Background/Objectives: Diabetic retinopathy (DR) remains a leading cause of preventable blindness, with its global prevalence projected to rise sharply as diabetes incidence increases. Early detection and timely management are critical to reducing DR-related vision loss. Optical Coherence Tomography Angiography (OCTA) now enables non-invasive, layer-specific visualization of the retinal vasculature, facilitating more precise identification of early microvascular changes. Concurrently, advancements in artificial intelligence (AI), particularly deep learning (DL) architectures such as convolutional neural networks (CNNs), attention-based models, and Vision Transformers (ViTs), have revolutionized image analysis. These AI-driven tools substantially enhance the sensitivity, specificity, and interpretability of DR screening. Methods: A systematic review of PubMed, Scopus, WOS, and Embase databases, including quality assessment of published studies, investigating the result of different AI algorithms with OCTA parameters in DR patients was conducted. The variables of interest comprised training databases, type of image, imaging modality, number of images, outcomes, algorithm/model used, and performance metrics. Results: A total of 32 studies were included in this systematic review. In comparison to conventional ML techniques, our results indicated that DL algorithms significantly improve the accuracy, sensitivity, and specificity of DR screening. Multi-branch CNNs, ensemble architectures, and ViTs were among the sophisticated models with remarkable performance metrics. Several studies reported that accuracy and area under the curve (AUC) values were higher than 99%. Conclusions: This systematic review underscores the transformative potential of integrating advanced DL and machine learning (ML) algorithms with OCTA imaging for DR screening. By synthesizing evidence from 32 studies, we highlight the unique capabilities of AI-OCTA systems in improving diagnostic accuracy, enabling early detection, and streamlining clinical workflows. These advancements promise to enhance patient management by facilitating timely interventions and reducing the burden of DR-related vision loss. Furthermore, this review provides critical recommendations for clinical practice, emphasizing the need for robust validation, ethical considerations, and equitable implementation to ensure the widespread adoption of AI-OCTA technologies. Future research should focus on multicenter studies, multimodal integration, and real-world validation to maximize the clinical impact of these innovative tools.

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.

Corneal ulcer is one of the most important ophthalmic emergencies. A portable, recordable, and smartphone-attachable slit-lamp device called the “Smart Eye Camera” (SEC) is introduced to compare evaluating corneal ulcers between the SEC and the conventional slit-lamp. A total of 110 participants were included in the study, consisting of 55 patients with corneal ulcers and 55 age- and gender-matched healthy volunteers as controls. The participants were first subjected to examination by a conventional slit lamp. The video recording with SEC and imaging with a slit lamp were done by a non-medical person. Both SEC videos and slit-lamp photos were reported by two independent ophthalmologists and compared with a slit-lamp examination as a gold standard. The average age of the study participants was 48.85 ± 20.45 years and 68 participants (61.8%) were male. All corneal ulcers were detected by two ophthalmologists using SEC. Ulcer size evaluated in slit lamp and SEC horizontally (Intraclass Correlation Coefficient (ICC); 0.90, 95% CI; 0.84–0.94) and vertically (ICC; 0.90, 95% CI; 0.84–0.94) is correlated about 90%. Hypopyon size (ICC; 0.95, 95% CI; 0.92–0.97), and corneal epithelial defect (CED) size horizontally (ICC; 0.94, 95% CI; 0.91–0.96) and vertically (ICC; 0.94, 95% CI; 0.91–0.96) also correlated about 94%. The infiltration pattern evaluated by SEC was consistent with the pattern evaluated in slit lamps in more than 80% of patients. The SEC is so accurate in diagnosing corneal ulcers and its reliability makes it a valuable telemedicine device.

Purpose: The Moraxella species is a very uncommon pathogen that leads to microbial keratitis (MK). This study aimed to evaluate the clinical features, predisposing factors, and outcomes of Moraxella keratitis in patients of a tertiary eye hospital. Methods: This retrospective study was conducted from 2015 to 2022, on patients who were admitted with the diagnosis of Moraxella keratitis confirmed by positive culture in a referral eye hospital. Demographics, predisposing factors, best-corrected visual acuity (BCVA), and prognosis were assessed. Results: A total of 106 individuals diagnosed with Moraxella keratitis, were analyzed. The mean age was 54.42 ± 19.43 years. The mean baseline BCVA of the patients was 2.28 ± 0.6 LogMAR, while this amount reached 1.49 ± 0.81 in the 6-month follow-up (P-value = 0.02). The mean BCVA in the six-month follow-up of the patients who needed surgical interventions was significantly lower than the patients who received only medical treatment (2.15 ± 0.65 vs. 1.29 ± 0.75 LogMAR, P-value = 0.02). Patients with diabetes and those without diabetes did not substantially vary in the prevalence of corneal perforation (P-value = 0.515). Three predisposing factors including corneal perforation (odds ratio = 19.27, P-value = 0.001), hypertension (HTN) (odds ratio = 3.62, P-value = 0.03), and older age (odds ratio = 1.03, P-value = 0.008) were significantly associated with more need for surgical interventions. Conclusion: In this cohort, poor prognosis necessitating surgical interventions in Moraxella keratitis was found to be associated with corneal perforation, HTN, and older age.

We evaluated the clinical applications of artificial intelligence models in diagnosing corneal diseases, highlighting their performance metrics and clinical potential. A systematic search was conducted for several disease categories: keratoconus (KC), Fuch’s endothelial corneal dystrophy (FECD), infectious keratitis (IK), corneal neuropathy, dry eye disease (DED), and conjunctival diseases. Metrics such as sensitivity, specificity, accuracy, and area under the curve (AUC) were extracted. Across the diseases, convolutional neural networks and other deep learning models frequently achieved or exceeded established diagnostic benchmarks (AUC > 0.90; sensitivity/specificity > 0.85–0.90), with a particularly strong performance for KC and FECD when trained on consistent imaging modalities such as anterior segment optical coherence tomography (AS-OCT). Models for IK and conjunctival diseases showed promise but faced challenges in heterogeneous image quality and limited objective training criteria. DED and tear film models benefited from multimodal data yet lacked direct comparisons with expert clinicians. Despite high diagnostic precision, challenges from heterogeneous data, a lack of standardization in disease definitions, imaging acquisition, and model training remain. The broad implementation of artificial intelligence must address these limitations to improve eye care equity.