Predicting Male Infertility Using Artificial Neural Networks: A Review of the Literature.

Male infertility is a relevant public health problem, but there is no systematic review of the different machine learning (ML) models and their accuracy so far. The present review aims to comprehensively investigate the use of ML algorithms in predicting male infertility, thus reporting the accuracy of the used models in the prediction of male infertility as a primary outcome. Particular attention will be paid to the use of artificial neural networks (ANNs). A comprehensive literature search was conducted in PubMed, Scopus, and Science Direct between 15 July and 23 October 2023, conducted under the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. We performed a quality assessment of the included studies using the recommended tools suggested for the type of study design adopted. We also made a screening of the Risk of Bias (RoB) associated with the included studies. Thus, 43 relevant publications were included in this review, for a total of 40 different ML models detected. The studies included reported a good quality, even if RoB was not always good for all the types of studies. The included studies reported a median accuracy of 88% in predicting male infertility using ML models. We found only seven studies using ANN models for male infertility prediction, reporting a median accuracy of 84%.

Validity of an android device for assessing mobility in people with chronic stroke and hemiparesis: a cross-sectional study.

BACKGROUND: Incorporating instrument measurements into clinical assessments can improve the accuracy of results when assessing mobility related to activities of daily living. This can assist clinicians in making evidence-based decisions. In this context, kinematic measures are considered essential for the assessment of sensorimotor recovery after stroke. The aim of this study was to assess the validity of using an Android device to evaluate kinematic data during the performance of a standardized mobility test in people with chronic stroke and hemiparesis. METHODS: This is a cross-sectional study including 36 individuals with chronic stroke and hemiparesis and 33 age-matched healthy subjects. A simple smartphone attached to the lumbar spine with an elastic band was used to measure participants' kinematics during a standardized mobility test by using the inertial sensor embedded in it. This test includes postural control, walking, turning and sitting down, and standing up. Differences between stroke and non-stroke participants in the kinematic parameters obtained after data sensor processing were studied, as well as in the total execution and reaction times. Also, the relationship between the kinematic parameters and the community ambulation ability, degree of disability and functional mobility of individuals with stroke was studied. RESULTS: Compared to controls, participants with chronic stroke showed a larger medial-lateral displacement (p = 0.022) in bipedal stance, a higher medial-lateral range (p < 0.001) and a lower cranio-caudal range (p = 0.024) when walking, and lower turn-to-sit power (p = 0.001), turn-to-sit jerk (p = 0.026) and sit-to-stand jerk (p = 0.001) when assessing turn-to-sit-to-stand. Medial-lateral range and total execution time significantly correlated with all the clinical tests (p < 0.005), and resulted significantly different between independent and limited community ambulation patients (p = 0.042 and p = 0.006, respectively) as well as stroke participants with significant disability or slight/moderate disability (p = 0.024 and p = 0.041, respectively). CONCLUSION: This study reports a valid, single, quick and easy-to-use test for assessing kinematic parameters in chronic stroke survivors by using a standardized mobility test with a smartphone. This measurement could provide valid clinical information on reaction time and kinematic parameters of postural control and gait, which can help in planning better intervention approaches.

Motor imagery for paediatric neurorehabilitation: how much do we know? Perspectives from a systematic review.

Background: Motor Imagery (MI) is a cognitive process consisting in mental simulation of body movements without executing physical actions: its clinical use has been investigated prevalently in adults with neurological disorders. Objectives: Review of the best-available evidence on the use and efficacy of MI interventions for neurorehabilitation purposes in common and rare childhood neurological disorders. Methods: systematic literature search conducted according to PRISMA by using the Scopus, PsycArticles, Cinahl, PUBMED, Web of Science (Clarivate), EMBASE, PsychINFO, and COCHRANE databases, with levels of evidence scored by OCEBM and PEDro Scales. Results: Twenty-two original studies were retrieved and included for the analysis; MI was the unique or complementary rehabilitative treatment in 476 individuals (aged 5 to 18 years) with 10 different neurological conditions including, cerebral palsies, stroke, coordination disorders, intellectual disabilities, brain and/or spinal cord injuries, autism, pain syndromes, and hyperactivity. The sample size ranged from single case reports to cohorts and control groups. Treatment lasted 2 days to 6 months with 1 to 24 sessions. MI tasks were conventional, graded or ad-hoc. MI measurement tools included movement assessment batteries, mental chronometry tests, scales, and questionnaires, EEG, and EMG. Overall, the use of MI was stated as effective in 19/22, and uncertain in the remnant studies. Conclusion: MI could be a reliable supportive/add-on (home-based) rehabilitative tool for pediatric neurorehabilitation; its clinical use, in children, is highly dependent on the complexity of MI mechanisms, which are related to the underlying neurodevelopmental disorder.

Artificial neural network analysis of factors affecting functional independence recovery in patients with lumbar stenosis after neurosurgery treatment: An observational cohort study.

Background and aim: Lumbar spinal stenosis (LSS) is a leading cause of low back pain and lower limbs pain often associated with functional impairment which entails the loss or the impairment of independence in older adults. Conservative treatment is effective in a small percentage of patients, while a significant percentage undergo surgery, even if often without a complete resolution of clinical symptoms and motor deficits. The aim of the study is to identify clinical and demographic prognostic factors characterising the patients who would benefit most from surgical treatment in relation to the functional independence recovery using an innovative approach based on an artificial neural network. Methods: Adult patients with LSS and indication of neurosurgical treatment were enrolled in the study. Clinical evaluation was performed in the preoperative-phase (into the 48 h before surgery) and after two months. Clinical battery investigated the motor, functional, cognitive, behavioural, and pain status. Demographics and clinical characteristics were analysed via Artificial Neural Network (ANN) using 24 input variables, 2 hidden layers and a single final output layer to predict the outcome. ANN results were compared with those of a multiple linear regression. Results: 108 patients were included in the study and 90 of them [66.5 ± 12.8 years; 27.8 % F] were submitted to surgery treatment and completed longitudinal evaluation. Statistically significant improvement was recorded in all clinical scales comparing pre- and post-surgery. The ANN results showed a prediction ability up to 81 %. Disability, functional limitations, and pain concerning clinical assessment and stature, onset and age about demographic characteristics are the main variables impacting on surgical outcome. Conclusions: ANN can support clinical decision making, using clinical and demographic characteristics of patients with LSS identifying the characteristics of those who might benefit more from the surgical treatment in terms of global functional recovery.

Exploring harmonic walking development in children with unilateral cerebral palsy and typically developing toddlers: Insights from walking experience.

This longitudinal study investigated the impact of the first independent steps on harmonic gait development in unilateral cerebral palsy (CP) and typically developing (TD) children. We analysed the gait ratio values (GR) by comparing the duration of stride/stance, stance/swing and swing/double support phases. Our investigation focused on identifying a potential trend towards the golden ratio value of 1.618, which has been observed in the locomotion of healthy adults as a characteristic of harmonic walking. Locomotor ability was assessed in both groups at different developmental stages: before and after the emergence of independent walking. Results revealed that an exponential fit was observed only after the first unsupported steps were taken. TD children achieved harmonic walking within a relatively short period (approximately one month) compared to children with CP, who took about seven months to develop harmonic walking. Converging values for stride/stance and stance/swing gait ratios, averaged on the two legs, closely approached the golden ratio in TD children (R2 = 0.9) with no difference in the analysis of the left vs right leg separately. In contrast, children with CP exhibited a trend for stride/stance and stance/swing (R2 = 0.7), with distinct trends observed for the most affected leg which did not reach the golden ratio value for the stride/stance ratio (GR = 1.5), while the least affected leg exceeded it (GR = 1.7). On the contrary, the opposite trend was observed for the stance/swing ratio. These findings indicate an overall harmonic walking in children with CP despite the presence of asymmetry between the two legs. These results underscore the crucial role of the first independent steps in the progressive development of harmonic gait over time.

Effects of shoulder brace usage on postural stability in stroke survivors: A pilot randomized controlled trial.

BACKGROUND: Despite advances in stroke rehabilitation, challenges in upper limb motor recovery and postural stability persist, negatively affecting overall well-being. Arm slings and shoulder braces have been proposed to address these issues, but their efficacy in promoting postural stability remains unclear. OBJECTIVE: This pilot randomized controlled study aimed to evaluate the impact of a new shoulder brace (N1-Neurosling) on trunk postural stability during walking, pain, and upper limb muscle strength in chronic stroke survivors. METHODS: Twenty-four adult chronic stroke patients were involved and randomly assigned to the shoulder brace group (SBg) or control group (CTRLg). Were assessed at baseline (T0) and after 4 weeks (T1) through the Trunk Control Test, the Numerical Rating Scale, the Motricity Index, Manual Muscle Test, and instrumental wearable-based assessment. RESULTS: After 4 weeks, the SBg showed significant improvement in Trunk Control Test scores (p = 0.020) and smoothness of gait measured by log dimensionless jerk along the Antero-Posterior axis (- 5.31±0.25 vs. - 5.18±0.27, p = 0.018) compared to the CTRLg. The SBg also demonstrated a reduction in pain in the shoulder girdle and enhanced upper limb muscle strength. CONCLUSION: The use of the N1-Neurosling shoulder brace led to improvements in postural stability and smoothness of gait in stroke patients.

Embodimetrics: A Principal Component Analysis Study of the Combined Assessment of Cardiac, Cognitive and Mobility Parameters.

There is a growing body of literature investigating the relationship between the frequency domain analysis of heart rate variability (HRV) and cognitive Stroop task performance. We proposed a combined assessment integrating trunk mobility in 72 healthy women to investigate the relationship between cognitive, cardiac, and motor variables using principal component analysis (PCA). Additionally, we assessed changes in the relationships among these variables after a two-month intervention aimed at improving the perception-action link. At baseline, PCA correctly identified three components: one related to cardiac variables, one to trunk motion, and one to Stroop task performance. After the intervention, only two components were found, with trunk symmetry and range of motion, accuracy, time to complete the Stroop task, and low-frequency heart rate variability aggregated into a single component using PCA. Artificial neural network analysis confirmed the effects of both HRV and motor behavior on cognitive Stroop task performance. This analysis suggested that this protocol was effective in investigating embodied cognition, and we defined this approach as "embodimetrics".

Michelangelo Effect in Virtual Sculpturing: Prospective for Motor Neurorehabilitation in the Metaverse.

We investigated the Michelangelo effect, i.e. the facilitatory effect of a virtual art therapy in motor rehabilitation (Iosa et al. 2021), with a novel virtual reality paradigm in which users are engaged in motor exercises with 3D sculptures. In particular, thirty young adults were immersed in a virtual environment where they could sculpt, by using the real hands, some famous sculptures in the history of art, such as the David of Michelangelo, the Venus of Milo and the statue of Laocoon and His Sons, and their control stimuli, i.e. statues in very low resolution or cubes. We recorded the kinematics (length, the time to complete each trial, mean normalized jerk) and questionnaire answers (objective and subjective beauty, User Satisfaction Evaluation Questionnaire and Nasa Task Load Index). In general, we found that the perception of subjective and objective beauty was higher when sculpting the statues than control stimuli, the judgment of usability of the system was high. The perceived fatigue was not higher when sculpting the statues despite the longer time spent in completing the task that with respect to the control stimuli. Moreover, we found that the interaction with the experimental statues affected the fluidity and symmetry of hands movements. Finally, we discuss this evidence regarding the art therapy and neuroaesthetics principles for motor rehabilitation in the Metaverse with VR, including the possible role of virtual embodiment (illusory feeling to have a virtual body) for boosting the efficacy of the clinical applications.

Cortico-cortical stimulation and robot-assisted therapy (CCS and RAT) for upper limb recovery after stroke: study protocol for a randomised controlled trial.

BACKGROUND: Since birth, during the exploration of the environment to interact with objects, we exploit both the motor and sensory components of the upper limb (UL). This ability to integrate sensory and motor information is often compromised following a stroke. However, to date, rehabilitation protocols are focused primarily on recovery of motor function through physical therapies. Therefore, we have planned a clinical trial to investigate the effect on functionality of UL after a sensorimotor transcranial stimulation (real vs sham) in add-on to robot-assisted therapy in the stroke population. METHODS: A randomised double-blind controlled trial design involving 32 patients with a single chronic stroke (onset > 180 days) was planned. Each patient will undergo 15 consecutive sessions (5 days for 3 weeks) of paired associative stimulation (PAS) coupled with UL robot-assisted therapy. PAS stimulation will be administered using a bifocal transcranial magnetic stimulator (TMS) on the posterior-parietal cortex and the primary motor area (real or sham) of the lesioned hemisphere. Clinical, kinematics and neurophysiological changes will be evaluated at the end of protocol and at 1-month follow-up and compared with baseline. The Fugl-Meyer assessment scale will be the primary outcome. Secondly, kinematic variables will be recorded during the box-and-block test and reaching tasks using video analysis and inertial sensors. Single pulse TMS and electroencephalography will be used to investigate the changes in local cortical reactivity and in the interconnected areas. DISCUSSION: The presented trial shall evaluate with a multimodal approach the effects of sensorimotor network stimulation applied before a robot-assisted therapy training on functional recovery of the upper extremity after stroke. The combination of neuromodulation and robot-assisted therapy can promote an increase of cortical plasticity of sensorimotor areas followed by a clinical benefit in the motor function of the upper limb. TRIAL REGISTRATION: ClinicalTrials.gov NCT05478434. Registered on 28 Jul 2022.

The Future of Neurorehabilitation: Putting the Brain and Body Together Again.

The neurorehabilitation of cerebrovascular diseases is a challenging scientific topic that has rapidly grown in recent decades [...].

Robot- and Technology-Boosting Neuroplasticity-Dependent Motor-Cognitive Functional Recovery: Looking towards the Future of Neurorehabilitation.

The sequelae of neurological disorders are the leading causes of disability in all industrialized countries [...].

FunctionaL Assessment Scale of Hemianopia (FLASH): A New Multidisciplinary Tool to Assess Hemianopia in Patients with Severe Acquired Brain Injury.

BACKGROUND: Severe acquired brain injury (sABI) encompasses a range of neurological impairments. Visual dysfunction, particularly homonymous visual field defects (HVFDs) and homonymous hemianopia (HH), commonly afflicts sABI survivors, affecting their cognitive and motor rehabilitation. This study presents the FunctionaL Assessment Scale of Hemianopia (FLASH), developed to analyze the most common postural behaviors exhibited by sABI patients with hemianopia during activities of daily living. A comparison to traditional static automated perimetry for diagnosing visual field deficits (VFDs) to determine the sensitivity and specificity of the FLASH was used. Additionally, this study also aimed to assess its reliability. METHODS: Fifty-six patients (25 F, 31 M, mean age 60.59 ± 14.53) with strokes in the sub-acute phase (<6 months from the onset) were assessed with both FLASH and a Humphrey Field Analyzer. RESULTS: After removing two items found to be less reliable than others, FLASH showed high sensitivity (81%) and specificity (77%) when compared to static automated perimetry. Inter-rater reliability was also high, with an intra-class correlation coefficient of 0.954, as well as the internal consistency computed by Cronbach's alpha, equal to 0.874. CONCLUSION: FLASH could offer a valuable and cost-effective screening tool for VFD in sABI patients during neurorehabilitation, with potential implications for healthcare cost reduction.

Computer-assisted cognitive rehabilitation in neurological patients: state-of-art and future perspectives.

Background and aim: Advances in computing technology enabled researchers and clinicians to exploit technological devices for cognitive training and rehabilitation interventions. This expert review aims to describe the available software and device used for cognitive training or rehabilitation interventions of patients with neurological disorders. Methods: A scoping review was carried out to analyze commercial devices/software for computerized cognitive training (CCT) in terms of feasibility and efficacy in both clinical and home settings. Several cognitive domains responding to the different patients' needs are covered. Results: This review showed that cognitive training for patients with neurological diseases is largely covered by several devices that are widely used and validated in the hospital setting but with few translations to remote/home applications. It has been demonstrated that technology and software-based devices are potential and valuable tools to administer remotely cognitive rehabilitation with accessible costs. Conclusion: According to our results, CCT entails the possibility to continue cognitive training also in different settings, such as home, which is a significant breakthrough for the improvement of community care. Other possible areas of use should be the increase in the amount of cognitive therapy in the free time during the hospital stay.

Headaches treatment with EMG biofeedback: a focused systematic review and meta-analysis.

INTRODUCTION: The aim of this paper was to present an up-to-date evaluation of the efficacy of EMG-biofeedback (EMG-BFB) for primary headaches and to address possible mediators of outcome. EVIDENCE ACQUISITION: PubMed, Scopus, Embase and Pedro databases were searched from inception to May 1, 2023. All randomized controlled trials (RCT) studies using an EMG-BFB to treat headache have been included in this systematic review. The current systematic review was performed following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) recommendations and was registered in the PROSPERO database (CRD42022312827). Methodological quality was assessed through the Risk of Bias tool 2 (RoB 2). The effect sizes and 95% confidence interval (CI) were calculated by random-effect models on frequency, intensity, and duration variables. Egger regression and the Begg-Mazumdar rank correlation test were used for publication bias. EVIDENCE SYNTHESIS: A total of 3059 articles were identified through the database searches. 29 articles, involving 1342 participants, met the inclusion criteria for the systematic review; of them, 4 were included in the meta-analysis. Ten studies reported a significant improvement in the EMG-BFB group with respect to the control group. Meta-analyses show a reduction in the intensity of attacks in patients subjected to EMG-BFB (ES 0.21 [(95% CI=-0.02; 0.44), P value=0.07] based on 293 patients). CONCLUSIONS: EMG-BFB represents a non-pharmacological approach to headache treatment as shown via qualitative synthesis, despite not impressive results, this technique can be particularly useful in paediatric or in adult patients who cannot undergo drug therapies. Quantitative synthesis revealed a promising effect in the intensity of headaches attacks. Moreover, no significant effect was found about the effectiveness of EMG-BFB in the reduction of frequency and durations of headache attacks. Future studies with new multimodal technologic assessment and following RCT guidelines can unmask the potentiality of EMG-BFB in the treatment of headache.

Ambient assisted living systems for falls monitoring at home.

INTRODUCTION: Monitoring systems at home are critical in the event of a fall, and can range from standalone fall detection devices to activity recognition devices that aim to identify behaviors in which the user may be at risk of falling, or to detect falls in real-time and alert emergency personnel. AREAS COVERED: This review analyzes the current literature concerning the different devices available for home fall detection. EXPERT OPINION: Included studies highlight how fall detection at home is an important challenge both from a clinical-assistance point of view and from a technical-bioengineering point of view. There are wearable, non-wearable and hybrid systems that aim to detect falls that occur in the patient's home. In the near future, a greater probability of predicting falls is expected thanks to an improvement in technologies together with the prediction ability of machine learning algorithms. Fall prevention must involve the clinician with a person-centered approach, low cost and minimally invasive technologies able to evaluate the movement of patients and machine learning algorithms able to make an accurate prediction of the fall event.

Convergent Validity of the Timed Walking Tests with Functional Ambulatory Category in Subacute Stroke.

Determining the walking ability of post-stroke patients is crucial for the design of rehabilitation programs and the correct functional information to give to patients and their caregivers at their return home after a neurorehabilitation program. We aimed to assess the convergent validity of three different walking tests: the Functional Ambulation Category (FAC) test, the 10-m walking test (10MeWT) and the 6-minute walking test (6MWT). Eighty walking participants with stroke (34 F, age 64.54 ± 13.02 years) were classified according to the FAC score. Gait speed evaluation was performed with 10MeWT and 6MWT. The cut-off values for FAC and walking tests were calculated using a receiver-operating characteristic (ROC) curve. Area under the curve (AUC) and Youden's index were used to find the cut-off value. Statistical differences were found in all FAC subgroups with respect to walking speed on short and long distances, and in the Rivermead Mobility Index and Barthel Index. Mid-level precision (AUC > 0.7; p < 0.05) was detected in the walking speed with respect to FAC score (III vs. IV and IV vs. V). The confusion matrix and the accuracy analysis showed that the most sensitive test was the 10MeWT, with cut-off values of 0.59 m/s and 1.02 m/s. Walking speed cut-offs of 0.59 and 1.02 m/s were assessed with the 10MeWT and can be used in FAC classification in patients with subacute stroke between the subgroups able to walk with supervision and independently on uniform and non-uniform surfaces. Moreover, the overlapping walking speed registered with the two tests, the 10MeWT showed a better accuracy to drive FAC classification.

Are neuroaesthetic principles applied in art therapy protocols for neurorehabilitation? A systematic mini-review.

Art is an instrument created by humans as an alternative way of expression. For this reason, it has found its use in clinical contexts to improve mood, increase participation in therapy, or improve communication for patients with different pathologies. In this systematic mini-review, the Preferred Reporting Item for Systematic Reviews and Meta-Analysis (PRISMA) guidelines were adopted. Internet-based bibliographic searches were conducted via major electronic databases (Web of Science and PubMed). We analyzed the quantitative studies in which art figures as a neurorehabilitation treatment to identify whether standard art therapy protocols exist and whether these are based on the principles of neuroaesthetics. Our review identified 8 quantitative and 18 qualitative studies. Although art therapy has been used for more than 20 years as a clinical tool, there are no standard protocols to refer to when planning interventions. Although the effectiveness of using arts as therapy has been reported in many qualitative or feasibility studies, there is still a lack of quantitative studies in which the outcomes of art therapy are directly based on the principles of neuroaesthetics.

Efficacy of videogames and exergames in pediatric neurorehabilitation: a systematic review.

INTRODUCTION: In recent years, the rehabilitation of children with neurological disorders has taken into account the possibility of using videogaming consoles and virtual reality systems to make children's therapy more enjoyable, motivating, participated and effective. This study aims at conducting a systematic review about the use and the efficacy of digital games in pediatric neurorehabilitation. EVIDENCE ACQUISITION: In accordance with the PRISMA approach, a rather wide-ranging search was conducted on PubMed, Scopus, and Web of Science databases by using different combinations of keywords based on MeSH terms. EVIDENCE SYNTHESIS: Fifty-five papers have been included into this review, namely, 38 original studies and 17 reviews. The total number of children and adolescents is 573, with 58% of them being affected by cerebral palsy. Despite a wide variability in the adopted protocols, devices, assessment tools, and a more frequent focus on motor aspects than on cognitive ones, the results of the majority of the analyzed studies support the safety (i.e., absence of severe adverse effects) and efficacy of the videogame-based therapy. CONCLUSIONS: Videogames, when administered by means of commercial consoles or ad-hoc digital systems, seem to be a valid support for physical therapy. Further researchers are needed to deeply investigate the role of this approach in cognitive therapy and cognitive outcomes.

The impact of cognitive function deficits and their recovery on functional outcome in subjects affected by ischemic subacute stroke: results from the Italian multicenter longitudinal study CogniReMo.

BACKGROUND: The recovery of independence in activities of daily living is a fundamental goal of rehabilitation programs in subjects affected by subacute stroke. Rehabilitation is focused both on motor and cognitive aspects, and some evidence has reported cognitive deficits as prognostic factors of motor recovery. However, rehabilitation is a dynamic process during which executive functions and motor functions should be improved. AIM: The aim of the study is to evaluate the relationships between impairments in cognitive functions and recovery of functional independence in stroke patients during the subacute phase. DESIGN: Multicenter observational study. SETTING: Intensive rehabilitation units. POPULATION: A sample of 319 stroke patients in subacute phase (70.6±11.6 years, 40.4% females), consecutively admitted from November 2019 to July 2021 at sixteen rehabilitation centers were enrolled in this observational, prospective and multicentric study with longitudinal assessments. METHODS: Cognitive and functional assessments were performed at hospital admission and discharge, including Oxford Cognitive Screen, modified Barthel Index, Functional Independent Measure, Fugl-Meyer assessment scale and National Institutes of Health Stroke Scale. RESULTS: A regression analysis identified five predictors (out of about 200 tested variables) of functional recovery related to four aspects assessed at admission: functional status (P<0.001), lower limb functioning (P=0.002), attention (P=0.011), and executive functions (P=0.017). Furthermore, patients who recovered deficits in executive functions had the same recovery of those without deficits, whereas those who maintained deficits had a smaller recovery (P=0.019). CONCLUSIONS: The relationship between cognitive and motor deficits is increasingly highlighted and the recovery of executive functions deficits seems to contribute to motor recovery. CLINICAL REHABILITATION IMPACT: Our results suggest that the recovery of executive functions may promote the recovery of the functional outcome of the patient with subacute stroke. Future treatment protocols may benefit from paying more attention to the recovery of executive functions.

Virtual Art Therapy: Application of Michelangelo Effect to Neurorehabilitation of Patients with Stroke.

In neurorehabilitation, some studies reported the effective use of art therapy for reducing psychological disorders and for enhancing physical functions and cognitive abilities. Neuroaesthetical studies showed that seeing an art masterpiece can spontaneously elicit a widespread brain arousal, also involving motor networks. To combine contemplative and performative benefits of art therapy protocols, we have developed an immersive virtual reality system, giving subjects the illusion that they are able to paint a copy of famous artistic paintings. We previously observed that during this virtual task, subjects perceived less fatigue and performed more accurate movements than when they were asked to color the virtual canvas. We named this upshot the Michelangelo effect. The aim of this study was to test the rehabilitative efficacy of our system. Ten patients with stroke in the subacute phase were enrolled and trained for one month with virtual art therapy (VAT) and physiotherapy. Their data were compared with those of ten patients matched for pathology, age and clinical parameters, trained only with conventional therapy for the same amount of time. The VAT group showed a significantly higher improvements in the Barthel Index score, a measure of independency in activities of daily living (66 ± 33% vs. 31 ± 28%, p = 0.021), and in pinching strength (66 ± 39% vs. 18 ± 33%, p = 0.008), with respect to the group treated with conventional rehabilitation.