From population-based cancer registration to quality registries: the Polish National Cancer Registry as an integrated oncology data ecosystem

Background and purpose Population-based cancer registries provide an essential data source for epidemiological research and surveillance. This article presents the organizational and functional architecture of Poland's electronic Polish National Cancer Registry (e-PNCR) platform, an integrated data ecosystem designed to modernize national cancer registration and support the development of high-granularity quality registries. Materials and methods Implemented in 2023, the e-PNCR platform centralizes nationwide data acquisition, integrating multi-institutional real-world data (RWD) via automated hospital network exports (Enterprise Service Bus) and structured web interfaces. Natural language processing (NLP) models extract registry-relevant concepts from unstructured clinical documents, followed by automated validation compliant with European Network of Cancer Registries/Joint Research Center recommendations. Results The platform utilizes a modular architecture to support disease-specific quality registries. Frameworks such as the Polish Onco-Hematological Registry are deployed directly as structural extensions of the core national infrastructure. This paradigm allows new registries to reuse existing standardized terminologies and validation rules without modifying external hospital interfaces. Furthermore, the integrated NLP pipelines extract clinical information with an average sensitivity and positive predictive value of ∼87%, streamlining case registration while maintaining mandatory expert verification. Conclusions The e-PNCR platform establishes a highly scalable paradigm for national cancer registration, facilitating the efficient generation of high-quality RWD. By leveraging a shared technological infrastructure, the deployment of specialized quality registries requires substantially fewer resources. Crucially, the platform's standardized data environment increases the registry's readiness for seamless future integration with European data-sharing initiatives, including the European Health Data Space.