Periodic Reporting for period 2 - AISN (Integrating AI in Stroke Neurorehabilitation)
Reporting period: 2024-06-01 to 2025-11-30
The AISN project aims to revolutionize post-stroke rehabilitation by integrating AI into healthcare, addressing a critical global health issue. It will specifically look at how the integration of AI in neurorehabilitation in affects treatment pathways. AISN's comprehensive AI health platform integrates validated systems for data acquisition, clinical interpretation, whole-brain simulation, and intervention delivery. This platform will be validated, transforming care pathways and informing new treatment guidelines. AISN emphasizes ethical AI deployment by developing robust legal and ethical guidelines, ensuring fair and trustworthy implementation, and validating acceptance and transparency. The project focuses on evidence-based interventions, transparency, prognostics, personalized treatments, and information access for clinicians, patients, and caregivers. Stroke's economic burden is significant, with annual costs of 60 billion euros in Europe. AISN's AI-enhanced healthcare aligns with Value-Based Healthcare (VBHC) principles, linking reimbursement to clinical outcomes, enhancing results, and reducing costs. The project tackles barriers to AI adoption, such as staff shortages, skill gaps, and interoperability issues, offering a TRL6 integrated platform for AI-enhanced VBHC. To achieve these outcomes, AISN has 4 key objectives:
1. AISN AI-enhanced stroke neurorehabilitation Platform.
2. AI-based Decision-Support Module for Clinicians.
3. Clinical validation and guidelines for long-term stroke care.
4. Inclusion of clinicians, patients, and caregivers through the AISN education platform.
During Months 19–36, the AISN project transitioned from architectural design to the delivery of an operational, trial-ready digital health platform. The technical core is now consolidated around the Medical Information Management System (MIMS), Prognostics and Recommender Systems, and the Clinical Decision Support System (CDSS), which enables a "clinician-in-the-loop" workflow for personalised stroke rehabilitation, which is embedded in a broader “patient-in-the-loop” system delivering the RGS interventions to patients at home. This GDPR and AI-act compatible AI-enhanced pipeline is deployed and working, and a major milestone was achieved in October 2025 with the commencement of the AISN multicentre Randomised Controlled Trial (RCT) (Italy and Romania). The consortium has ensured a streamlined and robust environment for trial data collection using a certified EDC platform (Datacapt). The consortium in parallel has developed guidelines and standards to ensure the ethical and legal frameworks for the integration of AI in healthcare.
1. AISN AI-enhanced stroke neurorehabilitation Platform.
2. AI-based Decision-Support Module for Clinicians.
3. Clinical validation and guidelines for long-term stroke care.
4. Inclusion of clinicians, patients, and caregivers through the AISN education platform.
During Months 19–36, the AISN project transitioned from architectural design to the delivery of an operational, trial-ready digital health platform. The technical core is now consolidated around the Medical Information Management System (MIMS), Prognostics and Recommender Systems, and the Clinical Decision Support System (CDSS), which enables a "clinician-in-the-loop" workflow for personalised stroke rehabilitation, which is embedded in a broader “patient-in-the-loop” system delivering the RGS interventions to patients at home. This GDPR and AI-act compatible AI-enhanced pipeline is deployed and working, and a major milestone was achieved in October 2025 with the commencement of the AISN multicentre Randomised Controlled Trial (RCT) (Italy and Romania). The consortium has ensured a streamlined and robust environment for trial data collection using a certified EDC platform (Datacapt). The consortium in parallel has developed guidelines and standards to ensure the ethical and legal frameworks for the integration of AI in healthcare.
The technical core of the AISN platform is defined by the seamless integration of patient-facing intervention tools and clinician-facing decision-support systems. At the centre of this ecosystem is the Medical Information Management System (MIMS), which acts as the primary clinician interface for managing patient profiles and executing training prescriptions. The platform utilises advanced prognostics derived from dynamical statistical models to predict recovery trajectories, which directly inform the recommender system. This core component of the CDSS ranks RGSapp protocols using a multi-objective therapeutic score that aligns patient needs with intervention parameters. Progress is monitored via the integrated dashboard in MIMS, which provides human-readable explanations of AI recommendations and ensures an accountable workflow throughout the rehabilitation continuum.
The multicentre RCT was successfully launched in October 2025. As of January 2026, recruitment progress is as follows: 29 patients have been screened at IRCCS (Italy), and 6 patients have been enrolled and initiated intervention at UMF (Romania). This early recruitment confirms the feasibility of the randomisation procedures and the integration of AISN technologies into routine care.
The multicentre RCT was successfully launched in October 2025. As of January 2026, recruitment progress is as follows: 29 patients have been screened at IRCCS (Italy), and 6 patients have been enrolled and initiated intervention at UMF (Romania). This early recruitment confirms the feasibility of the randomisation procedures and the integration of AISN technologies into routine care.
AISN has achieved a number of beyond the state of the art results which include:
New Biomarkers for Recovery: The project has identified metastability and synchrony as potential biomarkers for stroke recovery.
Scale-Free Clinical Assessment: New pipelines for extracting kinematic variables have been developed, allowing for "clinical scale-free" assessments of patient recovery.
Technological Infrastructure: A substantial advancement was made through the deployment of a Docker-based infrastructure featuring a Vector DB and FastAPI for the recommender engine.
Integrated AI Diagnostics & Prognostics: The successful integration of diagnostic and prognostic algorithms into the platform enabling real-time prediction improving the efficiency and accuracy of clinical decision-making.
User-Centric Innovations: Advancements in the RGSapp include personalised and interactive elements, such as video tutorials and enhanced cybersecurity protocols, ensuring a robust and secure user experience for home-based rehabilitation.
The Patient Aware Coach: integrated into the RGSapp to support home-based rehabilitation. The system provides personalised coaching driven by machine learning algorithms, monitoring patient performance and progress. The coach system works in tandem with the clinician-facing MIMS dashboard, ensuring progress is continuously monitored and AI recommendations are explained to clinicians.
Improved Device Usability: Ongoing refinements to RGSweb and RGSwear have increased the usability and data accuracy of these tools, while the MIMS platform has been upgraded to address specific patient needs through personalised features.
The AISN project has advanced the state of the art in stroke neurorehabilitation by delivering a fully integrated, trial-ready digital health platform that uniquely combines objective, scale-free kinematic assessments with AI-driven real-time diagnostics and prognostics.
Scalability: The optimisation of AI modules for scalability ensures the platform can support larger clinical populations and more complex data-intensive research steps.
Ethics and law: The AISN project has advanced beyond the state of the art by transitioning from abstract principles to operationalised tools and novel research on human-AI interaction, such as Relational Transparency and Autonomy. AISN has developed and deployed the IDEA Framework Operational Governance Tools to bridge the Principle-to-Practice Gap, enabling Defensible Decisions. AISN has moved beyond general compliance to provide specific, project-tailored legal guidance on the EU AI Act and the Medical Devices Regulation (MDR) and addressed AI Act Integration, the European Health Data Space (EHDS), the Data Act, and the Data Governance Act to guide the lawful and secure sharing of medical data.
New Biomarkers for Recovery: The project has identified metastability and synchrony as potential biomarkers for stroke recovery.
Scale-Free Clinical Assessment: New pipelines for extracting kinematic variables have been developed, allowing for "clinical scale-free" assessments of patient recovery.
Technological Infrastructure: A substantial advancement was made through the deployment of a Docker-based infrastructure featuring a Vector DB and FastAPI for the recommender engine.
Integrated AI Diagnostics & Prognostics: The successful integration of diagnostic and prognostic algorithms into the platform enabling real-time prediction improving the efficiency and accuracy of clinical decision-making.
User-Centric Innovations: Advancements in the RGSapp include personalised and interactive elements, such as video tutorials and enhanced cybersecurity protocols, ensuring a robust and secure user experience for home-based rehabilitation.
The Patient Aware Coach: integrated into the RGSapp to support home-based rehabilitation. The system provides personalised coaching driven by machine learning algorithms, monitoring patient performance and progress. The coach system works in tandem with the clinician-facing MIMS dashboard, ensuring progress is continuously monitored and AI recommendations are explained to clinicians.
Improved Device Usability: Ongoing refinements to RGSweb and RGSwear have increased the usability and data accuracy of these tools, while the MIMS platform has been upgraded to address specific patient needs through personalised features.
The AISN project has advanced the state of the art in stroke neurorehabilitation by delivering a fully integrated, trial-ready digital health platform that uniquely combines objective, scale-free kinematic assessments with AI-driven real-time diagnostics and prognostics.
Scalability: The optimisation of AI modules for scalability ensures the platform can support larger clinical populations and more complex data-intensive research steps.
Ethics and law: The AISN project has advanced beyond the state of the art by transitioning from abstract principles to operationalised tools and novel research on human-AI interaction, such as Relational Transparency and Autonomy. AISN has developed and deployed the IDEA Framework Operational Governance Tools to bridge the Principle-to-Practice Gap, enabling Defensible Decisions. AISN has moved beyond general compliance to provide specific, project-tailored legal guidance on the EU AI Act and the Medical Devices Regulation (MDR) and addressed AI Act Integration, the European Health Data Space (EHDS), the Data Act, and the Data Governance Act to guide the lawful and secure sharing of medical data.