The ASME-ASCAPE Architecture
The ASME (Artificial intelligence Supporting CAncer Patients across Europe) project, carried out by ZELUS and Stockholm University, will adapt the ASCAPE Open AI Infrastructure to make use of the ASME Research Dataset (thus creating the ASCAPE-ASME Research Prototype). This will be one of the project’s key outcomes.
The ASCAPE has created an Open-AI Framework with Federated Learning and Homomorphic Encryption capabilities. Such a framework is meant to facilitate new AI applications in the health domain with minimal effort. The ASCAPE Open AI framework is meant to not only provide state-of-the-art AI algorithms, but a well-designed platform that lets integrators create a new application or enhance old ones using ASCAPE AI in a manner that preserves the privacy of patients on the one hand, keeping data local at the site of the healthcare provider, but permits the sharing of knowledge obtained from their data in order to advance the state of the AI models at a global scale. The ASME-ASCAPE prototype will be based on the ASCAPE Open AI Framework but be able to ingest the (anonymized) patient data in the ASME Research Dataset. Its architecture was designed by ZELUS based on the ASCAPE AI Framework’s architecture and its implementation is planned to be completed in the forthcoming months.
ASME (Artificial intelligence Supporting CAncer Patients across Europe), is a sub-project of the Horizon 2020 project ASCAPE (Artificial intelligence Supporting CAncer Patients across Europe). ASCAPE has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 875351.