Multiple sclerosis (MS) is a multifaceted neurological condition characterized by challenges in timely diagnosis and personalized patient management. The application of Artificial Intelligence (AI) to MS holds promises for early detection, accurate diagnosis, and predictive modeling. The objectives of this study are: 1) to propose new MS trajectory descriptors that could be employed in Machine Learning (ML) regressors and classifiers to predict patient evolution; 2) to explore the contribution of ML models in discerning MS trajectory descriptors using only baseline Magnetic Resonance Imaging (MRI) studies. This study involved 446 MS patients who had a baseline MRI, at least two measurements of Expanded Disability Status Scale (EDSS), and a 1-year follow-up. Patients were divided into two groups: 1) for model development and 2) for evaluation. Three descriptors: β₁, β₂, and EDSS(t), were related to baseline MRI parameters using regression and classification XGBoost models. Shapley Additive Explanations (SHAP) analysis enhanced model transparency by identifying influential features. The results of this study demonstrate the potential of AI in predicting MS progression using the proposed patient trajectories and baseline MRI scans, outperforming classic Multiple Linear Regression (MLR) methods. In conclusion, MS trajectory descriptors are crucial; incorporating AI analysis into MRI assessments presents promising opportunities to advance predictive capabilities. SHAP analysis enhances model interpretation, revealing feature importance for clinical decisions.

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder characterized by the accumulation of amyloid-β plaques, tau hyperphosphorylation, and chronic neuroinflammation. Emerging evidence suggests a crucial role of lipid signaling pathways in AD pathogenesis, particularly those mediated by autotaxin (ATX) and lysophosphatidic acid (LPA). ATX, an enzyme responsible for LPA production, has been implicated in neuroinflammatory processes, blood–brain barrier dysfunction, and neuronal degeneration. LPA signaling, through its interaction with specific G-protein-coupled receptors, influences neuroinflammation, synaptic plasticity, and tau pathology, all of which contribute to AD progression. This review synthesizes recent findings on the ATX/LPA axis in AD, exploring its potential as a biomarker and therapeutic target. Understanding the mechanistic links between ATX, LPA, and AD pathology may open new avenues for disease-modifying strategies.

Objective: Encephalitis is brain parenchyma inflammation, frequently resulting in seizures which worsens outcomes. Early anti-seizure medication could improve outcomes but requires identifying patients at greatest risk of acute seizures. The SEIZURE (SEIZUre Risk in Encephalitis) score was developed in UK cohorts to stratify patients by acute seizure risk. A ‘basic score’ used Glasgow Coma Scale (GCS), fever and age; the ‘advanced score’ added aetiology. This study aimed to evaluate the score internationally to determine its global applicability. Design: Patients were retrospectively analysed regionally, and by country, in this international evaluation study. Univariate analysis was conducted between patients who did and did not have inpatient seizures, followed by multivariable logistic regression, hierarchical clustering and analysis of the area under the receiver operating curves (AUROC) with 95% CIs. Participants and setting: 2032 patients across 13 countries were identified, among whom 1324 were included in SEIZURE score calculations and 970 were included in regression modelling. The involved countries comprised 19 organisations spanning all WHO regions. Outcome measures: The primary outcome was measuring inpatient seizure rates. Results: Autoantibody-associated encephalitis, low GCS and presenting with a seizure were frequently associated with inpatient seizures; fever showed no association. Globally, the score had limited discriminatory ability (basic AUROC 0.58 (95% CI 0.55 to 0.62), advanced AUROC 0.63 (95% CI 0.60 to 0.66)). The scoring system performed acceptably in western Europe, excluding Spain, with the best performance in Portugal (basic AUROC 0.82 (95% CI 0.69 to 0.94), advanced AUROC 0.83 (95% CI 0.72 to 0.95)). Conclusions: The SEIZURE score performed best in several countries in Western Europe but performed poorly elsewhere, partly due to differing and unknown aetiologies. In most regions, the score did not reach a threshold to be clinically useful. The Western European results could aid in designing clinical trials assessing primary anti-seizure prophylaxis in encephalitis following further prospective trials. Beyond Western Europe, there is a need for tailored, localised scoring systems and future large-scale prospective studies with optimised aetiological testing to accurately identify high-risk patients.

Objective: To evaluate the effectiveness, tolerability, and retention of PER as monotherapy in adults with focal or idiopathic generalized epilepsy over a 12‐month period in routine clinical practice. Methods: In this single‐center, ambispective, noninterventional observational study, 74 patients (age 18–90 years) initiated PER monotherapy—either as first‐line treatment (n = 21) or conversion from another antiseizure medication (n = 53)—and were followed for 12 months. Demographic and clinical variables, prior antiseizure regimens, indication for PER initiation (suboptimal seizure control, adverse effects, or sleep improvement), PER dosage, seizure outcomes (seizure freedom and ≥ 50% reduction), and adverse events (AEs) were recorded at 6‐ and 12‐month visits. Retention rates were calculated, and safety was assessed by AE reports and discontinuations. Results: The mean PER dose was 7.22 ± 1.71 mg/day, with 85.1% of patients remaining on monotherapy at 12 months (first‐line: 90.5%; conversion: 83.0%). Overall, 70.3% of patients achieved seizure freedom at 12 months (first‐line: 81.0%; conversion: 66.0%), and 79.7% were ≥ 50% responders (first‐line: 85.7%; conversion: 75.5%). In patients initiated for sleep improvement (n = 24), hypnotic medications were withdrawn in 87.5%, and 79% reported better sleep. AEs were reported in 46.2% of patients at 12 months, most commonly somnolence (28.4%), dizziness (18.9%), and irritability (10.8%). Severe AEs leading to discontinuation occurred in 6.7% of cases. Significance: In a real‐world cohort, PER monotherapy demonstrated high rates of seizure freedom and retention, with a manageable safety profile. These findings support PER as an effective and tolerable monotherapy option for adult patients with focal or idiopathic generalized epilepsy, corroborating similar observations in recent Epilepsia Open studies of antiseizure monotherapy. Plain Language Summary: Perampanel (PER) is approved as an add‐on treatment for seizures, but information on its use alone (monotherapy) is scarce. We studied 74 adults who started PER by itself—either as their first treatment or after stopping another medication—over 1 year. Eighty‐five percent stayed on PER for the full year. Seventy percent became seizure‐free, and nearly 80% had their seizures cut by at least half. In those taking PER to improve sleep, most could stop sleep‐aid drugs and reported better rest. Side effects (mostly mild sleepiness, dizziness, or irritability) occurred in about half of patients, but only 7% stopped PER because of them. Our results suggest that PER alone works well and is generally well tolerated in everyday clinical practice.