Intel and the University of Pennsylvania have announced they are co-developing a technology to enable a federation of 29 international healthcare and research institutions led by Penn Medicine to train artificial intelligence (AI) models that identify brain tumours. Called 'federated learning', the technique involves a distributed machine learning approach that enables organisations to collaborate on deep learning projects. Intel argues that the technology is privacy-friendly, as the involved organisations do not have to share patient data: federated learning will be used to 'produce a new state-of-the-art artificial intelligence model that is trained on the largest brain tumour dataset to date - all without sensitive patient data leaving the individual collaborators'.