Building a Digital Health Twin for Personalized Intervention: The EPI Project
Jamila Alsayed Kassema, C. Allaart, Saba Amiria, Milen G. Kebedeb c, Tim Müller, Rosanne Turner, A. Bellouma c, L. T. van Binsbergenb, P. Grunwald, A. van Halteren, Paola Grossoa, C. de Laatb, S. Klousd e
- aMNS, University of Amsterdam, The Netherlands
- bCCI, University of Amsterdam, The Netherlands
- cMassachusetts Institute Of Technology#TAB#
- dUniversity of Amsterdam, The Netherlands
- eKPMG, Netherlands
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
Abstract
In this work, we introduce SplitNN-driven Vertical Partitioning, a configuration of a distributed deep learning method called SplitNN to facilitate learning from vertically distributed features. SplitNN does not share raw data or model details with collaborating institutions. The proposed configuration allows training among institutions holding diverse sources of data without the need of complex encryption algorithms or secure computation protocols. We evaluate several configurations to merge the outputs of the split models, and compare performance and resource efficiency. The method is flexible and allows many different configurations to tackle the specific challenges posed by vertically split datasets.
TL;DRAlgorithms and tools for algorithmic real-time response and analysis of distributed data at scale and the automatic enforcement of legal interpretations and data-sharing conditions as executable policies are described. (Semantic Scholar)