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.

Venous thromboembolism (VTE) (deep vein thrombosis and its complication, pulmonary embolism) is a major cause of morbidity and mortality in hospitalized patients and about 7% of these cases are due to immobility secondary to a neurological impairment. Acquired brain injury (ABI) has also been recognized as one of the main risk factors for VTE. Numerous epidemiological studies have been conducted to assess the risk factors for VTE in institutionalized polytrauma patients, although there is a lack of information about neurorehabilitation wards. Since VTE is often undiagnosed, this prospective study aimed to determine the prevalence and clinical characteristics of lower-limb deep venous thrombosis (DVT) in ABI patients at neurorehabilitation admission. Methods: ABI patients were screened for DVT on admission to the intensive rehabilitation unit (IRU) with compression ultrasonography and basal D-dimer assay and were daily clinically monitored until discharge. A total of 127 consecutive ABI patients (mean age: 60.1 ± 17.6 years; 63% male; time from event: 30.9 ± 22.1 days; rehabilitation time in IRU: 84.6 ± 58.4 days) were enrolled. Results: On admission to the IRU, the DVT prevalence was about 8.6%. The mean D-dimer level in patients with DVT was significantly higher than in patients without DVT (6 ± 0.9 vs. 1.97 ± 1.61, p-value = 0.0001). ABI patients with DVT did not show any significant clinical characteristics with respect to ABI without DVT, although a prevalence of hemorrhagic strokes and patients originating from the Intensive Care Unit and Neurosurgery ward was revealed. During the rehabilitation period, patients with DVT showed a significant difference in pharmacological DVT prophylaxis (high prevalence of nadroparin with 27.3% vs. 1.7%, p-value = 0.04) and a prevalence of transfers in critical awards (36% versus 9.5% of patients without DVT, p-value = 0.05). The mortality rate was similar in the two groups. Conclusions: Our research offers a more comprehensive view of the clinical development of DVT patients and confirms the prevalence rate of DVT in ABI patients as determined upon IRU admission. According to our findings, screening these individuals regularly at the time of rehabilitation admission may help identify asymptomatic DVT quickly and initiate the proper treatment to avoid potentially fatal consequences. However, to avoid time-consuming general ultrasonography observation, a more precise selection of patients entering the rehabilitation ward is required.

Although botulinum toxin is widely considered an effective and safe treatment for a variety of neurological conditions (such as disabling spasticity), local or systemic adverse effects have often been reported. This study describes three cases of patients with severe acquired brain injury who were receiving speech therapy for recovering dysphagia and dysarthria but showed worsening of these symptoms after receiving BoNT treatment for motor spasticity. To increase clinicians’ knowledge of these adverse effects, we present our cases and explore their significance to avoid major complications such as aspiration pneumonia.