The German-Canadian NephroCAGE Consortium is testing the safe application of artificial intelligence (AI) to multinational health data using chronic kidney disease as a use case. The project’s goal is to enable an international comparison of treatment strategies.
The project partners will create a learning AI system that will be used to match organ donors and recipients accurately in advance to reduce risks in kidney transplants and prevent organ damage. To this end, clinical centers of excellence in both nations are contributing transplant data from the past 10 years. They will be analyzed using artificial intelligence and combined with a novel matching algorithm to create clinical prognostic models for kidney transplant recipients. To enable the international comparison, a clinical prediction model is developed that allows combined analysis of clinical data, laboratory data, and genetics in kidney transplant patients.
By using a federated learning approach, the algorithms are transferred to the data: thus, data protection is maintained and the sensitive health data of both nations can serve as a common basis for clinical prediction models without having to leave the respective hospital.
Project Partners:
- Hasso-Plattner-Institut für Digital Engineering gGmbH (Project lead, Germany)
- Pirche AG (Germany)
- Charité – Universitätsmedizin Berlin (Germany)
- Karlsruher Institut für Technologie (Germany)
- The University of British Columbia (Canada)
- McGill University Health Centre (Canada)
- Genome Canada (Canada)
- Genome BC (Canada)
- Genome Quebec (Canada)
