A paper by Daniel Petersheim was published in the journal “nature”
In the article "Swarm Learning for decentralized and confidential clinical machine learning", the re-searchers present Swarm Learning, a decentralized approach to machine learning.
Machine learning can be used to identify patients with leukaemia. However, there is an increasing gap between what is technically feasible and what is allowed by data protection laws. Swarm learn-ing is an approach to facilitate the integration of any medical data from any data owner worldwide without violating privacy laws.
To illustrate the feasibility of using Swarm Learning to develop disease classifiers using distributed data, four use cases of heterogeneous diseases (COVID-19, tuberculosis, leukaemia and lung pa-thologies) had been chosen. 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 the scientists could show, that Swarm Learning classifiers out-perform those developed at individual sites.
Collectively, Swarm Learning and transcriptomics (or other medical data) are a very promising ap-proach to democratize the use of AI among the many stakeholders in the domain of medicine, while at the same time resulting in improved data confidentiality, privacy, and data protection, and a decrease in data traffic.
Congratulations to Daniel Petersheim!