The EuroCAT project: Large-scale research into cancer treatment

Nineteen organizations across the world are collaborating on the ambitious EuroCAT project to develop a shared database of medical characteristics in cancer patients, tumors and treatments. Copying data from existing databases and linking them together on a larger scale will greatly improve our ability to learn and predict the outcome of individual treatments within the next three years. In other words: we will be able to dramatically improve the quality of treatment each individual cancer patient receives by skillfully mining the available data and treatment results of many patients. This can be achieved through extensive, cross-border and cross continental cooperation among the parties.

Long-cherished dream

MUMC+ is the leading partner and initiator of this cross-border platform. Professor Dr Phillippe Lambin, is excited about the breakthrough. "Realizing this database has been a long-cherished dream," he says. "This project will be revolutionary in terms of cancer research and treatment. Nowhere else in the world will there be this much specific information available in one place. This will greatly facilitate personalizing medicine by making multifactorial Decision Support systems continuously updated by new data"

Additional benefits

Another big advantage is that the project facilitates cooperation among all parties involved. The infrastructure for this project can also serve as the foundation for trials within other disciplines (e.g. chronic disease) and may be used to further develop therapy. The IT infrastructure, which stores vast amounts of data, is also greatly appealing to medical companies - like pharmaceutical companies, for instance - that develop new cancer medications. The project will act as a catalyst for clinical trials and the development of new medications as research results can be quickly and efficiently collected and validated on a large scale.

Privacy guaranteed

All personal information entered into the EuroCAT database is safeguarded and kept anonymous. We used the approach of federated databases with distributed learning. "This is the solution for Big Data in health care because the data of the patient will never leave the firewalls of the hospitals: we only move "metadata", says prof. P. Lambin. The system also takes into account the privacy laws of the different countries. Furthermore information will never be used from patients who have raised objections.