Artificial intelligence (AI) is becoming increasingly influential in ophthalmology, particularly through advancements in machine learning, deep learning, robotics, neural networks, and natural language processing (NLP). Among these, NLP-based chatbots are the most readily accessible and are driven by AI-based large language models (LLMs). These chatbots have facilitated new research avenues and have gained traction in both clinical and surgical applications in ophthalmology. They are also increasingly being utilized in studies on ophthalmology-related exams, particularly those containing multiple-choice questions (MCQs). This narrative review evaluates both the opportunities and the challenges of integrating chatbots into ophthalmology research, with separate assessments of studies involving open- and close-ended questions. While chatbots have demonstrated sufficient accuracy in handling MCQ-based studies, supporting their use in education, additional exam security measures are necessary. The research on open-ended question responses suggests that AI-based LLM chatbots could be applied across nearly all areas of ophthalmology. They have shown promise for addressing patient inquiries, offering medical advice, patient education, supporting triage, facilitating diagnosis and differential diagnosis, and aiding in surgical planning. However, the ethical implications, confidentiality concerns, physician liability, and issues surrounding patient privacy remain pressing challenges. Although AI has demonstrated significant promise in clinical patient care, it is currently most effective as a supportive tool rather than as a replacement for human physicians.

To compare the thicknesses of the retinal layers in smokers with those of nonsmoking healthy subjects using spectral-domain optical coherence tomography (SD-OCT). One hundred and eight subjects were included in the study. Two groups were separated as smokers and nonsmokers. Both groups were chosen to be similar in terms of age and gender. SD-OCT images were generated with Spectralis OCT (Heidelberg Engineering, Heidelberg, Germany). An automated algorithm was developed to segment the macular retina into eight layers and quantitate the thickness of each layer for the fovea, parafovea and perifovea. The mean smoking history was 18.33 ± 8.45 years (range: 10-40). The mean number of pack-years was 22.22 ± 15.51 (range: 10-80). No significant difference was observed regarding retinal layer measurements between the smoker and nonsmoker groups. Also, no significant difference was observed for central macular thicknesses at 1000, 3000, and 6000 μm between two groups. The thickness of retinal layers in healthy smokers was similar to those of healthy individuals.

Purpose: To determine the levels of serum oxidative, antioxidative markers and inflammatory cytokines in patients diagnosed with diabetic macular edema (DME) whose hyperreflective spots (HRS) were detected by optical coherence tomography (OCT). Methods: In this prospective cross-sectional clinical study included a total of 88 patients; 31 patients (group-1) with DME and HRS detected by OCT, 29 patients (group-2) with DME without HRS, and 28 patients (group-3) diagnosed with diabetes mellitus (DM) without any diabetic retinopathy findings. The main outcomes were best-corrected visual acuity (BCVA), CMT (central macular thickness), CMV (central macular volume), TMV (total macular volume), CT (choroidal thickness), serum TAS (total antioxidant status), TOS (total oxidant status), VEGF (vascular endothelial growth factor), FGF (fibroblast growth factor) and IL-1b levels. OCT parameters and biochemical measurements were compared statistically between the three groups. Results: A total of 88 patients (43 females (48.9%) and 45 males (51.1%)) were included in the study. The mean age was 56.29 ± 9.23 years. There was no difference between the three groups in age-and-sex. In group-1 and 2, BCVA(LogMAR) was statistically higher than group 3. CMT, CMV, TMV, TAS, TOS, VEGF and FGF were significantly higher in group-1 than in group-3. CMT, CMV, TMV, VEGF and FGF were significantly higher in group-2 than group 3. TOS and VEGF were significantly higher in group-1 than group-2. Conclusions: This study demonstrates that in patients with DME and HRS, TOS and VEGF levels were higher than those without HRS. Hence, hyperreflective spots may be an inflammatory biomarker.