Integration of a Robotic Platform for Clinical Monitoring of Patients With Severe Acquired Brain Injury in High-Intensity Care Units

Summary

Frailty is not related exclusively to age, but represents a state of increased biological and clinical vulnerability characterized by reduced functional reserve and greater susceptibility to adverse events, even in response to minor stress factors. In patients with complex conditions, such as severe acquired brain injuries, early detection and prompt treatment of clinical deterioration are essential to reduce the risk of acute readmission, complications, and in-hospital mortality. Many of these events are potentially predictable and preventable, given the presence of appropriate monitoring systems.

Advanced care models, including early warning systems, have been developed to support healthcare professionals in identifying patients at risk by detecting significant changes in physiological parameters. In recent years, technological innovations-particularly in the fields of robotics and telemedicine-have created new opportunities to enhance clinical monitoring, enabling continuous data collection and more timely, proactive interventions.

Social assistive robots are emerging as promising tools in healthcare settings. These systems can support clinicians and nurses in routine monitoring activities, help reduce workload, and facilitate more efficient and personalized care. By integrating robotic assistance with digital health platforms, it is possible to improve the quality and responsiveness of patient management, especially in high-complexity environments such as neurorehabilitation units.

This study focuses on the use of an innovative robotic telemedicine system based on the integration of the MOVER-L prototype with the ROB.IN.CARE platform, owned by Item Oxygen Srl, which purchased the platform from the company CO-ROBOTICS S.R.L. through the PON SI-ROBOTICS project. The system is designed to continuously monitor patients' clinical conditions, collecting vital parameters and identifying early signs of deterioration. It supports healthcare professionals by providing real-time data and alerts, enabling earlier and more targeted interventions.

The study is a low-intensity interventional clinical trial conducted in a Neurorehabilitation Unit. Patients with varying levels of clinical severity, classified according to the Glasgow Coma Scale, are enrolled and divided into two groups: a control group receiving standard care and an experimental group monitored using the robotic system in addition to usual care.

The primary objective of the study is to evaluate the feasibility, usability, safety, and reliability of this robotic telemedicine solution in a real clinical setting. In addition, the study assesses its acceptability among both patients and healthcare professionals. These aspects are measured using validated tools, including the System Usability Scale (SUS) and the Health and Safety Executive Stress Scale (HSE), to understand the impact of the technology on user experience and workload.

The integrated MOVER-L/ROB.IN.CARE system combines robotic assistance with continuous monitoring of vital signs and advanced software architecture. The platform incorporates predictive algorithms designed to stratify clinical risk and assess patient severity. It utilizes established clinical scoring systems, such as the Modified Early Warning Score (MEWS) for early detection of clinical deterioration, the quick Sequential Organ Failure Assessment (qSOFA) for sepsis risk evaluation, and the Kidney Disease: Improving Global Outcomes (KDIGO) criteria for the assessment of acute kidney injury.

By enabling early identification of clinical worsening, the system aims to improve the timeliness and effectiveness of healthcare interventions, optimize clinical workflow, and reduce the risk of adverse events and complications. Ultimately, this study explores whether robotic telemedicine can represent a safe, feasible, and valuable tool to enhance the management of fragile patients in neurorehabilitation settings.

Conditions

• User Experience
• Usability
• Acceptability
• Satisfaction

Interventions

DEVICE

Robotic platform monitoring system

The robot will observe patients and collect health data through clinical assessment scales including MEWS, qSOFA, and KDIGO, using the dedicated software application on a tablet. The data collected will then be processed to determine the patient's current risk status. If necessary, the robot will alert medical and nursing staff to the patient's condition in order to stabilize it as quickly as possible.

Sponsors & Collaborators

• Item Oxygen

  collaborator UNKNOWN

• Ernesto Losavio

  lead OTHER

Study Design

Allocation

RANDOMIZED

Purpose

SUPPORTIVE_CARE

Masking

NONE

Model

PARALLEL

Eligibility

Min Age

18 Years

Sex

ALL

Healthy Volunteers

No

Timeline & Regulatory

Start

2026-08-31

Primary Completion

2026-11-30

Completion

2026-11-30