Record linkage of cancer registry data and multimodal, reporting-based diagnostic data for Al-based biomarker detection
The development of better cancer therapies requires comprehensive case data that describe the respective clinical picture, the response to therapy and the course of the disease. For this reason, the German cancer registries systematically collect data on cancer cases and make them available for research. Every patient and every cancer are highly individual. Therefore, case data must be very detailed and contain molecular, cellular and immunological information in particular. Reports to the cancer registries are based on a defined data set. Therefore, the inclusion of further diagnostic data and the linking of this data with the cancer registry data has great potential for research into cancer types and the development of patient-specific therapies.
Aims and approach
The CanConnect project aims to link cancer registry data with diverse diagnostic data from reporting hospitals. The focus is on the development of a general linking concept that makes extensive, detailed case data usable for research and at the same time ensures the protection of patient data. The feasibility and benefit of the developed linking concept will be demonstrated using the use case "glioblastoma", a malignant brain tumor. For this purpose, the developed linking concept is used to enrich cancer registry data with further diagnostic data from pathology. The linked data will be analysed using artificial intelligence (AI) methods in order to derive new diagnostic parameters (so-called biomarkers) for glioblastoma as an exemplary application.
Perspectives for practice
The CanConnect project is intended to make a significant contribution to being able to use cancer registry data more effectively for cancer research. The developed data linkage concepts are to be considered in the design of the planned national platform for the nationwide evaluation of clinical cancer registry data. For patients, research results based on this could result in more precise and effective treatment methods.
- Begin: September 2022
End: August 2025
- Federal Ministry of Health
- Andreas Schreiber, Fraunhofer Institute for Digital Medicine MEVIS