This study evaluated the distribution of research on the use of large language models (LLMs) in ophthalmology through a bibliographic analysis of articles retrieved from PubMed through November 2024. Studies were categorized into four main areas of LLM application: clinical decision-making (further divided according to subspecialties), education, patient interactions, and miscellaneous applications. Descriptive statistics were used to analyze the distribution of studies by ophthalmic subspecialty, geographical region, journal quality, and author characteristics, including gender and scholarly impact (h-index and i10-index). The findings revealed that clinical decision-making was the most common application (43.7%), with the majority of studies in this subgroup focusing on the retina (39.5%). Geographically, most of the research originated from North America (48.3%), followed by Asia (29.9%) and Europe (20.7%). Most studies were published in high-impact journals (Q1 journals: 74.7%), particularly for those related to clinical decision-making in retina (80.0%), glaucoma (100%), and multiple subspecialties (87.5%). Gender disparities were evident across all author roles, with female authors accounting for only 29.9% of first authors, 25.3% of last authors, and 26.4% of corresponding authors. The results suggest a need for greater diversity in terms of gender and geographic representation in LLM research in ophthalmology to promote inclusive progress in the field.

The Turkish Journal of Ophthalmology is the only scientific periodical publication of the Turkish Ophthalmological Association and has been published since January 1929 and an open access, scientific, double-blind peer-reviewed journal in the field of ophthalmology and all other health professionals interested in these issues. No fee is charged from the authors during the submission, evaluation and publication process. It is the official publication of the Turkish Ophthalmological Association and is published six times a year.

This study aimed to compare year-over-year change in ChatGPT's performance on nationwide ophthalmology exams with the performance change among residents over the same period. This observational study included ophthalmology residents in Türkiye who participated in both the 2023 and 2024 Resident Training Development Exams organized by the Turkish Ophthalmological Association Qualifications Committee. The 2023 examination consisted of 69 single-best-answer multiple-choice questions and was administered to ChatGPT-3.5. The 2024 version, containing 72 questions, was administered to ChatGPT-4o. The success rates of ChatGPT and the residents who participated in both exams were compared. ChatGPT's accuracy improved from 53.6% in 2023 to 84.7% in 2024. Among the 501 residents who participated in both years, the average score increased from 48.2% to 53.1%. ChatGPT ranked 292nd among residents in 2023 but achieved the top score in 2024. Based on percentage improvement in scores, ChatGPT-4o ranked 8th overall. The most notable performance gains for ChatGPT were seen in the areas of strabismus (+75%), neuro-ophthalmology (+40%), and optics (+40%). Among residents, the largest improvement occurred in oculoplastics (+33.5%), while a decrease was observed in cornea and ocular surface (-4.1%). ChatGPT-4o showed a marked improvement in answering ophthalmology questions compared to its predecessor, whereas resident learning progressed more gradually. This rapid advancement in ChatGPT highlights the potential speed with which artificial learning can progress within defined boundaries. In contrast, human learning remains a deeper and more time-intensive process. Results suggest that evolving large language models will play an increasingly significant role in medical education and clinical support.

This study aimed to evaluate the 48-month visual and anatomical outcomes, as well as the number of clinic visits and intravitreal injections, in patients treated with three consecutive loading doses of intravitreal anti-vascular endothelial growth factor (anti-VEGF) therapy for diabetic macular edema (DME) under real-world conditions in Türkiye. In this retrospective, multicenter study conducted by the BOSPHORUS-DME Study Group, the medical records of 2,424 eyes of 1,696 patients who experienced vision loss due to DME and were treated with intravitreal anti-VEGF injections between January 2019 and January 2023 were reviewed. The study was carried out across eight tertiary referral hospitals located on the European side of İstanbul and in the province of Kocaeli. Seven cohort groups were created based on follow-up at baseline and months 3, 6, 12, 18, 24, 36, and 48. Best-corrected visual acuity (BCVA), central macular thickness (CMT), the number of clinic visits and injections, and the rates of anti-VEGF or dexamethasone switching were analyzed. The study included a total of 2,424 eyes of 1,696 patients (mean age: 60.6±10.0 years; 46.4% female). The mean baseline BCVA and CMT were 0.34±0.24 (decimal) and 400±134 μm, respectively. At month 48, these values improved to 0.49±0.29 (p<0.0001) and 324±115 μm (p<0.0001). The mean cumulative number of injections at years 1, 2, 3, and 4 were 6.5, 9.6, 12.2, and 15.7, respectively. A switch in anti-VEGF therapy occurred between month 3 and 6 in 43.5% of eyes, mostly due to mandatory transition to on-label agents. This is the largest and longest real-world study on DME treatment conducted in Türkiye. It demonstrates that visual and anatomical gains can be sustained over a 48-month period. While the overall trend aligns with previous real-world studies, the higher injection frequency in our cohort appears to have contributed to more favorable outcomes. These findings underscore the importance of early intensive therapy and sustained treatment adherence in the real-world management of DME.

Keratoprosthesis (KPro) implantation serves as a last resort for visual rehabilitation in patients with end-stage bilateral corneal blindness, particularly when conventional corneal transplantation is no longer viable. Advances in biomaterials and refinements in prosthetic design have significantly enhanced anatomical retention and visual outcomes. Among the various types available, the Boston type 1 and 2 devices and the modified osteo-odonto-KPro remain the most widely utilized globally. This review aims to support comprehensive clinical decision-making by providing an in-depth overview of the design characteristics, surgical considerations, and postoperative care protocols associated with the most widely used KPro devices. In addition, we discuss a broad range of influencing factors, including the status of the ocular surface, eyelid anatomy, tear film adequacy, underlying systemic or autoimmune diseases, and patient-related logistical and socioeconomic concerns. Special emphasis is placed on the importance of preoperative evaluation and counselling and the role of a multidisciplinary approach in achieving successful long-term outcomes. Drawing on current evidence and clinical experience, we propose a practical decision-making algorithm to aid ophthalmologists in selecting the most appropriate KPro tailored to individual patient profiles.

To evaluate the response and interpretative capabilities of two pioneering artificial intelligence (AI)-based large language model (LLM) platforms in addressing ophthalmology-related multiple-choice questions (MCQs) from Turkish Medical Specialty Exams. MCQs from a total of 37 exams held between 2006-2024 were reviewed. Ophthalmology-related questions were identified and categorized into sections. The selected questions were asked to the ChatGPT-4o and Gemini 1.5 Pro AI-based LLM chatbots in both Turkish and English with specific prompts, then re-asked without any interaction. In the final step, feedback for incorrect responses were generated and all questions were posed a third time. A total of 220 ophthalmology-related questions out of 7312 MCQs were evaluated using both AI-based LLMs. A mean of 6.47±2.91 (range: 2-13) MCQs was taken from each of the 33 parts (32 full exams and the pooled 10% of exams shared between 2022 and 2024). After the final step, ChatGPT-4o achieved higher accuracy in both Turkish (97.3%) and English (97.7%) compared to Gemini 1.5 Pro (94.1% and 93.2%, respectively), with a statistically significant difference in English (p=0.039) but not in Turkish (p=0.159). There was no statistically significant difference in either the inter-AI comparison of sections or interlingual comparison. While both AI platforms demonstrated robust performance in addressing ophthalmology-related MCQs, ChatGPT-4o was slightly superior. These models have the potential to enhance ophthalmological medical education, not only by accurately selecting the answers to MCQs but also by providing detailed explanations.

To evaluate the effectiveness of conventional therapy and 20% autologous platelet-rich plasma (aPRP) eye drops for moderate to severe dry eye disease (DED). In this prospective interventional study, 40 individuals (80 eyes) with moderate to severe DED were analyzed. Twenty patients each were randomly assigned to the study and control groups. The study group was given 20% aPRP eye drops; the control group was given artificial tears as per conventional treatment. Comprehensive eye examinations including evaluation of best corrected visual acuity (BCVA), tear meniscus height, tear break-up time (TBUT), Schirmer's test, corneal fluorescein staining, conjunctival impression cytology, and Ocular Surface Disease Index (OSDI) were conducted in both groups for 3 months. Pre- and posttreatment results were compared. The average age of patients in the study group was 51±14 years (range, 37-65 years), whereas that of the control group was 50±17 years (range, 33-67 years). After 3 months, there was a more significant decrease in OSDI score in the study group than in the control group (p<0.01). The BCVA data demonstrated no statistically significant difference (p>0.05). Measurements of tear meniscus height, Schirmer's value, and TBUT at 3 months showed statistically significant differences (p<0.01). The posttreatment improvements in fluorescein staining and impression cytology scores in the study group were markedly superior to those in the control group (p<0.01). aPRP is both safe and more effective than conventional treatments for moderate to severe symptomatic DED.