Background: This article presents the system architecture and validation of the NeuroSuitUp body–machine interface (BMI). The platform consists of wearable robotics jacket and gloves in combination with a serious game application for self-paced neurorehabilitation in spinal cord injury and chronic stroke. Methods: The wearable robotics implement a sensor layer, to approximate kinematic chain segment orientation, and an actuation layer. Sensors consist of commercial magnetic, angular rate and gravity (MARG), surface electromyography (sEMG), and flex sensors, while actuation is achieved through electrical muscle stimulation (EMS) and pneumatic actuators. On-board electronics connect to a Robot Operating System environment-based parser/controller and to a Unity-based live avatar representation game. BMI subsystems validation was performed using exercises through a Stereoscopic camera Computer Vision approach for the jacket and through multiple grip activities for the glove. Ten healthy subjects participated in system validation trials, performing three arm and three hand exercises (each 10 motor task trials) and completing user experience questionnaires. Results: Acceptable correlation was observed in 23/30 arm exercises performed with the jacket. No significant differences in glove sensor data during actuation state were observed. No difficulty to use, discomfort, or negative robotics perception were reported. Conclusions: Subsequent design improvements will implement additional absolute orientation sensors, MARG/EMG based biofeedback to the game, improved immersion through Augmented Reality and improvements towards system robustness.

With the rise in global life expectancy, ensuring healthier aging experiences for the older population becomes paramount. This scoping review delves into the technologies employed in the remote health monitoring of the elderly over the past 15 years. Exploring the concept of “Healthy Ageing” as proposed by the World Health Organization, this paper attempts to highlight the techniques and technologies used in health monitoring of the elderly population. The integration of wearable sensors in health monitoring presents promising avenues for enhancing healthcare delivery to older adults. However, challenges such as limited digital literacy and privacy concerns persist, necessitating innovative solutions for unobtrusive monitoring. This paper discusses the potential of passive and ambient sensors to address these challenges, offering insights into enhancing the well-being of the older population while preserving their independence and privacy.

Our team has engineered a mobile and cost-efficient diagnostic tool that leverages Electrical Impedance Spectroscopy (EIS) technology to conduct differential assessment of the electrical impedance of skin tissue. Now in its third prototype iteration, the DermaSense apparatus performs non-invasive data collection from the epidermal layer, processing and analyzes the data, and serves as a support tool in dermatological diagnostic decisions. Device development focuses on an array of skin malignancies and relevant precursors conditions, such as actinic keratosis. Subsequent to rigorous evaluations in both controlled lab environments and clinical scenarios, our empirical data suggests that DermaSense holds promise in enhancing the precision of skin condition classification. Crucially, impedance measurements derived from individuals with certain pre existing dermatological ailments appear to be distinguishable from those acquired from healthy patches of skin from the same subject, as well as those from other healthy subjects.

This study investigates the use of machine learning (ML) techniques to predict intervention response in patients with Multiple Sclerosis (PwMS) using real-world data from wearable devices. Data from 27 PwMS, monitored over two months were analyzed with several state-of-the-art ML models to predict the efficacy of a computerized cognitive intervention targeting cognitive decline. A model based on Support Vector Machines achieved high accuracy in identifying patient response within the first 2-3 weeks of intervention, aided by feature selection methods like Mutual Information and Recursive Feature Elimination. Early prediction capability enables timely therapeutic adjustments, enhancing personalization of treatment and improving patient quality of life.

Cognitive impairment is a frequent, disabling symptom of multiple sclerosis (MS). Digital interventions may help people with MS maintain or improve cognition, but effectiveness varies between individuals. This exploratory study examines the feasibility of using machine learning models trained on Fitbit-derived real-world data to predict responsiveness to a computerised cognitive training intervention. Linear support vector machine classifiers achieved a mean balanced accuracy of 0.71 in distinguishing responders from non-responders, while SHAP analysis identified sleep and cardiac activity features as key behavioural predictors. y linking real-world behavioural metrics with cognitive outcomes, this work shows how artificial intelligence and wearables may personalise neurorehabilitation and bridge the gap between data and precision care in MS.