Artificial intelligence (AI) has been explored as a promising diagnostic aid for ocular surface diseases (OSDs). The spectrum of OSD ranges from highly prevalent benign conditions such as dry eye disease (DED) to rare but potentially dangerous disorders, including ocular surface squamous neoplasia (OSSN) and conjunctival melanoma. This review provides an overview of current applications of AI across the major categories of ocular surface pathology and specifically highlights anterior segment imaging modalities, including slit-lamp examination, optical coherence tomography (OCT), and in vivo confocal microscopy (IVCM). Meibography, tear film dynamics, biochemical profiling, and other DED-related measures are also examined. Across these domains, reported AI model performance matches or exceeds that of ophthalmologists, offering consistent, reproducible, and accurate approaches for guiding diagnosis. However, studies with limited external or prospective validation, variable labeling strategies, and small, device-specific datasets predominate in the current literature, thereby limiting generalizability. Large multicenter datasets, standardized diagnostic frameworks, multimodal integration, and prospective trials that assess human–AI cooperation in practical settings should be an emphasis in future research. By filling these gaps, AI systems could advance from experimental tools to clinically reliable applications that improve access and diagnostic accuracy in the care of ocular surface disease and tumors.

Purpose: To describe a case series of patients who experienced hemorrhagic complications following intravitreal antivascular endothelial growth factor (anti-VEGF) injections. Methods: In a small case series of 3 patients with retinal disorders, imaging with ultrasound biomicroscopy was performed within 1 day following anti-VEGF injection. Results: The first patient had a mild vitreous hemorrhage, and UBM demonstrated a suspected needle track through the pars plana; the hemorrhage cleared spontaneously. The second patient had a dense vitreous hemorrhage as well as hyphema, and UBM demonstrated a suspected needle track through the pars plicata; the hemorrhage did not clear and the patient was subsequently treated elsewhere with pars plana vitrectomy. The third patient had a subconjunctival hemorrhage but no vitreous hemorrhage, and UBM demonstrated no definite evidence of a needle track. Conclusions: In some patients with vitreous hemorrhage following anti-VEGF injection, a suspected needle track may be imaged with UBM within 1 day following injection.

BACKGROUND: Artificial Intelligence (AI) models have shown potential in various educational contexts. However, their utility in explaining complex biological phenomena, such as Intrinsically Disordered Proteins (IDPs), requires further exploration. This study empirically evaluated the performance of various Large Language Models (LLMs) in the educational domain of IDPs. METHODS: Four LLMs, GPT-3.5, GPT-4, GPT-4 with Browsing, and Google Bard (PaLM 2), were assessed using a set of IDP-related questions. An expert evaluated their responses across five categories: accuracy, relevance, depth of understanding, clarity, and overall quality. Descriptive statistics, ANOVA, and Tukey's honesty significant difference tests were utilized for analysis. RESULTS: The GPT-4 model consistently outperformed the others across all evaluation categories. Although GPT-4 and GPT-3.5 were not statistically significantly different in performance (p>0.05), GPT-4 was preferred as the best response in 13 out of 15 instances. The AI models with browsing capabilities, GPT-4 with Browsing and Google Bard (PaLM 2) displayed lower performance metrics across the board with statistically significant differences (p<0.0001). CONCLUSION: Our findings underscore the potential of AI models, particularly LLMs such as GPT-4, in enhancing scientific education, especially in complex domains such as IDPs. Continued innovation and collaboration among AI developers, educators, and researchers are essential to fully harness the potential of AI for enriching scientific education.