This study aimed to evaluate the performance of seven advanced AI Large Language Models (LLMs)—ChatGPT 4o, ChatGPT O3 Mini, ChatGPT O1, DeepSeek V3, DeepSeek R1, Gemini 2.0 Flash, and Grok-3—in answering multiple-choice questions (MCQs) in optics and refractive surgery, to assess their role in medical education for residents. The AI models were tested using 134 publicly available MCQs from national ophthalmology certification exams, categorized by the need to perform calculations, the relevant subspecialty, and the use of images. Accuracy was analyzed and compared statistically. ChatGPT O1 achieved the highest overall accuracy (83.5%), excelling in complex optical calculations (84.1%) and optics questions (82.4%). DeepSeek V3 displayed superior accuracy in refractive surgery-related questions (89.7%), followed by ChatGPT O3 Mini (88.4%). ChatGPT O3 Mini significantly outperformed others in image analysis, with 88.2% accuracy. Moreover, ChatGPT O1 demonstrated comparable accuracy rates for both calculated and non-calculated questions (84.1% vs. 83.3%). This is in stark contrast to other models, which exhibited significant discrepancies in accuracy for calculated and non-calculated questions. The findings highlight the ability of LLMs to achieve high accuracy in ophthalmology MCQs, particularly in complex optical calculations and visual items. These results suggest potential applications in exam preparation and medical training contexts, while underscoring the need for future studies designed to directly evaluate their role and impact in medical education. The findings highlight the significant potential of AI models in ophthalmology education, particularly in performing complex optical calculations and visual stem questions. Future studies should utilize larger, multilingual datasets to confirm and extend these preliminary findings.

Background: Convergence insufficiency (CI) is a common binocular vision disorder that causes eye strain, headaches, and blurriness. Although pencil push-ups (PPU) are widely used to treat CI, their real-world effectiveness may be limited by inconsistent performance and poor adherence. MobileS (the App) is an AI-based smartphone application that tracks eye movements through the front camera, enabling guided “digital push-ups” with instant visual feedback and automatic performance monitoring. This follow-up study evaluated the feasibility, recorded adherence, and preliminary clinical signals of MobileS as a home-based therapy for CI compared with conventional PPU. Methods: Twenty-five participants with CI were randomly assigned to either the App group (n = 12) or the PPU group (n = 13) for 8 weeks of home-based training. Both groups performed convergence push-ups—using the app or a pencil. NPC was measured using a RAF ruler at baseline, mid-point, and endpoint. Symptom severity was assessed using the Convergence Insufficiency Symptom Survey (CISS), and adherence was recorded automatically by the app or manually by participants. Results: All 25 randomized participants completed all three NPC assessment points. The App group showed a statistically significant improvement in NPC from baseline to study completion (mean improvement = 2.81 cm, p = 0.007), whereas the PPU group showed no significant change. Recorded adherence was higher in the App group compared with the PPU group (90.1% vs. 75.4%, p = 0.0069). The App group showed a significant reduction in symptom severity (p = 0.049). Between-group differences in symptom change were not statistically significant. Conclusions: MobileS appears feasible as a home-based CI management tool, and was associated with higher recorded adherence and preliminary NPC improvement signals. Larger, adequately powered studies are needed to confirm efficacy, particularly for symptoms, and guide teleophthalmology implementation.

Objective: To assess the accuracy and clinical education value of responses from AI models (GPT-3.5, GPT-4o, Gemini, Gemini Advanced) compared to expert ophthalmologists’ answers to common patient questions about blepharitis, and evaluate their potential for patient education and clinical use. Methods: Thirteen frequently asked questions about blepharitis were selected. Responses were generated by AI models and compared to expert answers. A panel of ophthalmologists rated each response for correctness and clinical education value using a 7-point Likert scale. The Friedman test with post hoc comparisons was used to identify performance differences. Results: Expert responses had the highest correctness (6.3) and clinical education value (6.4) scores, especially in complex, context-driven questions. Significant differences were found between expert and AI responses ( P < 0.05). Among AI models, GPT-3.5 performed best in simple definitions (correctness: 6.4) but dropped to 5.5 in nuanced cases. GPT-4o followed (5.4), while Gemini and Gemini Advanced scored lower (5.0 and 4.9), especially in diagnostic and treatment contexts. Conclusions: AI models can support patient education by effectively answering basic factual questions about blepharitis. However, their limitations in complex clinical scenarios highlight the continued need for expert input. While promising as educational tools, AI should complement—not replace—clinician guidance in patient care.