This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 964220. This website reflects only the author’s view and the Commission is not responsible for any use that may be made of the information it contains.

The AI-Mind method

In AI-Mind, two new artificial-intelligence-based medical devices will be developed to rapidly and precisely identify and assess dementia risks in people with mild cognitive impairment (MCI). Through international collaboration, consortium members effectively combine various scientific approaches and product development activities, which 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

The cutting-edge of the AI-Mind model development and testing is done by available retrospective and new prospective data collected at the five clinical centres: in Finland (HUS), Italy (IRCCS/UCSC), Norway (OUS), and Spain (UCM).

The AI-Mind data spans from acquiring the EEG/MEG data, digital cognitive testing, blood samples, and textual data from questionnaires and neuropsychological testing (NPT), to managing the (pseudonymised) clinical data at the respective sites. The data collection is implemented through a recruitment of 1000 MCI subjects, who provided signed Informed Consent before entering the study.

The AI-Models

For the model development we explore two AI approaches for development and integration of the AI-Mind tools: probabilistic machine learning (ML) using brain network features and deep learning (DL) modelling based on non-processed source-reconstructed data. These approaches are being 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

As part of the framework development, the use of early health technology assessment (HTA) will be explored. Early HTA includes modelling of the potential cost-effectiveness of the implementation of new technologies and can give decision makers an indication of which potential health gain and/or cost savings are associated with a technology adoption.

Furthermore, 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.