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.

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.

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.

Early onset ataxia represents a group of heterogeneous neurological conditions typically characterized by motor disability. Speech problems are one of the main core features of ataxic syndromes, where automatic and computational characterization of speech impairment might represent a source of biomarkers for early screening and stratification of patients. The main contribution of this paper consists in proposing a novel hierarchical machine learning model (HMLM) to improve detection and assessment of dysarthria from a structured speech disturbance test. Performances are tested on a new audio dataset containing 10 seconds recordings of standardized clinical PATA test for 55 subjects: 18 healthy subjects and 37 with ataxia. Results show that the proposed HMLM achieves performances with an accuracy of about 90% at the first level (healthy vs patients) selecting an optimal subset of conventional features. In cascade, at the second level, speech disturbance severity (Low vs High) is assessed using deep learning feature extraction technique based on a VGG pre-trained network with maximum accuracy of about 80%. Both levels are processed through the majority voting ensemble technique testing Support Vector Machine (SVM), k-Nearest Neighbors (kNN), Decision Tree (DT) and Naïve Bayes (NB). In our results, the use of HMLM considerably outperforms the results achieved with a single machine learning or deep learning modeling. These outcomes demonstrate that the investigation of the PATA speech test through HMLM can be considered very promising. We also observed that the use of conventional feature extraction techniques and machine learning modeling seems to be a good solution for the diagnosis of patients with ataxia, while the deep learning approach is more appropriate for stratification of severity of dysarthria.

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.