We need to make biomedical data easily accessible and securely usable, to find new medicines and diagnostics, and to establish data-based insights that evolve the practice of medicine.
How a MedTech company built up the capability for reliable and strategic data access to thousands of annotated MRI scans from several hospitals
How a data science team in a pharma company collaborated with hospitals and institutions to securely leverage cancer patient data for AI
How a genomics company analyzed genomics data from laboratories at scale
In recent years, Deep Learning has gained considerable traction in many fields, but none more so than in the realm of drug discovery. Applications range from generating de novo hit-like molecules, predicting drug-disease associations and activity, toxicology estimation, to the analysis of medical images.
Joining complementary data sets creates stronger machine learning capabilities. But valuable data containing intellectual property cannot be shared and must adhere to regulatory frameworks. Healthcare companies can use federated learning to work with decentralized data, allowing secure collaboration without sharing data.
In our daily work as a company that builds a platform for federated and privacy-preserving data science, we are often asked to clarify concepts around federated learning with customers. This article highlights 7 common myths about federated learning (FL) and, using practical examples, shows you exactly why they are misleading.