Application of extreme analytic methods in healthcare
Exascale volumes of diverse healthcare data stand out in size (the 2020 production exceeded 2 000 exabytes), heterogeneity (numerous media and acquisition methods), knowledge (diagnostic reports) and commercial value. The supervised nature of deep learning models requires large labelled, annotated data, preventing models from extracting knowledge and value. The aim of the EU-funded EXA MODE project is to allow easy and fast, weakly supervised knowledge discovery of exascale heterogeneous data, limiting human interaction. The project objectives include the development and release of new methods and tools for extreme-scale analytics for precise predictions, supporting decision making by industry and hospitals. The multimodal semantic middleware will offer easier and faster management and analysis of heterogeneous data, improving architectures for complex distributed systems and increasing the speed of data throughput and access.
Fields of science
Call for proposal
See other projects for this call
Funding SchemeRIA - Research and Innovation action
53 135 Wroclaw
1098 XG Amsterdam