Linking cancer registry data and multimodal diagnostic data for AI-based biomarker detection (CanConnect)

Project duration: September 2022 to August 2025

Motivation

The development of better cancer therapies requires comprehensive case data describing 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 tumor cases and make them available to research. Each patient and each cancer are highly individual. Therefore, case data must be very detailed and contain, in particular, molecular, cellular and immunological information. Currently, however, the data reported to the cancer registries describe tumor cases only roughly and partially. This makes research into cancer types and the development of patient-specific therapies much more difficult. 

Goals 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 data linkage concept that makes extensive, detailed case data usable for research while ensuring the protection of patient data. The feasibility and usefulness of the developed linkage concept will be demonstrated using the use case "glioblastoma", a malignant brain tumor. For this purpose, the developed linkage concept is applied to enrich cancer registry data with further diagnostic data from pathology. The linked data will be analyzed using artificial intelligence (AI) methods 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 data linkage concepts developed are to be considered in the design of the future central application and registry office at the Center for Cancer Registry Data. For patients, further research building on the results of this project could lead to more precise and effective treatments. 

© Fraunhofer MEVIS
Linking cancer registry datasets with other decentralized diagnostic data for AI-based biomarker research