Exploring ChatGPT's potential in the clinical stream of neurorehabilitation.

In several medical fields, generative AI tools such as ChatGPT have achieved optimal performance in identifying correct diagnoses only by evaluating narrative clinical descriptions of cases. The most active fields of application include oncology and COVID-19-related symptoms, with preliminary relevant results also in psychiatric and neurological domains. This scoping review aims to introduce the arrival of ChatGPT applications in neurorehabilitation practice, where such AI-driven solutions have the potential to revolutionize patient care and assistance. First, a comprehensive overview of ChatGPT, including its design, and potential applications in medicine is provided. Second, the remarkable natural language processing skills and limitations of these models are examined with a focus on their use in neurorehabilitation. In this context, we present two case scenarios to evaluate ChatGPT ability to resolve higher-order clinical reasoning. Overall, we provide support to the first evidence that generative AI can meaningfully integrate as a facilitator into neurorehabilitation practice, aiding physicians in defining increasingly efficacious diagnostic and personalized prognostic plans.

Multiparametric Evaluation of Geriatric Patients Admitted to Intermediate Care: Impact on Geriatric Rehabilitation.

Optimizing the functional status of patients of any age is a major global public health goal. Rehabilitation is a process in which a person with disabilities is accompanied to achieve the best possible physical, functional, social, intellectual, and relational outcomes. The Intermediate Care Unit within the O.U. of Geriatrics and Gerontology of the San Martino Hospital in Genoa is focused on the treatment and motor reactivation of patients with geriatric pathologies. The objective of this study was to identify which factor, among the characteristics related to the patient and those identified by the geriatric evaluation, had the greatest impact on rehabilitation outcomes. Our findings revealed significant correlations between the Barthel Index delta, the 4AT Screening Test, and the number of drugs taken. This association highlights the potential benefits of medication management in enhancing the overall well-being and functional abilities of frail older adults, despite the literature suggesting that polypharmacotherapy is associated with a reduction in functional status and an increase in mortality. These findings underscore the significance of a multidimensional geriatric assessment. Refining and optimising these multidisciplinary approaches is the objective of a more effective geriatric rehabilitation strategy.

Application of Machine Learning Algorithms for Prognostic Assessment in Rotator Cuff Pathologies: A Clinical Data-Based Approach.

AIM: The overall aim of this proposal is to ameliorate the care of rotator cuff (RC) tear patients by applying an innovative machine learning approach for outcome prediction after arthroscopic repair. MATERIALS AND METHODS: We applied state-of-the-art machine learning algorithms to evaluate the best predictors of the outcome, and 100 RC patients were evaluated at baseline (T0), after 1 month (T1), 3 months (T2), 6 months (T3), and 1 year (T4) from surgical intervention. The outcome measure was the Costant-Murley Shoulder Score, whereas age, sex, BMI, the 36-Item Short-Form Survey, the Simple Shoulder Test, the Hospital Anxiety and Depression Scale, the American Shoulder and Elbow Surgeons Score, the Oxford Shoulder Score, and the Shoulder Pain and Disability Index were considered as predictive factors. Support vector machine (SVM), k-nearest neighbors (k-NN), naïve Bayes (NB), and random forest (RF) algorithms were employed. RESULTS: Across all sessions, the classifiers demonstrated suboptimal performance when using both the complete and shrunken sets of features. Specifically, the logistic regression (LR) classifier achieved a mean accuracy of 46.5% ± 6%, while the random forest (RF) classifier achieved 51.25% ± 4%. For the shrunken set of features, LR obtained a mean accuracy of 48.5% ± 6%, and RF achieved 45.5% ± 4.5%. No statistical differences were found when comparing the performance metrics of ML algorithms. CONCLUSIONS: This study underlines the importance of extending the application of AI methods to new predictors, such as neuroimaging and kinematic data, in order to better record significant shifts in RC patients' prognosis. LIMITATIONS: The data quality within the cohort could represent a limitation, since certain variables, such as smoking, diabetes, and work injury, are known to have an impact on the outcome.

TeleRehabilitation of Social-Pragmatic Skills in Children with Autism Spectrum Disorder: A Principal Component Analysis.

In many therapeutic settings, remote health services are becoming increasingly a viable strategy for behavior management interventions in children with autism spectrum disorder (ASD). However, there is a paucity of tools for recovering social-pragmatic skills. In this study, we sought to demonstrate the effectiveness of a new online behavioral training, comparing the performance of an ASD group carrying out an online treatment (n°8) with respect to a control group of demographically-/clinically matched ASD children (n°8) engaged in a traditional in-presence intervention (face-to-face). After a 4-month behavioral treatment, the pragmatic skills language (APL test) abilities detected in the experimental group were almost similar to the control group. However, principal component analysis (PCA) demonstrated that the overall improvement in socio-pragmatic skills was higher for ASD children who underwent in-presence training. In fact, dimensions defined by merging APL subscale scores are clearly separated in ASD children who underwent in-presence training with respect to those performing the online approach. Our findings support the effectiveness of remote healthcare systems in managing the social skills of children with ASD, but more approaches and resources are required to enhance remote services.

Predicting Outcome in Patients with Brain Injury: Differences between Machine Learning versus Conventional Statistics.

Defining reliable tools for early prediction of outcome is the main target for physicians to guide care decisions in patients with brain injury. The application of machine learning (ML) is rapidly increasing in this field of study, but with a poor translation to clinical practice. This is basically dependent on the uncertainty about the advantages of this novel technique with respect to traditional approaches. In this review we address the main differences between ML techniques and traditional statistics (such as logistic regression, LR) applied for predicting outcome in patients with stroke and traumatic brain injury (TBI). Thirteen papers directly addressing the different performance among ML and LR methods were included in this review. Basically, ML algorithms do not outperform traditional regression approaches for outcome prediction in brain injury. Better performance of specific ML algorithms (such as Artificial neural networks) was mainly described in the stroke domain, but the high heterogeneity in features extracted from low-dimensional clinical data reduces the enthusiasm for applying this powerful method in clinical practice. To better capture and predict the dynamic changes in patients with brain injury during intensive care courses ML algorithms should be extended to high-dimensional data extracted from neuroimaging (structural and fMRI), EEG and genetics.

Mediating Mindfulness-Based Interventions with Virtual Reality in Non-Clinical Populations: The State-of-the-Art.

Mindfulness is one of the most popular psychotherapeutic techniques that help to promote good mental and physical health. Combining mindfulness with immersive virtual reality (VR) has been proven to be especially effective for a wide range of mood disorders for which traditional mindfulness has proven valuable. However, the vast majority of immersive VR-enhanced mindfulness applications have focused on clinical settings, with little evidence on healthy subjects. This narrative review evaluates the real effectiveness of state-of-the-art mindfulness interventions mediated by VR systems in influencing mood and physiological status in non-clinical populations. Only studies with an RCT study design were considered. We conclude that most studies were characterized by one single meditation experience, which seemed sufficient to induce a significant reduction in negative mood states (anxiety, anger, depression, tension) combined with increased mindfulness skills. However, physiological correlates of mindfulness practices have scarcely been investigated. The application of VR-enhanced mindfulness-based interventions in non-clinical populations is in its infancy since most studies have several limitations, such as the poor employment of the RCT study design, the lack of physiological measurements (i.e., heart rate variability), as well as the high heterogeneity in demographical data, technological devices, and VR procedures. We thus concluded that before applying mindfulness interventions mediated by VR in clinical populations, more robust and reliable methodological procedures need to be defined.

Heterologous COVID-19 Booster Vaccination in the Chronic Disorder of Consciousness: A Pilot Study.

Significant anti-spike protein receptor-binding domain (S-RBD) antibody responses have been demonstrated in patients with chronic disorder of consciousness (DOC) completing a COVID-19 vaccine regime with BNT162b2 (Pfizer-BioNTech). We now provide further prospective data on the immunogenicity of these patients followed by heterologous booster injection with mRNA-1273 (Moderna). These patients were compared with two different demographically comparable healthcare workers (HCW) groups who underwent homologous booster injection with BNT162b2 vaccine or heterologous booster injection with mRNA-1273. Antibody responses were evaluated at 21 days after the administration of the booster dose of vaccination. Results: No severe adverse reactions were reported after each type of vaccination. Heterologous boosting with mRNA-1273 elicited a higher increase of S-RBD IgG levels than homologous boosting with BNT162b2 both in DOC patients and HCW who had previously received two doses of BNT162b2. No significant difference was detected between DOC and HCW patients who received heterologous boosting. Conclusions: Despite the small sample size, our preliminary results suggest that heterologous boosting with mRNA-1273, following initial vaccination with BNT162b2, is safe and tends to be more immunogenic than homologous boosting, either in fragile people or in healthy controls.

Gender Influences Virtual Reality-Based Recovery of Cognitive Functions in Patients with Traumatic Brain Injury: A Secondary Analysis of a Randomized Clinical Trial.

The rehabilitation of cognitive deficits in individuals with traumatic brain injury is essential for promoting patients' recovery and autonomy. Virtual reality (VR) training is a powerful tool for reaching this target, although the effectiveness of this intervention could be interfered with by several factors. In this study, we evaluated if demographical and clinical variables could be related to the recovery of cognitive function in TBI patients after a well-validated VR training. One hundred patients with TBI were enrolled in this study and equally randomized into the Traditional Cognitive Rehabilitation Group (TCRG: n = 50) or Virtual Reality Training Group (VRTG: n = 50). The VRTG underwent a VRT with BTs-N, whereas the TCRG received standard cognitive treatment. All the patients were evaluated by a complete neuropsychological battery before (T0) and after the end of the training (T1). We found that the VR-related improvement in mood, as well as cognitive flexibility, and selective attention were influenced by gender. Indeed, females who underwent VR training were those showing better cognitive recovery. This study highlights the importance of evaluating gender effects in planning cognitive rehabilitation programs. The inclusion of different repetitions and modalities of VR training should be considered for TBI male patients.

Predicting Outcome of Traumatic Brain Injury: Is Machine Learning the Best Way?

One of the main challenges in traumatic brain injury (TBI) patients is to achieve an early and definite prognosis. Despite the recent development of algorithms based on artificial intelligence for the identification of these prognostic factors relevant for clinical practice, the literature lacks a rigorous comparison among classical regression and machine learning (ML) models. This study aims at providing this comparison on a sample of TBI patients evaluated at baseline (T0), after 3 months from the event (T1), and at discharge (T2). A Classical Linear Regression Model (LM) was compared with independent performances of Support Vector Machine (SVM), k-Nearest Neighbors (k-NN), Naïve Bayes (NB) and Decision Tree (DT) algorithms, together with an ensemble ML approach. The accuracy was similar among LM and ML algorithms on the analyzed sample when two classes of outcome (Positive vs. Negative) approach was used, whereas the NB algorithm showed the worst performance. This study highlights the utility of comparing traditional regression modeling to ML, particularly when using a small number of reliable predictor variables after TBI. The dataset of clinical data used to train ML algorithms will be publicly available to other researchers for future comparisons.

Anti-SARS-CoV-2 S-RBD IgG Antibody Responses after COVID-19 mRNA Vaccine in the Chronic Disorder of Consciousness: A Pilot Study.

OBJECTIVE: In the last year, a large amount of research has investigated the anti-spike protein receptor-binding domain (S-RBD) antibody responses in patients at high risk of developing severe acute respiratory syndrome because of COVID-19 infection. However, no data are available on the chronic disorder of consciousness (DOC). METHODS: Here, we evaluated anti-S-RBD IgG levels after vaccination in chronic DOC patients compared with demographically matched healthy controls (HC) by indirect chemiluminescence immunoassay. All individuals completed a two-dose-cycle vaccination with Pfizer mRNA vaccine (BNT162b2), and antibody responses were evaluated at 30 and 180 days after the administration of the second dose of vaccination. RESULTS: We compared 32 DOC patients with 34 demographically matched healthy controls. Both DOC and HC groups showed a similar antibody response at 30 days, whereas at follow-up (180 days) DOC patients were characterized by lower S-RBD IgG levels with respect to controls. Additional multiple regression analyses including demographical and clinical comorbidities as predictors revealed that age was the only factor associated with the decrease in S-RBD IgG levels at follow-up (180 days). Elderly individuals of both groups were characterized by a reduction in the antibody responses with respect to younger individuals. CONCLUSIONS: Our results show an efficacy seroconversion in DOC patients in the first period after vaccination, which significantly declines over time with respect to healthy controls.