Background: Optic neuritis (ON), a common manifestation of demyelinating disorders such as multiple sclerosis (MS), neuromyelitis optica spectrum disorder (NMOSD), and myelin oligodendrocyte glycoprotein antibody-associated disease (MOGAD), often leads to significant visual impairment. Although high-dose corticosteroids are a first-line therapy, many patients experience incomplete recovery. Apheresis therapies, including plasma exchange (PLEX) and immunoadsorption (IA), are being increasingly used as rescue treatments, but their efficacy and safety are debated. Methods: We conducted a systematic review and meta-analysis of studies evaluating PLEX and IA for acute ON in patients with demyelinating diseases. Four databases were searched up to January 2025. The included studies reported visual or neurological outcomes in patients with MS, NMOSD, MOGAD, or idiopathic ON. The primary outcomes were treatment response and visual acuity changes (logMAR). The study quality was assessed using RoB 2, ROBINS-I, or JBI tools. Random effects models were employed for the meta-analysis. Results: Twelve studies (800+ ON attacks) were analyzed. Both PLEX and IA demonstrated significant visual improvement, with a pooled mean logMAR reduction of -1.11 (95% CI: -1.70 to -0.53). Early intervention correlated with better outcomes. MOGAD-ON patients showed the highest response rates, while delayed treatment in NMOSD-ON patients was linked to poorer vision. Adverse events were rare and mild. Conclusion: PLEX and IA are effective and safe second-line therapies for steroid-refractory ON, particularly when initiated early. These findings support the prompt use of apheresis in eligible patients to optimize visual recovery.

BACKGROUND Artificial intelligence (AI) applications in dermatology show promising potential for diagnostic support and healthcare accessibility, yet successful implementation requires understanding public acceptance patterns. Limited research has examined attitudes toward AI specifically in dermatology within culturally diverse populations. This study assessed Saudi public attitudes toward AI in dermatology to inform implementation strategies for similar healthcare contexts. OBJECTIVE To evaluate knowledge, attitudes, and acceptance factors regarding AI applications in dermatology among Saudi adults and identify demographic and experiential predictors of AI adoption intentions. METHODS We conducted a cross-sectional online survey among Saudi adults aged 18 years and older from May 21 to June 5, 2025. The survey included 30 items divided into three sections: demographics (10 items), attitudes toward AI in dermatology (20 items on a 5-point Likert scale), and system priority ratings (6 items on a 5-point importance scale). We employed convenience and snowball sampling through social media platforms. For data analysis, we used descriptive statistics, one-way ANOVA for group comparisons, and binary logistic regression to identify predictors of high behavioral intention. We set the statistical significance at P < .05. RESULTS The study included 668 participants (61.1% female, 45.4% aged 18-24 years). Participants demonstrated high overall acceptance of AI in dermatology (mean score: 74.48 ± 10.20, Cronbach's α = 0.868). Strong preferences emerged for physician-supervised AI systems rather than autonomous implementations, with medical supervision receiving the highest endorsement (4.27 ± 0.87), followed by explainable AI decisions (4.12 ± 0.82) and physician authority during diagnostic disagreements (4.11 ± 0.86). While recognizing AI's potential benefits for healthcare access in remote areas (3.92 ± 0.94) and cost reduction (3.81 ± 0.86), participants expressed moderate enthusiasm for personal use (3.60 ± 0.97) and reservations about independent AI diagnosis (3.26 ± 0.97). System priorities emphasized privacy protection (56.4% rated as very important) and diagnostic accuracy (55.8%), followed by cultural compatibility (49.3%) and decision transparency (47.2%). Age significantly influenced acceptance (P = .009), with younger adults (18-24 years) showing the highest acceptance (75.96 ± 9.38). Technology interest demonstrated the strongest associations with both acceptance and perceived importance (P < .001). Healthcare professionals valued AI's importance more than general participants (P = .004) while maintaining similar acceptance levels. Gender, geographic region, education level, and dermatological experience showed no significant associations with acceptance patterns. CONCLUSIONS Saudi adults demonstrate predominantly positive yet nuanced attitudes toward dermatological AI, with strong preferences for collaborative physician-AI models over autonomous systems. Successful implementation requires prioritizing transparent, secure AI architectures with physician oversight, developing targeted educational initiatives across demographic groups, and ensuring cultural responsiveness in AI system design. These findings provide crucial baseline data for AI integration within Saudi Arabia's Vision 2030 healthcare objectives and offer insights relevant for culturally diverse healthcare contexts globally.

Background/Objectives: Artificial intelligence (AI) holds significant potential to enhance diagnostic support and access to dermatological care; however, its adoption depends on public trust and acceptance. This study aimed to assess knowledge, attitudes, and acceptance of dermatological AI among Saudi adults, and to identify factors associated with adoption, trust, and preferred system characteristics. Methods: A nationwide cross-sectional online survey was conducted among 668 Saudi adults (≥18 years) between 21 May and 5 June 2025, using convenience and snowball sampling via social media platforms (WhatsApp, Snapchat, Twitter/X, and Telegram). The questionnaire captured demographics, attitudes toward AI (20-item Likert scale), and perceived importance of six AI system features. Data were analyzed using descriptive statistics, one-way ANOVA, and binary logistic regression. The study was approved by the Institutional Review Board of King Faisal University (Approval No. KFU-REC-2025-MAY-ETHICS3443, approval date 19 May 2025). Results: The mean overall AI attitude orientation score was 74.48 ± 10.20 (Cronbach’s α = 0.868), reflecting moderately positive but conditional attitudes toward dermatological AI. Participants strongly preferred physician-supervised AI over fully autonomous systems, with medical oversight receiving the highest agreement (mean 4.27 ± 0.87). Privacy protection and diagnostic accuracy were rated as the most important system features. Age was significantly associated with the overall AI attitude orientation score (p = 0.009), with younger participants demonstrating more favorable orientations. Interest in technology showed the strongest association with both AI attitude orientation and perceived importance (p < 0.001). No demographic variable independently predicted high intention to use AI in multivariate analysis. Conclusions: Saudi adults generally exhibit favorable yet cautious attitudes toward dermatological AI. Implementation strategies should prioritize physician oversight, transparency, data privacy, and culturally responsive design to support responsible integration into clinical practice.