ASH 2025 | Federated learning to train generative AI models for diagnosis & prognosis of hematological diseases
Gianluca Asti
• 7 Dec 2025
In this video, Gianluca Asti, MSc, Humanitas Clinical and Research Center, IRCCS, Rozzano, Italy, discusses the use of federated learning to train generative artificial intelligence (AI) models for diagnosis and prognosis of hematological diseases without sharing patient data. He explains how this technology enables the creation of high-quality synthetic patient datasets while preserving privacy and improving model performance. This interview took place at the 67th ASH Annual Meeting and Exposition, held in Orlando, FL.
These works are owned by Magdalen Medical Publishing (MMP) and are protected by copyright laws and treaties around the world. All rights are reserved.
