Despite progress in using computational approaches to inform medicine and neuroscience in the last 30 years, there have been few attempts to model the mechanisms underlying sensorimotor rehabilitation. We argue that a fundamental understanding of neurologic recovery, and as a result accurate predictions at the individual level, will be facilitated by developing computational models of the salient neural processes, including plasticity and learning systems of the brain, and integrating them into a context specific to rehabilitation. Here, we therefore discuss Computational Neurorehabilitation, a newly emerging field aimed at modeling plasticity and motor learning to understand and improve movement recovery of individuals with neurologic impairment. We first explain how the emergence of robotics and wearable sensors for rehabilitation is providing data that make development and testing of such models increasingly feasible. We then review key aspects of plasticity and motor learning that such models will incorporate. We proceed by discussing how computational neurorehabilitation models relate to the current benchmark in rehabilitation modeling – regression-based, prognostic modeling. We then critically discuss the first computational neurorehabilitation models, which have primarily focused on modeling rehabilitation of the upper extremity after stroke, and show how even simple models have produced novel ideas for future investigation. Finally, we conclude with key directions for future research, anticipating that soon we will see the emergence of mechanistic models of motor recovery that are informed by clinical imaging results and driven by the actual movement content of rehabilitation therapy as well as wearable sensor-based records of daily activity.

The analysis of human gait is an important tool in medicine and rehabilitation to evaluate the effects and the progression of neurological diseases resulting in neuromotor disorders. In these fields, the gold standard techniques adopted to perform gait analysis rely on motion capture systems and markers. However, these systems present drawbacks: they are expensive, time consuming and they can affect the naturalness of the motion. For these reasons, in the last few years, considerable effort has been spent to study and implement markerless systems based on videography for gait analysis. Unfortunately, only few studies quantitatively compare the differences between markerless and marker-based systems in 3D settings. This work presented a new RGB video-based markerless system leveraging computer vision and deep learning to perform 3D gait analysis. These results were compared with those obtained by a marker-based motion capture system. To this end, we acquired simultaneously with the two systems a multimodal dataset of 16 people repeatedly walking in an indoor environment. With the two methods we obtained similar spatio-temporal parameters. The joint angles were comparable, except for a slight underestimation of the maximum flexion for ankle and knee angles. Taking together these results highlighted the possibility to adopt markerless technique for gait analysis.

The use of augmented reality (AR) and virtual reality (VR) for life support training is increasing. These technologies provide an immersive experience that supports learning in a safe and controlled environment. This review focuses on the use of AR and VR for emergency care training for health care providers, medical students, and nonprofessionals. In particular, we analyzed (1) serious games, nonimmersive games, both single-player and multiplayer; (2) VR tools ranging from semi-immersive to immersive virtual and mixed reality; and (3) AR applications. All the toolkits have been investigated in terms of application goals (training, assessment, or both), simulated procedures, and skills. The main goal of this work is to summarize and organize the findings of studies coming from multiple research areas in order to make them accessible to all the professionals involved in medical simulation. The analysis of the state-of-the-art technologies reveals that tools and studies related to the multiplayer experience, haptic feedback, and evaluation of user’s manual skills in the foregoing health care-related environments are still limited and require further investigation. Also, there is an additional need to conduct studies aimed at assessing whether AR/VR-based systems are superior or, at the minimum, comparable to traditional training methods.

Lack of social skills and/or a reduced ability to determine when to use them are common symptoms of Autism Spectrum Disorder (ASD). Here we examine whether an integrated approach based on virtual environments and natural interfaces is effective in teaching safety skills in adults with ASD. We specifically focus on pedestrian skills, namely street crossing with or without traffic lights, and following road signs. Seven adults with ASD explored a virtual environment (VE) representing a city (buildings, sidewalks, streets, squares), which was continuously displayed on a wide screen. A markerless motion capture device recorded the subjects’ movements, which were translated into control commands for the VE according to a predefined vocabulary of gestures. The treatment protocol consisted of ten 45-minutes sessions (1 session/week). During a familiarization phase, the participants practiced the vocabulary of gestures. In a subsequent training phase, participants had to follow road signs (to either a police station or a pharmacy) and to cross streets with and without traffic lights. We assessed the performance in both street crossing (number and type of errors) and navigation (walking speed, path length and ability to turn without stopping). To assess their understanding of the practiced skill, before and after treatment subjects had to answer a test questionnaire. To assess transfer of the learned skill to real-life situations, another specific questionnaire was separately administered to both parents/legal guardians and the subjects’ personal caregivers. One subject did not complete the familiarization phase because of problems with depth perception. The six subjects who completed the protocol easily learned the simple body gestures required to interact with the VE. Over sessions they significantly improved their navigation performance, but did not significantly reduce the errors made in street crossing. In the test questionnaire they exhibited no significant reduction in the number of errors. However, both parents and caregivers reported a significant improvement in the subjects’ street crossing performance. Their answers were also highly consistent, thus pointing at a significant transfer to real-life behaviors. Rehabilitation of adults with ASD mainly focuses on educational interventions that have an impact in their quality of life, which includes safety skills. Our results confirm that interaction with VEs may be effective in facilitating the acquisition of these skills.

Although robot therapy is progressively becoming an accepted method of treatment for stroke survivors, few studies have investigated how to adapt the robot/subject interaction forces in an automatic way. The paper is a feasibility study of a novel self-adaptive robot controller to be applied with continuous tracking movements. The haptic robot Braccio di Ferro is used, in relation with a tracking task. The proposed control architecture is based on three main modules: 1) a force field generator that combines a non linear attractive field and a viscous field; 2) a performance evaluation module; 3) an adaptive controller. The first module operates in a continuous time fashion; the other two modules operate in an intermittent way and are triggered at the end of the current block of trials. The controller progressively decreases the gain of the force field, within a session, but operates in a non monotonic way between sessions: it remembers the minimum gain achieved in a session and propagates it to the next one, which starts with a block whose gain is greater than the previous one. The initial assistance gains are chosen according to a minimal assistance strategy. The scheme can also be applied with closed eyes in order to enhance the role of proprioception in learning and control. The preliminary results with a small group of patients (10 chronic hemiplegic subjects) show that the scheme is robust and promotes a statistically significant improvement in performance indicators as well as a recalibration of the visual and proprioceptive channels. The results confirm that the minimally assistive, self-adaptive strategy is well tolerated by severely impaired subjects and is beneficial also for less severe patients. The experiments provide detailed information about the stability and robustness of the adaptive controller of robot assistance that could be quite relevant for the design of future large scale controlled clinical trials. Moreover, the study suggests that including continuous movement in the repertoire of training is acceptable also by rather severely impaired subjects and confirms the stabilizing effect of alternating vision/no vision trials already found in previous studies.

Quantitative descriptions of the process of recovery of motor functions in impaired subjects during robot-assisted exercise might help to understand how to use these devices to make recovery faster and more effective. Linear dynamical models have been used to describe the dynamics of sensorimotor adaptation. Here, we extend this formalism to characterize the neuromotor recovery process. We focus on a robot therapy experiment that involved chronic stroke survivors, based on a robot-assisted arm extension task. The results suggest that modeling the recovery process with dynamical models is feasible, and could allow predicting the long-term outcome of a robot-assisted rehabilitation treatment.