Background and Objectives: Progressive supranuclear paralysis (PSP) is an atypical parkinsonian disorder associated with oculomotor features, motor disturbances, along with cognitive problems and neuropsychiatric symptoms. Quality of life (QoL) is often assessed in relation to the motor symptoms. Our aim was to investigate the impact of neuropsychiatric symptoms on QoL.Methods: We used data from 40 patients meeting criteria for probable PSP from the Rossy PSP Centre. Motor and neuropsychiatric symptoms, cognition, functionality, disease severity, and quality of life were examined using validated scales. We performed a linear regression model using multiple imputations with chained equations with 500 sets.Results: We found that lower quality of life scores were related to higher anxiety and depression and the interaction between these two. There was a decrease in the quality of life of −3.7 points (95% CI: −6.1 to −1.1) for every one point of increase on the depression scale; there was a decrease in the quality of life scale of −4.3 points for each point of increase on the depression score (95% CI: −7.8 to −0.8). The fully adjusted linear model showed that motor scores, cognition, and other neuropsychiatric symptoms were not associated with quality of life.Conclusion: We found that both anxiety and depression significantly impacted quality of life. Given the prevalence of non‐motor manifestations in PSP, these results emphasize the importance of comprehensive evaluations to better capture the multi‐faceted impairments seen in PSP that have a meaningful impact on the patient's life.

Objectives: To examine patient activation levels among Arabic-speaking adults with epilepsy and to explore their associations with selected clinical and sociodemographic variables. Methods: We conducted a cross-sectional study of 109 adult patients with confirmed epilepsy between December 2023 and October 2025. Data were collected during outpatient clinic visits, with additional information obtained through telephone contact when necessary. A sample size estimate indicated that at least 96 participants were required to achieve 80% statistical power. Patient activation was assessed using the validated Arabic version of the 13-item Patient Activation Measure (PAM-13). The variables examined included seizure type, medication regimen (monotherapy versus polytherapy), employment status, and medication adherence. Self-reported adherence was categorized as high or low based on patient responses regarding medication-taking behavior. Statistical analyses were performed using SPSS version 27. PAM scores were compared across relevant groups using appropriate bivariate statistical tests, and a p value <0.05 was considered to indicate statistical significance. Results: The mean PAM score was 66.2 ± 17.6, corresponding to a moderate level of activation. Most participants (86.2%) demonstrated activation levels of 3 or 4. Focal epilepsy was more common (62.4%) than generalized epilepsy was (37.6%). Monotherapy was used by 51.4% of the participants, and 77.1% reported high medication adherence. Compared with unemployed or retired participants, employed individuals had significantly higher PAM scores (72.0 vs. 60.0, p<0.01). Greater adherence was also associated with greater activation (p<0.01). No significant associations were observed between PAM scores and seizure types or treatment regimens. Conclusion: Most patients demonstrated moderate to high activation levels. Employment status and medication adherence were positively associated with activation, suggesting potential targets for interventions aimed at improving self-management among individuals with epilepsy.

Background: Epilepsy affects around 50 million people worldwide and remains a major diagnostic challenge, particularly in resource-limited settings. Electroencephalography (EEG) is essential for diagnosis but relies heavily on expert interpretation, often limited by workforce shortages. Artificial intelligence (AI) offers a promising solution to automate EEG interpretation, enhance diagnostic accuracy, and improving diagnostic efficiency. Methods: This retrospective diagnostic validation study was conducted to evaluate the performance of an AI-based system for automated EEG interpretation. A total of 649 EEG recordings from patients aged 1–91 years were analyzed, with expert neurophysiologist interpretations serving as the reference standard. The AI model, developed using a deep learning architecture, was trained to classify EEGs as normal or abnormal and to further categorize findings into epileptiform-focal, epileptiform-generalized, non-epileptiform-focal, and non-epileptiform-diffuse. Performance metrics included sensitivity, specificity, accuracy, area under the ROC curve (AUC), and Cohen’s kappa coefficient for agreement. Results: The model achieved an overall diagnostic accuracy of 93.8% (95% CI: 90.9–96.0) and an AUC of 0.94, demonstrating strong discriminative ability. Sensitivity for abnormal EEG detection was 99.0%, with specificity of 89.7%, PPV of 98.7%, and NPV of 90.0%. Agreement with expert interpretations was κ = 0.87 (p < 0.001), indicating almost perfect concordance. The model maintained robust performance across clinical contexts, with false positives (5.5%) exceeding false negatives (0.5%), reflecting a safety-oriented error profile suited for screening. No statistically significant impact of artifact presence, sleep state, or EEG type was observed on classification accuracy. Conclusions: The model demonstrated high diagnostic accuracy and near-perfect agreement with expert interpreters, highlighting its potential as a clinical decision-support tool for EEG triage and preliminary screening. Integration into real-world workflows could help alleviate workforce shortages, reduce diagnostic delays, and improve early epilepsy detection—particularly in underserved regions. Further refinement, including enhanced artifact handling and diverse dataset validation, will be essential for clinical deployment.