Timely surveillance of cancer treatment requires real-time integration of electronic health records (EHR) data into population-based registries. We validated data from the Datagateway, an automated system that harmonizes structured EHR data across hospitals into a common model to support near real-time enrichment of the Netherlands Cancer Registry (NCR). Data from patients with acute myeloid leukemia, multiple myeloma, lung cancer, and breast cancer were extracted via the Datagateway and compared to NCR data and EHR source data. The system achieved 100% accuracy compared to registered NCR diagnoses, and an accuracy of 95% when comparing new diagnoses to the NCR inclusion criteria. Treatment was correctly identified in all cases, with only 3% of combination therapies misclassified. Laboratory values matched virtually completely; toxicity indicators showed 72%-100% accuracy. Automated real-time EHR data integration using a harmonized model is feasible and reliable, enabling scalable, high-quality support for real-world oncology research.