Unlocking the Potential of ML in Healthcare in a Privacy-Preserved Way with Federated Learning

DECODE: AI for Pharma - June 8, 2021
Speaker: Victor Dillard, Commercial Operations Director, Owkin

Abstract: Today’s standard approach of centralizing data from multiple medical centers comes with critical concerns regarding patient privacy. Training machine learning models at scale across multiple institutions without moving the data is a technology addressing this problem. Federated Learning is a new learning paradigm to train models from data siloed and distributed over multiple independent providers in a privacy-preserving way, that ultimately overcomes the data sharing bottleneck in healthcare