Data Management Plan

A Data Management Plan (DMP) is a key element of good data management. A DMP describes the data management life cycle for the data to be collected, processed and/or generated. The data collection workflows are described in the DMP. AISN will consider the FAIR priciples (making research data findable, accessible, interoperable and re-usable).

Ethical and Legal Framework

AISN includes AI technologies in various domains, including diagnostics, data classification and compression, prognostics, adaptive control of treatment protocols and whole-brain modelling. We describe advances in these areas and their relevance in AISN.

Each AI-enhanced component of the AISN pipeline challenges existing guidelines and policies and thus defines concrete questions for developing new regulatory frameworks and guidelines.

Development plan

AISN will define the requirements and specifications of the digital brain health platform. The work package leader will coordinate, plan, and follow up on the software development process of the platform`s technical components: development, testing, documentation, release, and maintenance. Through this process, we will also ensure that clinical partners provide feedback on the technical requirements and design of the AI modules, interfaces and applications from the early stages of the development process.

AISN architecture

Based on the existing’s platforms for data acquisition and access (EBRAINS), clinical interpretation and simulation (Virtual Research Environment, CHARITE) and intervention planning, delivery, and optimisation (Rehabilitation Gaming System (RGS), EODYNE), we will configure and adapt these platforms and services for the AISN data and services. The objective is to deploy the applications in a cloud infrastructure to provide i) secure data storage, online data collection during the clinical trial and processing, ii) AI components for training and executing diagnostics, prognostics and closed-loop decision support, iii) intervention and reporting applications to deliver rehabilitation services and iv) access to Knowledge Graphs and High-Performance Computer (HPC).

AISN protocols

The adaptation of the intervention systems is connected with the AI decision support modules.  
The overall User Experience will be redesigned to include the new functionality of the AI modules and the adaptive intervention module that controls several parameters of the intervention and how this parameter affects the overall experience such as selecting which intervention protocols are more suitable, the time or the difficulty levels. This will also consider how this information is communicated to the patient, integrating the newly developed functionalities.

Clinical trial

The AISN platform will be validated in a clinical trial where AISN will assess the performance of the system (e.g., diagnostics and prognostics), as well as usability, safety and cost-efficiency during training at home against a control group that will receive therapy as usual. The insights gained from developing the AI-based solution and its validation will be used to formulate treatment guidelines for long-term quality stroke care.

The clinical partners and the sponsor will prepare the design of the clinical trial and the ethical and regulatory approval, establish the
monitoring units, and preparing the education platform for patients.

Education platform

The AISN consortium will develop materials based on case studies to educate the public and professionals about the issues related to ethics and data management. These will include case scenarios that tackle challenges related to bias in machine learning, paternalism, privacy, and consent. The cases will raise questions about how far developers should go in identifying potential harms caused by technology and how error rates can be minimalised for a therapeutic technology that can potentially cause harm. They will also present opportunities to engage with issues of paternalism and the use of data to “nudge” end users based on data collected, as well as elucidate how decisions to use data are made, who makes those decisions, and who needs to be informed by them.

Clinical impact

AISN, specifically the decision support component, needs to be assessed and validated in terms of performance, including its clinical impact, diagnostics and prognostics, usability, safety and cost-efficiency, in close collaboration with healthcare professionals, their patients and caregivers.
We hypothesise that the AISN decision support solution, its recommender system and its diagnostic-prognostic interface will be highly accepted by healthcare professionals in terms of usability, credibility and time needed to prescribe training protocols. We also predict that the system will be more effective and efficient in assessing the progress (e.g. diagnostics and prognostics) of patients after the therapy and will be more cost-effective than current standard-of-care treatments. Finally, we prospect that the system will be deemed safe and trustworthy by clinicians, patients and their caregivers.

Sustainability strategy

The Innovation Strategy will ensure that innovative ideas that surface from project activities will be timely captured and meticulously investigated in terms of commercialisation potential.
AISN will focus on the main exploitable assets of the project, the main target groups of external stakeholders and the potential benefits they stand to gain from AISN outcomes, sustainability actions towards their post-project exploitation and continuation.

Business plan

AISN aims to produce a set of commercially viable AI services and sustainable business models for neurorehabilitation, taking into account the needs of our potential users/customers as well as the interests and visions of AISN partners. We build upon the valuable market intelligence produced inside the AISN project in order to gain a firm understanding of the target market and its structure. We will perform a market analysis aiming at capturing the main characteristics of the addressable market, its segments, size, competition and existing value-added networks. Our view is threefold: identify market deficiencies, underserved market segments, and potential areas for improvement that AISN services could better address compared to the competition. As such, the foreseen competition analysis will also aim at assisting AISN positioning in the European and global markets, while it is expected to reveal potential local value-added networks on which we could capitalise to strengthen our value proposition and offering.

Workplan in a nutshell

The AISN project has a duration of 48 months, divided in three phases.

During the first phase (Q4 2022-Q2 2023): AISN will focus on setting up the data management plan, organize the data collection workflows, set up the ethical and legal framework and the development plan, defining the requirements and specifications of the technology, and performing market analysis.

The second phase (Q3 2023-Q4 2024) will focus on

  • setting up the components of the AISN architecture: the cloud infrastructure, the data collection, and processing workflows, the AI modules, intervention protocols for rehabilitation and
  • preparing the design of the clinical trial and the ethical and regulatory approval, establishing the monitoring units, and preparing the education platform for patients.

Finally, in the third phase (Q1 2025-Q4 2026), AISN will evaluate the clinical impact, usability, safety, and cost-efficiency of the AISN solution and the acceptance and uptake of the users. In this phase the business plan and the sustainability strategy will be finalised.

General Assembly

The AISN General Assembly is the highest decision making body and is responsible for the overall direction of the project and decides on all major issues. The General Assembly members are:


GA member


Radboud University

Paul Verschure

Mohamed Eledeisy


Ton Coolen

Theodore Nikoletopoulos

Eodyne systems

Santiago Brandi

Gerónimo Galíndez


Ciprian Ciulpan



Jorge Posada

Berta Borras


Petra Zalud

Boris Nalbach

University of Vienna

Nikolaus Forgo

Michael Schmidbauer

San Camillo IRCCS

Francesca Burgio

Andreina Giustiniani

Institut de Recerca Sant Joan de Déu

Íñigo Chivite

Clara Szymanski

Limoges University

Stéphane Mandigout


Charité – Universitätsmedizin Berlin

Petra Ritter

Dionysios Perdikis

Centre Hospitalier Universitaire de Limoges

Stéphane Mandigout


Universitätsspital Bern

Adrian Guggisberg


University of Oxford

Julian Savulescu

Hazem Zohny