An international team of scientists unveiled an artificial intelligence (AI) technique that securely analyses global cancer samples, paving the way for more personalised and privacy-protected cancer treatments. This innovative approach promises to accelerate personalised cancer treatment by enabling clinicians to match therapies to individual patients better.
The study involved the analysis of protein profiles from 7,525 cancer samples collected by 30 collaborating research groups across six countries.
Strict privacy laws and technical differences in lab methods have long made it difficult to combine large cancer datasets, said the researchers led by Australia’s Children’s Medical Research Institute (CMRI). To overcome these obstacles, the CMRI team in Sydney used federated deep learning, training AI models locally so that only insights, not sensitive data, were shared with a central server, which allowed them to build an accurate global diagnostic tool without transferring patient information between institutions.
Must Read
- Advertisement -
