This exploratory study analyses parameters influencing a tele-rehabilitation program using the Virtual Reality Rehabilitation System (VRSS) HomeKit for patients with Parkinson’s disease (PD). Data from 10 patients with idiopathic PD who completed 20 upper limb motor exercise sessions were analysed to assess correlations between system-generated metrics and clinical outcomes. Patients were clinically assessed with the Fugl-Meyer Assessment (FMA) and the Unified Parkinson’s Disease Rating Scale (UPDRS). In the experiments, we focused on two macro categories of exercises performed by patients, i.e., reaching and catching, while analysing how correlations among patients’ age, clinician-provided Hoehn-Yahr (HY) stage, and VRRS-provided metrics (such as repetitions, mean duration, correct responses, and omission errors) influenced exercise score assessments and other potential outcomes. This study is propaedeutic for advanced ML-based analyses to model patient progress and predict outcomes throughout treatment, laying the foundation for patient-centric precision medicine and the development of tailored remote rehabilitation strategies.

Remote patient monitoring is a form of telehealth that allows medical centres to monitor and manage their patients’ chronic conditions. Often, depending on the severity of the disease, patients can experience either temporary or permanent home hospitalization. Although the classical medical approach involves continuous monitoring of vital parameters through specialized medical devices, it does not allow observation of patient’s behaviours, which may provide additional information of interest to physicians. In this context, digital biomarkers represent the next frontiers towards precision medicine. In this paper, we explore the possible adoption of Audio Biomarkers for monitoring the behaviours of long-term home hospitalized patients. In particular, we trained and tested several Machine Learning (ML) models to recognise different sounds (i.e., sneezing, breathing, coughing, snoring, teeth brushing, and toilet flush). The results show that, even with a few audio samples, the considered models provide good performance.

Tele-rehabilitation has recently emerged as an effective solution for providing assisted living, increasing clinical outcomes, positively enhancing patients' Quality of Life (QoL) and fostering their reintegration into society, also pushing down clinical costs. Cloud computing in combination with Edge Computing, the Internet of Things (IoT), Big Data storage and analytics, and Artificial Intelligence (AI) are the main enablers for tele-rehabilitation. In this paper, we present the Italian founded PRIN 2022 project entitled “Tele-rehabilitation as a Service (TRaaS)”. It aims at creating a piece of reference intelligent Cloud/Edge framework architecture and a standard data model for the development of different kinds of new de-hospitalized tele-rehabilitation services. In particular, the rationale, study design, and methodology are discussed, also highlighting future research directions.

Nowadays, tele-rehabilitation has emerged as an effective approach for providing assisted living, increasing clinical outcomes, positively enhancing patients' Quality of Life (QoL) and fostering the reintegration of patients into society, also pushing down clinical costs. Cloud computing in combination with Edge Computing and Artificial Intelligence (AI) are the main enablers for tele-rehabilitation. In particular, Edge rehabilitation devices can act as smart digital biomarkers sending quantifiable physiological and behavioural patients' data to the Hospital Cloud. However, due to hardware limitations, it is not clear which Machine Learning (ML) models can be executed in cheap Edge devices. In this paper, we aim at answering this question. In particular, several ML-based pose estimation models (i.e., PoseNet, MoveNet and BlazePose) have been tested and assessed on the Edge, identifying the best one and demonstrating the feasibility of such an approach.

Tele-rehabilitation has recently emerged as an effective approach for providing assisted living, increasing clinical outcomes, positively enhancing patients' Quality of Life (QoL) and fostering their reintegration into society, also pushing down clinical costs. Nowadays, tele-rehabilitation has to face two main challenges: motor and cognitive rehabilitation. In this paper, we focus on the latter. Our idea is to monitor the patient's cognitive rehabilitation by analysing his/her facial expressions during motor rehabilitation exercises with the objective to understand if there is a correlation between motor and cognitive outcomes. Therefore, the aim of this preliminary study is to leverage the concept of Emotional Artificial Intelligence (AI) with a Facial Expression Recognition (FER) system which uses the face mesh generated by the MediaPipe suite of libraries to train a Machine Learning (ML) model in order to identify the facial expressions, according to the Ekman's model, contained inside images or video captured during motor rehabilitation exercises performed at home. In particular, different datasets, face features maps and ML models are tested providing an advancement in the state of the art.

Objective analysis of gait abilities (Gait Analysis, GAn) in clinic is an essential motor assessment to improve clinical decision-making and provide precision rehabilitation approaches to recover gait functions. GAn is usually based on wearable motion sensors or camera-based systems, which generate an extensive set of data which are challenging to manage, analyse, and interpret. This makes GAn a time-consuming unfeasible assessment approach in clinical practice. Machine Learning (ML) techniques can provide a viable solution, as they can handle massive time series and complex data. This study aims to correctly classify subjects’ physical activity levels, using as ground truth a self-reported questionnaire (International Physical Activity Questionnaire, IPAQ), via kinematic features provided by wearable wireless Inertial Measurement Unit (IMU) sensors. Kinematic gait data were collected from 37 healthy subjects (24 male and 13 female) while walking on a sensorised treadmill at natural speed. Velocity, acceleration, jerk, and smoothness were calculated using the kinematic features and used to perform statistical feature extraction. The Neighbourhood Component Analysis (NCA) algorithm was used to process the statistical features space and select the most significant ones. Several models have been trained and tested before and after the feature selection to validate the approach’s effectiveness. Feature reduction resulted in a significant increase in accuracy for K-Nearest Neighbours (KNN) (81.978 ± 0.368), Random Forest (84.044 ± 3.409) and Rough-Set-Exploration-System Library K-Nearest Neighbours (RSesLib KNN) (83.956 ± 0), with an improvement of ≈20%. The performance of the best-performing classifiers was then analysed, observing the behaviour of accuracy by varying the number of features considered.

Brain network analysis can offer useful information to guide the rehabilitation of post-stroke patients. We applied functional network connection models based on multiplex-multilayer network analysis (MMN) to explore functional network connectivity changes induced by robot-aided gait training (RAGT) using the Ekso, a wearable exoskeleton, and compared it to conventional overground gait training (COGT) in chronic stroke patients. We extracted the coreness of individual nodes at multiple locations in the brain from EEG recordings obtained before and after gait training in a resting state. We found that patients provided with RAGT achieved a greater motor function recovery than those receiving COGT. This difference in clinical outcome was paralleled by greater changes in connectivity patterns among different brain areas central to motor programming and execution, as well as a recruitment of other areas beyond the sensorimotor cortices and at multiple frequency ranges, contemporarily. The magnitude of these changes correlated with motor function recovery chances. Our data suggest that the use of RAGT as an add-on treatment to COGT may provide post-stroke patients with a greater modification of the functional brain network impairment following a stroke. This might have potential clinical implications if confirmed in large clinical trials.

The deterioration of specific topological network measures that quantify different features of whole-brain functional network organization can be considered a marker for awareness impairment. Such topological measures reflect the functional interactions of multiple brain structures, which support the integration of different sensorimotor information subtending awareness. However, conventional, single-layer, graph theoretical analysis (GTA)-based approaches cannot always reliably differentiate patients with Disorders of Consciousness (DoC). Using multiplex and multilayer network analyses of frequency-specific and area-specific networks, we investigated functional connectivity during resting-state EEG in 17 patients with Unresponsive Wakefulness Syndrome (UWS) and 15 with Minimally Conscious State (MCS). Multiplex and multilayer network metrics indicated the deterioration and heterogeneity of functional networks and, particularly, the frontal-parietal (FP), as the discriminant between patients with MCS and UWS. These data were not appreciable when considering each individual frequency-specific network. The distinctive properties of multiplex/multilayer network metrics and individual frequency-specific network metrics further suggest the value of integrating the networks as opposed to analyzing frequency-specific network metrics one at a time. The hub vulnerability of these regions was positively correlated with the behavioral responsiveness, thus strengthening the clinically-based differential diagnosis. Therefore, it may be beneficial to adopt both multiplex and multilayer network analyses when expanding the conventional GTA-based analyses in the differential diagnosis of patients with DoC. Multiplex analysis differentiated patients at a group level, whereas the multilayer analysis offered complementary information to differentiate patients with DoC individually. Although further studies are necessary to confirm our preliminary findings, these results contribute to the issue of DoC differential diagnosis and may help in guiding patient-tailored management.

Over the past years, in order to care neurolodical diseases, beyond conventional physical treatments, robotics rehabilitation has been widely adopted for improving the patients' therapies. Recent scientific works were mainly aimed at personalizing treatments, according to the patient's clinical conditions. On the contrary, this scientific work aims to propose an alternative approach based on big data analytics coming from the sensors of robotic rehabilitation devices in order to improve the patient's therapy in the perspective of a healthcare Cloud of Things scenario. We perform an exploratory analysis considering big data coming from sensors installed in Lokomat, i.e., one of the major robotic rehabilitation devices, in order to study the data model and the predictors that will allow clinical operators to forecast the best treatment personalizing the therapy. Data analysis proves that there are moderate correlations among features referring to stance and swing biofeedbacks of hip and knee. From the analytical point of view, these values may approximate the stance and swing phases of knee and hip. This can be compared with the normal gait pattern of healthy individuals, so as to point out those patients having a closer normal ambulation. Obtained results are comparable with the Lokomat therapy outcomes of patients with neurological injuries by means of pattern recognition techniques.

The extent of cortical reorganization after brain injury in patients with Vegetative State/Unresponsive Wakefulness Syndrome (UWS) and Minimally Conscious State (MCS) depends on the residual capability of modulating synaptic plasticity. Neuroplasticity is largely abnormal in patients with UWS, although the fragments of cortical activity may exist, while patients MCS show a better cortical organization. The aim of this study was to evaluate cortical excitability in patients with disorders of consciousness (DoC) using a transcranial direct current stimulation (TDCS) metaplasticity protocol. To this end, we tested motor-evoked potential (MEP) amplitude, short intracortical inhibition (SICI), and intracortical facilitation (ICF). These measures were correlated with the level of consciousness (by the Coma Recovery Scale-Revised, CRS-R). MEP amplitude, SICI, and ICF strength were significantly modulated following different metaplasticity TDCS protocols only in the patients with MCS. SICI modulations showed a significant correlation with the CRS-R score. Our findings demonstrate, for the first time, a partial preservation of metaplasticity properties in some patients with DoC, which correlates with the level of awareness. Thus, metaplasticity assessment may help the clinician in differentiating the patients with DoC, besides the clinical evaluation. Moreover, the responsiveness to metaplasticity protocols may identify the subjects who could benefit from neuromodulation protocols.