Background/Objectives: This study evaluated the diagnostic accuracy of seven publicly available large language models (LLMs)—GPT-3.5, GPT-4.o Mini, GPT-4.o, Gemini 1.5 Flash, Claude 3.5 Sonnet, Grok3, and DeepSeek R1—in diagnosing corneal diseases, comparing their performance to human specialists. Methods: Twenty corneal disease cases from the University of Iowa’s EyeRounds were presented to each LLM. Diagnostic accuracy was determined by comparing LLM-generated diagnoses to the confirmed case diagnoses. Four human cornea specialists evaluated the same cases to establish a benchmark and assess interobserver agreement. Results: Diagnostic accuracy varied significantly among LLMs (p = 0.001). GPT-4.o achieved the highest accuracy (80.0%), followed by Claude 3.5 Sonnet and Grok3 (70.0%), DeepSeek R1 (65.0%), GPT-3.5 (60.0%), GPT-4.o Mini (55.0%), and Gemini 1.5 Flash (30.0%). Human experts averaged 92.5% accuracy, outperforming all LLMs (p < 0.001, Cohen’s d = −1.314). GPT-4.o showed no significant difference from human consensus (p = 0.250, κ = 0.348), while Claude and Grok3 showed fair agreement (κ = 0.219). DeepSeek R1 also performed reasonably (κ = 0.178), although not significantly. Conclusions: Among the evaluated LLMs, GPT-4.o, Claude 3.5 Sonnet, Grok3, and DeepSeek R1 demonstrated promising diagnostic accuracy, with GPT-4.o most closely matching human performance. However, performance remained inconsistent, especially in complex cases. LLMs may offer value as diagnostic support tools, but human expertise remains indispensable for clinical decision-making.

With the increasing prevalence of diabetic retinopathy (DR), screening is of the utmost importance to prevent vision loss for patients and reduce financial costs for the healthcare system. Unfortunately, it appears that the capacity of optometrists and ophthalmologists to adequately perform in-person screenings of DR will be insufficient within the coming years. Telemedicine offers the opportunity to expand access to screening while reducing the economic and temporal burden associated with current in-person protocols. The present literature review summarizes the latest developments in telemedicine for DR screening, considerations for stakeholders, barriers to implementation, and future directions in this area. As the role of telemedicine in DR screening continues to expand, further work will be necessary to continually optimize practices and improve long-term patient outcomes.

To report a case of persistent bilateral sclerouveitis following bilateral bimatoprost implantation (Durysta) that required implant removal and oral steroid course. A 75-year-old Caucasian male with no prior ocular inflammation experienced bilateral sclerouveitis post bilateral bimatoprost implantation. Despite implant removal from both eyes, the ocular inflammation persisted, showing cystoid macular edema in both eyes and exudative retinal detachment in the right. A comprehensive assessment revealed no clear etiology and no definitive systematic inflammatory syndrome. The ocular inflammation was unresponsive to topical steroids and only receded following weeks-long course of oral steroids. Eventually, the patient required immunosuppression due to recurrence of the inflammation. The persistence and severity of this inflammatory response to bimatoprost implants, despite its removal, highlight the importance of considering patient-specific risk factors and tailoring management accordingly. Clinicians should be prepared for possible severe reactions requiring intervention.