Search

Abstract Affective states are psycho-physiological constructs connecting mental and physiological processes. They can be represented in terms of arousal and valence according to the Russel’s model and can be extracted from physiological changes in human body. However, a well-established optimal feature set and a classification method effective in terms of accuracy and estimation time are not present in the literature. This paper aims at defining a reliable and efficient approach for real-time affective state estimation. To obtain this, the optimal physiological feature set and the most effective machine learning algorithm, to cope with binary as well as multi-class classification problems, were identified. ReliefF feature selection algorithm was implemented to define a reduced optimal feature set. Supervised learning algorithms, such as K-Nearest Neighbors (KNN), cubic and gaussian Support Vector Machine, and Linear Discriminant Analysis, were implemented to compare their effectiveness in affective state estimation. The developed approach was tested on physiological signals acquired on 20 healthy volunteers during the administration of images, belonging to the International Affective Picture System, conceived for inducing different affective states. ReliefF algorithm reduced the number of physiological features from 23 to 13. The performances of machine learning algorithms were compared and the experimental results showed that both accuracy and estimation time benefited from the optimal feature set use. Furthermore, the KNN algorithm resulted to be the most suitable for affective state estimation. The results of the assessment of arousal and valence states on 20 participants indicate that KNN classifier, adopted with the 13 identified optimal features, is the most effective approach for real-time affective state estimation.

BackgroundAcute neurological diseases are leading causes of disability and death. The need for specialist neurocritical care skills for managing neurological emergencies has increased. Promising opportunities exist to improve outcomes in acute phases of neurological diseases, such as, for example, the concept of a stroke unit for stroke patients. A similar concept was introduced for a neurocritical care unit, which is associated with improved clinical outcomes compared with more traditional management. However, neurocritical care is often not recognized as a separate specialty. Significant progress in neurology has enabled better approaches for the critically ill neurologic patient, in particular those with stroke and hemorrhage, but also with epileptic seizures and epileptic status, traumatic brain injury (TBI), subdural/epidural hematoma, acute inflammatory polyradiculoneuritis, encephalitis, myasthenia gravis, acute myelitis, etc.Assessment of policy/guidelines options and implicationsExcept for cerebrovascular diseases, for other acute neurological diseases, there is no standardized model care service recognized. A good patient outcome can be obtained by the choice of neurology setting for acute patients including nursing and medical staff with specific training in neurocritical care. As we believe neurocritical care practices should be implemented, we suggest a pilot model on the basis of our experience. In this report, we show a model of the 2A setting of the Santo Stefano Hospital (Prato, USL Toscana Centro), where, as well as stroke units for cerebrovascular events, we have neurocritical care unit and acute-neurology experts for all acute neurological diseases.Actionable recommendations: our pilot experienceThe 2A setting of Stroke Unit/Neurocritical Care of the Santo Stefano Hospital includes 15 beds; 8 ± 2 beds are monitored by portable multi-parameter monitoring devices. Following acute treatment, diagnostic/etiologic work-up and automated monitoring of vital functions are performed in addition to adapted secondary prevention, early rehabilitation, and prevention of complications in all acute patients. We retrospectively assessed the diagnoses in the hospital discharge forms (HDF) of Stroke Unit/Neurocritical Care (2A) of 249 patients consecutively analyzed between 1 January 2022 and 30 June 2022. Out of the 249 patients affected by acute neurological diseases, 155 had cerebrovascular diseases (62.2%). In particular, 100 (64.5%) were diagnosed with ischemic stroke and 44 (28.4%) with hemorrhagic stroke. Thirty-two patients (12.8%) were hospitalized following a TBI. Sixteen patients (6.4%) had a new diagnosis of epilepsy and three (1.2%) of epileptic status. In our setting, the 3-month modified Rankin Scale (mRS) in the 36 stroke patients treated with recombinant-tissue plasminogen activator (r-TPA) was 0–2 (low disability) in 60% of cases. Additionally, 31% of 44 intracerebral haemorrhage (ICH) patients reported a moderate-severe degree of disability. Regarding TBI patients, the mRS ranged from 1 to 5, with significate difference between patients in Stroke Unit/Neurocritical Care (2A) in comparison with those in other departments (2–3 vs. 3–4, respectively). Globally, the setting discharge of the acute neurological patients were: rehabilitation (26%), intermediate care hospitals (44%), long-term care (5%), and home (25%). The 1-month mortality rate was 1.8%.DiscussionWe provide a brief description of the cases treated over a 6-month period to draw attention to the possibility of the existence of a ward dedicated exclusively and specifically to all acute neurological diseases. The sample of patients is very varied and interesting. More than 60% of patients had cerebrovascular diseases. The paucity of outcome data makes this report limited, but the diagnostic-therapeutic strategies, the presence of staff trained in specific neurocritical care, and the use of inpatient hospital-based registries are, in our opinion, strengths. Our pilot model of the setting of Stroke Unit/Neurocritical Care (2A) in the Santo Stefano Hospital (Prato, USL Toscana Centro) should be further implemented, also to verify systematically the associations with measurable outcome improvements in patients affected by strokes and other neurological acute diseases.

Physical therapy keeps exploiting more and more the capabilities of the robot of adapting the treatments to patients’ needs. This paper aims at presenting a psychophysiological-aware control strategy for upper limb robot-aided orthopedic rehabilitation. The main features are the capability of i) generating point-to-point trajectories inside an adaptable workspace, ii) providing assistance in guiding the patients’ limbs in accomplishing the assigned task allowing them to freely move with a certain degree of spatial and temporal autonomy and iii) tuning the control parameters according to the patients’ kinematics performance and psychophysiological state. The implemented control strategy is validated in a real clinical setting on eight orthopedic patients undergoing twenty daily robot-aided rehabilitation sessions. The psychophysiological-aware control strategy evidenced a positive impact on the enrolled participants since they are effectively conducted in a calmer condition with respect to the patients who did not receive the psychophysiological adaptation. Moreover, clinical performance indicators suggest that the proposed tailored control strategy improves motor functions.

The purpose of the present study was to compare attitudes toward body weight and physical activity in both regular-weight and overweight/obese children and adolescents, and assessing relations between attitudes and self-esteem, motivation for physical activity, life satisfaction and level of physical activity. A total of 126 children (Mage = 12.2, SD = 3.4), divided into two subsamples (i.e., overweight/obese, N = 44, and regular-weight), voluntarily participated in the study. A series of univariate analyses of variance was conducted to examine the differences in the study variables across the subsamples. Correlational analyses were conducted to examine the relationships among the variables. The results indicated that obese/overweight participants expressed a more positive implicit attitude toward the thin category than regular-weight participants. Furthermore, among overweight/obese participants, implicit attitude toward physical activity was significantly negatively correlated with explicit attitude toward physical activity and general self-esteem. Significant differences between obese/overweight and regular-weight participants indicated that the status in terms of weight played a key role in attitudes toward the explored constructs.

The ability to finely control hand grip forces can be compromised by neuromuscular or musculoskeletal disorders. Therefore, it is recommended to include the training and assessment of grip force control in rehabilitation therapy. The benefits of robot-mediated therapy have been widely reported in the literature, and its combination with virtual reality and biofeedback can improve rehabilitation outcomes. However, the existing systems for hand rehabilitation do not allow both monitoring/training forces exerted by single fingers and providing biofeedback. This paper describes the development of a system for the assessment and recovery of grip force control. An exoskeleton for hand rehabilitation was instrumented to sense grip forces at the fingertips, and two operation modalities are proposed: (i) an active-assisted training to assist the user in reaching target force values and (ii) virtual reality games, in the form of tracking tasks, to train and assess the user’s grip force control. For the active-assisted modality, the control of the exoskeleton motors allowed generating additional grip force at the fingertips, confirming the feasibility of this modality. The developed virtual reality games were positively accepted by the volunteers and allowed evaluating the performance of healthy and pathological users.

The central nervous system (CNS) is able to control a very high number of degrees of freedom to perform complex movements of both upper and lower limbs. However, what strategies the CNS adopts to perform complex tasks are not completely clear and are still being studied. Recent studies confirm that stroke subjects with mild and moderate impairment show altered upper limb muscle patterns, but the muscular patterns of the hand have not completely investigated, although the hand represents a paramount tool for performing activities of daily living (ADLs) and stroke can significantly alter the mobilization of this part of the body. In this context, this study aims at investigating hand muscular synergies in chronic stroke patients and evaluating some possible benefits in the robot-aided rehabilitation treatment of the hand in these subjects. Seven chronic stroke patients with mild-to-moderate impairment (FM>30) were involved in this study. They received a 5-week robot-aided rehabilitation treatment with the Gloreha hand exoskeleton, and muscle synergies of both the healthy and injured hand were evaluated at the beginning and at the end of the treatment. The performed analysis showed a very high degree of similarity of the involved synergies between the healthy and the injured limb both before and after the rehabilitation treatment (mean similarity index values: H-BR: 0.88±0.03, H-AR: 0.94±0.03, BR-AR: 0.89±0.05). The increasing similarity is regarded as an effect of the robot-aided rehabilitation treatment and future activities will be performed to increase the population involved in the study.

The design of patient-tailored rehabilitative protocols represents one of the crucial factors that influence motor recovery mechanisms, such as neuroplasticity. This approach, including the patient in the control loop and characterized by a control strategy adaptable to the user's requirements, is expected to significantly improve functional recovery in robot-aided rehabilitation. In this paper, a novel 3D bio-cooperative robotic platform is developed. A new arm-weight support system is included into an operational robotic platform for 3D upper limb robot-aided rehabilitation. The robotic platform is capable of adapting therapy characteristics to specific patient needs, thanks to biomechanical and physiological measurements, and thus closing the subject in the control loop. The level of arm-weight support and the level of the assistance provided by the end-effector robot are varied on the basis of muscular fatigue and biomechanical indicators. An assistance-as-needed approach is applied to provide the appropriate amount of assistance. The proposed platform has been experimentally validated on 10 healthy subjects; they performed 3D point-to-point tasks in two different conditions, i.e., with and without assistance-as-needed. The results have demonstrated the capability of the proposed system to properly adapt to real needs of the patients. Moreover, the provided assistance was shown to reduce the muscular fatigue without negatively influencing motion execution.

Affective states are psycho-physiological constructs connecting mental and physiological processes. They can be represented in terms of arousal and valence according to the Russel's model and can be extracted from physiological changes in human body. However, a well-established optimal feature set and a classification method effective in terms of accuracy and estimation time are not present in the literature. This paper aims at defining a reliable and efficient approach for real-time affective state estimation. To obtain this, the optimal physiological feature set and the most effective machine learning algorithm, to cope with binary as well as multi-class classification problems, were identified. ReliefF feature selection algorithm was implemented to define a reduced optimal feature set. Supervised learning algorithms, such as K-Nearest Neighbors (KNN), cubic and gaussian Support Vector Machine, and Linear Discriminant Analysis, were implemented to compare their effectiveness in affective state estimation. The developed approach was tested on physiological signals acquired on 20 healthy volunteers during the administration of images, belonging to the International Affective Picture System, conceived for inducing different affective states. ReliefF algorithm reduced the number of physiological features from 23 to 13. The performances of machine learning algorithms were compared and the experimental results showed that both accuracy and estimation time benefited from the optimal feature set use. Furthermore, the KNN algorithm resulted to be the most suitable for affective state estimation. The results of the assessment of arousal and valence states on 20 participants indicate that KNN classifier, adopted with the 13 identified optimal features, is the most effective approach for real-time affective state estimation. [ABSTRACT FROM AUTHOR]