This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 964220.

The AI-Mind method

Our multi-disciplinary consortium will follow the well-established cross-industry standard process for data mining CRISP-DM method, effectively combining scientific approaches and product development to delivery a cloud-based, easily accessible platform containing our AI-Mind Connector and Predictor. Our work will involve state of the art research, governance and scoping; implementation of results; innovation and creation of tools; delivery of prototypes; piloting; and market outreach.

The AI-Mind Data

As several aspects of the human body are affected by early dementia, we in AI-Mind will utilise several datatypes to best catch the disease development. These are EEG, MEG, genetics, serum-level analysis, cognitive data and background information. At the end of the project, the data will be available to all European research institutions through the European Open Science Cloud (EOSC) initiative. Prior to development and integration of the AI model, we will extract and process the EEG and MEG data to create brain network data for the AI-Mind Connector and Predictor.

The AI-Models

For the model development we will explore two AI approaches for development and integration of the AI-Mind tools: probabilistic ML using brain network features and DL modelling based on non-processed source-reconstructed data. These approaches will be evaluated through testing, bias control and assessment of predictive abilities to identify the most robust AI-based diagnostic candidates for integration into the AI-Mind connector platform.

The AI-Mind Tool-development

The developed AI-Mind Connector and Predictor tools will be delivered to clinicians through a digital sub-platform designed to directly process data input by end-users, perform analysis and reveal the risk of early-onset MCI. Feedback evaluation and assessment of the software architecture, graphic display, user-friendliness and tool utility will be carried out in collaboration with clinicians involved in AI-Mind and their associates.

Furthermore, to assess the clinical usefulness of the AI-Mind tools, we will map the trustworthiness of the service and preform health technology assessment to ensure maximum utilisation of our product for our end users.

Get Involved

Information Sheet