< Back to previous page
Project
IOF Proof of Concept: NEED - NEUR-o-AIMS federated learning demonstrator (IOFPOC57)
In this project, we will create the first international collaboration that performs federated machine learning in multiple
sclerosis. The idea is that data acquired by clinical centres remains at the institution but is still accessible for
machine learning research. In this way, data does not have to be shared and stored in one central database, which
is difficult to achieve in light of strict hospital data sharing policies and regulations such as the GDPR. The first
centre that will enter the federated learning network is the general academic hospital in Prague (VFN v Praze), after
which we aim to include partner institutes in Greifswald, Naples and Bern. We will use this this federated learning
network to answer research questions in Multiple Sclerosis, namely whether we can predict their (future) cognitive
performance based on their brain image.
sclerosis. The idea is that data acquired by clinical centres remains at the institution but is still accessible for
machine learning research. In this way, data does not have to be shared and stored in one central database, which
is difficult to achieve in light of strict hospital data sharing policies and regulations such as the GDPR. The first
centre that will enter the federated learning network is the general academic hospital in Prague (VFN v Praze), after
which we aim to include partner institutes in Greifswald, Naples and Bern. We will use this this federated learning
network to answer research questions in Multiple Sclerosis, namely whether we can predict their (future) cognitive
performance based on their brain image.
Date:1 Jan 2023 → Today
Keywords:deep learning, federated learning, multiple sclerosis, big data, brain age
Disciplines:Neurological and neuromuscular diseases
Project type:Collaboration project