In early 2023, a new research project establishing an Open Consortium for Decentralized Medical Artificial Intelligence (ODELIA) began. It is funded by the EU with the aim of using Swarm Learning (SL) to transform artificial intelligence in healthcare.
Over the next several years, partners will work together to train AI models without requiring the need to share personal patient data. ODELIA will overcome the obstacles of data collection and data sharing, and accelerate the scale-up of medical AI in Europe.
One of the primary challenges in implementing AI in healthcare is that there are not enough large datasets to train models with, or there are too many ethical and legal obstacles to overcome. ODELIA hopes to tackle these challenges by implementing a novel approach to AI training, known as SL, which will allow for privacy-conserving training of medical AI algorithms without compromising data privacy.
ODELIA aims to build the first open-source software framework for SL, providing an assembly line for the streamlined development of AI solutions.
ODELIA partners will work together to develop the first clinically useful AI algorithm to aid in the detection of breast cancer in magnetic resonance imaging (MRI). The size of ODELIA's distributed database will exceed all previous studies and ODELIA’s AI models will reach expert-performance for screening in breast cancer. ODELIA will not only deliver a useful medical application, but it will also highlight the clinical benefit of SL regarding fast development, high speed performance, and robust generalisability to ultimately save thousands of lives.
Image Source: iStock