AI-based Model for Rehabilitation Engagement and Motor Performance Evaluation in Pediatric Patients: A Pilot Study (AI-REMAP)

AI-based Model for Rehabilitation Engagement and Motor Performance Evaluation in Pediatric Patients

What is the purpose of this study? This study aims to evaluate the usability and feasibility of an artificial intelligence-based model designed to monitor in real-time the engagement and motor performance of pediatric patients during technology-assisted rehabilitation.

Who can take part? 15 participants between 5 and 17 years old with neuromotor impairments will take part, along with at least 5 of their referring physiotherapists.

What will happen in the study? Each pediatric patient will take part in a single, 1-hour rehabilitation session using either the Lokomat or GRAIL system, according to their standard clinical prescription. During the session, the physiotherapist will have access to a display showing real-time data from the AI model, including the patient's heart rate, engagement level, pleasantness, activation, and motor performance. At the end of the session, the physiotherapist will complete a System Usability Scale (SUS) questionnaire and provide direct feedback on how to improve the model.

Why is this study important? Assessing the usability of this real-time monitoring tool is a necessary step to understand if it is practical for clinical use. Providing therapists with objective, real-time insights into a child's psychological and physical state can ultimately help tailor therapy to the specific needs of each patient, improving the overall rehabilitation experience.

Study Overview

• Status: Not yet recruiting
• Conditions: Neuromotor Impairments
• Intervention / Treatment: Device: Artificial Intelligence Model for Rehabilitation Engagement Monitoring

• Study Type: Interventional
• Enrollment (Estimated): 15
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Simone Costantini, MSc; Email: simone.costantini@lanostrafamiglia.it
• Study Contact Backup: Name: Fabio Alexander Storm, PhD; Phone Number: +39 031877111; Email: fabio.storm@lanostrafamiglia.it

Study Locations

• Italy
  • Bosisio Parini, Italy, 23842
    • Scientific Institute IRCCS E.Medea
    • Contact: Emilia Biffi, PhD; Phone Number: +39 031877111; Email: emilia.biffi@lanostrafamiglia.it
    • Sub-Investigator: Simone Costantini, MSc
    • Contact: Fabio Alexander Storm, PhD; Phone Number: +39 031877111; Email: fabio.storm@lanostrafamiglia.it

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child
• Accepts Healthy Volunteers: No

Description

Inclusion Criteria:

• Subjects aged between 5 and 17 years with neuromotor impairments who are undergoing rehabilitation therapy using the Lokomat and GRAIL devices, according to the existing clinical plan.

Exclusion Criteria:

• Uncooperative subjects.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Device Feasibility
• Allocation: N/A
• Interventional Model: Single Group Assignment
• Masking: None (Open Label)

Number of Arms

1

Arms and Interventions

Participant Group / Arm

Intervention / Treatment

Experimental: Real-Time Engagement Monitoring; Participants in this experimental arm, consisting of pediatric patients with neuromotor impairments, will undergo a single 1-hour technology-assisted rehabilitation session using either the Lokomat or GRAIL system. During the session, the physiotherapist will use a display showing real-time outputs from the AI-based model, including the patient's heart rate, engagement levels, pleasantness, activation, and motor performance. The model acts as an observational support tool and will not directly alter the standard rehabilitation protocol. At the end of the session, the physiotherapist will evaluate the usability of the system.

Device: Artificial Intelligence Model for Rehabilitation Engagement Monitoring; The intervention consists of the deployment of a real-time AI-based monitoring system during a standard technology-assisted rehabilitation session. The physiotherapist is provided with a display showing continuous feedback on the patient's engagement levels, emotional state (pleasantness and activation), motor performance, and heart rate. The model processes physiological and inertial data collected via wearable sensors, acting purely as an observational support tool without altering the standard rehabilitation protocol.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
System Usability Scale (SUS) Score	This validated questionnaire is intended to evaluate the usability and feasibility of a system or product. It is composed of 10 items assessing factors such as system complexity, ease of use, and functionality integration. Each item is proposed on a 5-points Likert scale, with minimum value 1 and maximum value 5. Higher overall values stand for a higher degree of agreement with respect to the statement provided by the single item. For odd items, higher values stand for higher usability. For even items, higher values stand for lower usability.	Baseline

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Service Provider-Rated Measure of Client Engagement (PRIME-SP)	This measure is intended to capture the therapist's observation of patient engagement. PRIME-SP is a validated self-reported questionnaire that is composed of three main parts: Part A, where the therapist can perform an overall evaluation of patient engagement according to a 5-point Likert scale (from 0 to 4, with higher values corresponding to positive engagement); Part B, where the therapist can perform a domain-dependent (affective, cognitive, behavioral domains) evaluation of patient engagement according to a 5-point Likert scale (from 0 to 4, with higher values corresponding to positive engagement); Part C, where the therapist can take free notes about factors and circumstances that he/she believes may have affected patient engagement in the session.	Baseline
AI Model-Inferred Engagement Level	This objective measure is intended to capture the patient's continuous engagement level during the rehabilitation session. The AI-based model infers the engagement state using feed-forward neural networks that process real-time physiological data (such as HRV and EDA) and inertial signals (IMU). The model provides a categorical evaluation of engagement (low vs high).	Baseline

Collaborators and Investigators

• Sponsor: IRCCS Eugenio Medea
• Collaborators: Politecnico di Milano

Publications and helpful links

General Publications

• Costantini S, Falivene A, Chiappini M, Malerba G, Dei C, Bellazzecca S, Storm FA, Andreoni G, Ambrosini E, Biffi E. Artificial intelligence tools for engagement prediction in neuromotor disorder patients during rehabilitation. J Neuroeng Rehabil. 2024 Dec 19;21(1):215. doi: 10.1186/s12984-024-01519-2.
• Koenig A, Omlin X, Zimmerli L, Sapa M, Krewer C, Bolliger M, Muller F, Riener R. Psychological state estimation from physiological recordings during robot-assisted gait rehabilitation. J Rehabil Res Dev. 2011;48(4):367-85. doi: 10.1682/jrrd.2010.03.0044.
• Graffigna G, Barello S, Riva G, Castelnuovo G, Corbo M, Coppola L, Daverio G, Fauci A, Iannone P, Ricciardi W, Bosio AC; CCIPE Working Group. [Recommandation for patient engagement promotion in care and cure for chronic conditions.]. Recenti Prog Med. 2017 Nov;108(11):455-475. doi: 10.1701/2812.28441. Italian.
• Flynn R, Walton S, Scott SD. Engaging children and families in pediatric Health Research: a scoping review. Res Involv Engagem. 2019 Nov 4;5:32. doi: 10.1186/s40900-019-0168-9. eCollection 2019.
• Bray L, Appleton V, Sharpe A. The information needs of children having clinical procedures in hospital: Will it hurt? Will I feel scared? What can I do to stay calm? Child Care Health Dev. 2019 Sep;45(5):737-743. doi: 10.1111/cch.12692. Epub 2019 Jul 18.

Study record dates

Study Major Dates

• Study Start (Estimated): June 15, 2026
• Primary Completion (Estimated): September 30, 2026
• Study Completion (Estimated): September 30, 2026

Study Registration Dates

• First Submitted: June 8, 2026
• First Submitted That Met QC Criteria: June 17, 2026
• First Posted (Actual): June 23, 2026

Study Record Updates

• Last Update Posted (Actual): June 23, 2026
• Last Update Submitted That Met QC Criteria: June 17, 2026
• Last Verified: June 1, 2026

More Information

Terms related to this study

• Keywords: Gait; Heart Rate Variability; Engagement; Electrodermal Activity; Neuromotor Impairments; Pediatric Rehabilitation
• Other Study ID Numbers: L2-246-F2; RC 2024-2026 to E. Biffi (Other Grant/Funding Number: Italian Ministry of Health)

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: YES
• IPD Plan Description: The results obtained at the end of this clinical trial will be presented at national and international conferences and submitted to peer-reviewed international journals. The raw data of the study will be published among the supplementary materials of scientific articles and/or uploaded to Zenodo, a multidisciplinary repository, managed by CERN in Geneva, which allows researchers to share and preserve research results in any size and form. Depositing data in ZENODO guarantees their compliance with the FAIR principles.
• IPD Sharing Supporting Information Type: STUDY_PROTOCOL; SAP

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No