Swarm Learning for decentralized and confidential clinical machine learning

TLDR

Fast, reliable detection of severe heterogeneous illnesses is a key goal of precision medicine, yet privacy legislation increasingly limits data sharing. The study introduces Swarm Learning, a decentralized machine‑learning framework that enables privacy‑preserving integration of medical data across global sites, demonstrated on COVID‑19, tuberculosis, leukaemia, and lung pathology classifiers. Swarm Learning combines edge computing, blockchain‑based peer‑to‑peer networking, and decentralized coordination to train models without a central server. Using 16,400 transcriptomes and 95,000 chest X‑ray images, Swarm Learning classifiers outperformed site‑specific models, fully complied with local confidentiality regulations, and promise to accelerate precision medicine.

Abstract

Fast and reliable detection of patients with severe and heterogeneous illnesses is a major goal of precision medicine1,2. Patients with leukaemia can be identified using machine learning on the basis of their blood transcriptomes3. However, there is an increasing divide between what is technically possible and what is allowed, because of privacy legislation4,5. Here, to facilitate the integration of any medical data from any data owner worldwide without violating privacy laws, we introduce Swarm Learning-a decentralized machine-learning approach that unites edge computing, blockchain-based peer-to-peer networking and coordination while maintaining confidentiality without the need for a central coordinator, thereby going beyond federated learning. To illustrate the feasibility of using Swarm Learning to develop disease classifiers using distributed data, we chose four use cases of heterogeneous diseases (COVID-19, tuberculosis, leukaemia and lung pathologies). With more than 16,400 blood transcriptomes derived from 127 clinical studies with non-uniform distributions of cases and controls and substantial study biases, as well as more than 95,000 chest X-ray images, we show that Swarm Learning classifiers outperform those developed at individual sites. In addition, Swarm Learning completely fulfils local confidentiality regulations by design. We believe that this approach will notably accelerate the introduction of precision medicine.