Frontiers in ophthalmology最新文献

{"title":"Performance evaluation of mainstream large language models in cataract science popularization Q&A: a comparative study of readability, quality, and educational suitability.","authors":"Yunqing Hou, Mingyue Liu, Zhuowei Wang, Xiaohui Jiang","doi":"10.3389/fopht.2026.1943376","DOIUrl":"10.3389/fopht.2026.1943376","url":null,"abstract":"<p><strong>Background: </strong>Cataract is one of the main causes of visual impairment and reversible blindness worldwide, and it mainly affects the elderly population. Clinically accurate and sufficiently readable patient education materials play a crucial role in this regard. With the rapid development of large language models (LLMs), patients are increasingly obtaining health information generated by artificial intelligence (AI); however, the reliability of online medical information is often questionable. This study systematically evaluated the readability, quality, and educational suitability of mainstream LLMs when answering questions related to cataract.</p><p><strong>Methods: </strong>Five mainstream LLMs - Doubao, DeepSeek, Wenxin Yiyan, Tongyi Qianwen, and GPT-5 - were evaluated based on their responses to 20 frequently asked questions (FAQs) for cataract patient, which covered five subject categories. Text readability was assessed through multiple indicators, including the Coleman-Liau Index (CL), Linsear Write (LW), Automated Readability Index (ARI), Simple Measure of Gobbledygook (SMOG), Gunning Fog Index (GFOG), Flesch Reading Ease Score (FRES), and Flesch-Kincaid Grade Level (FKGL). Information quality and educational suitability were evaluated using the Global Quality Score (GQS) and the Chinese version of the Patient Education Material Readability Assessment Tool (c-PEMAT-P). Differences between groups were compared using one-way ANOVA and Kruskal-Wallis tests, with correlation analyses exploring relationships among indicators.</p><p><strong>Results: </strong>There were significant differences among LLMs in terms of readability, information quality, and educational suitability (all p < 0.05). GPT-5 had the highest c-PEMAT-P and GQS scores, however, several readability difficulty indices of GPT-5 and Tongyi Qianwen were also higher. There were significant differences in readability among different content categories. The postoperative management and risk/prevention topics tended to have better educational suitability, whereas surgical diagnosis, treatment, and preoperative management were more difficult to read. Correlation analysis demonstrated that the correlation between the quality indicators and the readability-related indicators is generally weak.</p><p><strong>Conclusion: </strong>In terms of generating educational materials for cataract patient, LLMs have potential, but the output quality varies depending on the model and the topic. GPT-5 performs best in terms of overall quality and educational suitability, but its readability is not always at an ideal level. Model selection has a crucial impact on the quality and educational suitability of the information, while the content topic mainly affects the language complexity. Therefore, for the responsible use of LLMs in cataract patient education, the cataract education materials generated by LLMs need to undergo expert review, readability optimization, and patient-centered v","PeriodicalId":73096,"journal":{"name":"Frontiers in ophthalmology","volume":"6 ","pages":"1943376"},"PeriodicalIF":2.4,"publicationDate":"2026-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13645593/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149139742","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparative analysis of cataract surgery outcomes in elderly Jewish and Arab patients from Northern Israel, a retrospective cohort study.","authors":"Shadi Boqaaiya, Diana Nujedat, Yuval Cohen, Srour Ward, Emad Ghnem, Adi Sharabi Nov, Karine Beiruti Wiegler, Otzem Chassid","doi":"10.3389/fopht.2026.1942047","DOIUrl":"10.3389/fopht.2026.1942047","url":null,"abstract":"<p><strong>Purpose: </strong>To compare postoperative visual recovery and complications after cataract surgery between Jewish and Arab elderly patients in Northern Israel within a shared healthcare system.</p><p><strong>Methods: </strong>A retrospective study was conducted at Ziv Medical Center, Safed, Israel, involving 251 patients aged 60 years or older who underwent cataract surgery in 2023. All surgeries were performed under standardized departmental protocols, carried out by senior attending surgeons or supervised senior residents. Demographic characteristics, comorbidities, cataract type, postoperative complications and best-corrected visual acuity (BCVA) were extracted from electronic medical records. Visual outcomes were compared at baseline, day 1, and day 30 postoperatively. All statistical analyses were performed using IBM SPSS Statistics version 31, with continuous variables compared via Mann-Whitney U test and categorical variables via chi-square or Fisher's exact test, as appropriate.</p><p><strong>Results: </strong>Baseline age, sex, and preoperative visual acuity were similar between Jewish (n=153) and Arab (n=98) patients. Of the 153 Jewish patients, 77 (50.3%) were male and 76 (49.7%) were female. Of the 98 Arab patients, 49 (50.0%) were male and 49 (50.0%) were female (p = 0.960). Arab patients had higher rates of diabetes (54.1% vs. 35.9%, p=0.005) and hypertension (70.4% vs. 58.2%, p=0.050). Jewish patients demonstrated significantly better postoperative BCVA at 30 days (median LogMAR 0.5 vs. 0.7, p=0.0032). Complications were more common in the Arab cohort, particularly corneal edema (43.9% vs. 15.7%, p<0.001) and posterior capsule rupture (11.2% vs. 3.3%, p=0.012).</p><p><strong>Conclusion: </strong>Ethnic disparities were observed in short-term outcomes despite a uniform surgical environment within the same tertiary facility. These differences are more plausibly explained by structural, socioeconomic, and comorbidity-related determinants than by any biological difference associated with ethnicity per se. Further multicenter, prospective studies with longer follow-up are required to clarify the multifactorial causes of outcome variation and guide interventions to promote equity in cataract care.</p>","PeriodicalId":73096,"journal":{"name":"Frontiers in ophthalmology","volume":"6 ","pages":"1942047"},"PeriodicalIF":2.4,"publicationDate":"2026-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13645526/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149139691","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Contributions of aquatic organisms to understanding the vertebrate ocular lens.","authors":"Mason Posner","doi":"10.3389/fopht.2026.1900415","DOIUrl":"10.3389/fopht.2026.1900415","url":null,"abstract":"<p><p>Aquatic species have played a vital role over the past 200 years in detailing the structure, physiology, development, and evolution of the ocular lens. As a living piece of biological \"glass\", the lens must balance the optical demands of transparency and refractive power with the requirements of a metabolically active tissue. Lens researchers have leveraged unique aspects of aquatic species, such as 1) the lack of corneal refraction and the simplification of modeling aquatic lens optics, 2) the presence of external embryos for real-time observation of eye and lens development, and 3) the diversity of habitats, ecology, and genetics that support comparative studies. Discoveries across many areas of aquatic lens research contribute to understanding human blindness, tissue aging and regeneration, optical and protein design, and fundamental features of cell biology relevant to many tissues. This review highlights key contributions in these areas and points to possible future areas of discovery.</p>","PeriodicalId":73096,"journal":{"name":"Frontiers in ophthalmology","volume":"6 ","pages":"1900415"},"PeriodicalIF":2.4,"publicationDate":"2026-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13643694/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149139744","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Impact of surgical complexity and surgeon experience on phacoemulsification outcomes: a one-year retrospective study from a Saudi tertiary eye hospital.","authors":"Rafah Fairaq, Sarah Mohammed Almuwarraee, Sarah Ayedh Almatrafi, Wejdan Saeed Alghamdi, Lojain Mohammed Maawadh, Rajiv Khandekar, Mohammed Almutlak, Anwar Ahmed, Muhammad Ali Ahad, Halah Bin Helayel","doi":"10.3389/fopht.2026.1882657","DOIUrl":"10.3389/fopht.2026.1882657","url":null,"abstract":"<p><strong>Introduction: </strong>This study aimed to assess one-year outcomes of phacoemulsification cataract surgery at King Khaled Eye Specialist Hospital (KKESH), a tertiary referral teaching hospital in Saudi Arabia. Evaluated outcomes included intraoperative complications, postoperative visual outcomes, and the association of surgeon experience and surgical complexity with posterior capsule rupture (PCR) and visual outcomes.</p><p><strong>Methods: </strong>A retrospective review included 3,377 eyes that underwent phacoemulsification cataract surgery between January 1 and December 31, 2019. Data were extracted from TrakCare, the hospital's electronic medical record system. Variables included demographics, pre- and postoperative visual acuity, intraoperative complications, combined surgical procedures, and surgeon experience. Statistical analyses were performed using Stata version 16.1. Comparisons between surgeon groups were performed using analysis of variance and chi-square tests. Multivariable logistic regression was used to identify factors associated with PCR, and multivariable linear regression was performed to evaluate predictors of postoperative visual acuity. Statistical significance was defined as P < 0.05.</p><p><strong>Results: </strong>A total of 3,377 phacoemulsification cataract surgeries were included. The mean patient age was 62.7 ± 13.1 years, 50.8% were male, and diabetes was present in 14.0% of patients. The overall posterior capsule rupture (PCR) rate was 2.8%. Although attending surgeons managed patients with poorer preoperative visual acuity and performed a greater proportion of combined procedures, surgeon level was not independently associated with PCR after adjustment for patient and surgical factors. Combined surgery was independently associated with a higher likelihood of PCR (adjusted OR 2.44, 95% CI 1.41-4.25; P = 0.002). Postoperative visual acuity improved significantly overall, while poorer postoperative visual acuity was independently associated with combined surgery, diabetes, and worse preoperative visual acuity, but not with PCR after multivariable adjustment.</p><p><strong>Conclusion: </strong>Phacoemulsification cataract surgery at a tertiary referral eye center achieved low complication rates and favorable visual outcomes, consistent with international benchmarks. After adjustment for baseline characteristics, surgical complexity rather than surgeon experience was independently associated with PCR and postoperative visual outcomes. These findings support structured case allocation in teaching hospitals and provide valuable benchmarks for surgical training and quality improvement.</p>","PeriodicalId":73096,"journal":{"name":"Frontiers in ophthalmology","volume":"6 ","pages":"1882657"},"PeriodicalIF":2.4,"publicationDate":"2026-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13638422/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Routine baseline clinical data do not reliably predict poor first-year myopia control with low-dose atropine: a machine-learning benchmarking study.","authors":"Karenna Mehta, Robert A Clark","doi":"10.3389/fopht.2026.1930814","DOIUrl":"10.3389/fopht.2026.1930814","url":null,"abstract":"<p><strong>Purpose: </strong>The aim of this study was to determine whether routinely recorded baseline clinical factors, alone or combined with machine-learning predictive modeling, can provide individual risk stratification for myopia control by identifying children who will progress more than 0.25 diopters (D) during their first year of low-dose atropine treatment.</p><p><strong>Methods: </strong>From a 555-child source cohort treated initially with atropine 0.01% or 0.02%, 468 children had qualifying 9- to 15-month follow-up; 427 children started atropine monotherapy without a baseline optical adjunct. A child was classified as poorly responsive if either treated eye progressed more than 0.25 D of spherical equivalent refraction from baseline to the qualifying visit. This threshold was a practical clinical refraction boundary and was tested in sensitivity analyses using a 0.50-D threshold, annualized progression, and an annualized >0.50 D/year threshold. A prevalence reference, age-plus-refraction logistic regression, elastic-net regression, gradient boosting, and an exploratory multilayer-perceptron neural network were compared by repeated cross-validation.</p><p><strong>Results: </strong>Of 427 children, 159 (37%) were poorly responsive. Discrimination was poor and machine learning provided no improvement: the area under the curve (AUC) was 0.60 for logistic regression and 0.57 for gradient boosting [difference -0.03; 95% confidence interval (CI) -0.06 to 0.01]. Age alone performed similarly (AUC 0.60). No threshold was clinically useful; a high-sensitivity rule flagged 85% of children to identify 88% of poor responders, with positive predictive value 0.39.</p><p><strong>Conclusions: </strong>Routinely recorded baseline factors did not provide clinically useful individual-level prediction of the first-year progression category. With this predictor set, observing early on-treatment progression remains the practical way to identify children who may need escalation.</p>","PeriodicalId":73096,"journal":{"name":"Frontiers in ophthalmology","volume":"6 ","pages":"1930814"},"PeriodicalIF":2.4,"publicationDate":"2026-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13638604/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119365","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Accuracy, readability, and bias of GPT-4o mini responses to oculoplastic patient questions.","authors":"Terry Henry, Grace Staes, Alexius Russell, Nikisha Q Richards-Walker","doi":"10.3389/fopht.2026.1718017","DOIUrl":"https://doi.org/10.3389/fopht.2026.1718017","url":null,"abstract":"<p><strong>Purpose: </strong>This cross-sectional evaluation of model outputs evaluates the accuracy, readability, transparency, objectivity, completeness, and bias of GPT-4o mini responses to common oculoplastic patient questions.</p><p><strong>Methods: </strong>The study was reviewed and deemed exempt from institutional review board approval. Thirty-three questions were developed across eight clinical domains: floppy eyelid syndrome, cicatricial ectropion, entropion, blepharoplasty, facial aging, brow lift, ptosis, and facial nerve function. Seven domains contained four patient-centered questions, while the facial aging domain contained five questions, for a total of 33 questions. On September 16, 2024, GPT-4o mini was prompted for each question with a standardized prompt requesting responses from the perspective of an expert oculofacial surgeon, using the latest medical guidelines. Verbatim responses were recorded. Six American Society of Ophthalmic Plastic and Reconstructive Surgery fellowship-trained surgeons independently evaluated each response using a 5-point Likert scale assessing clinical accuracy, completeness, transparency, objectivity, and bias. Readability was assessed using established readability indices.</p><p><strong>Results: </strong>GPT-4o mini demonstrated moderate clinical accuracy and completeness. Clinical accuracy was rated favorably in 51% of ratings (101/198), while completeness was rated favorably in 42% (84/198). Transparency and objectivity demonstrated stronger performance. 78% of ratings (155/198) agreed or strongly agreed that responses were transparent and 76% of ratings (150/198) agreed or strongly agreed that responses were objective. 8% of ratings (16/198) agreed or strongly agreed that Bias was present, while 65% (129/198) disagreed or strongly disagreed. Readability analyses demonstrated that ratings required college- to graduate-level reading ability.</p><p><strong>Conclusion: </strong>GPT-4o mini generated transparent and objective ratings with low measured bias but demonstrated limitations in clinical accuracy, completeness, and readability. These findings apply specifically to GPT-4o mini and should not be generalized to other large language models. Future investigations should compare contemporary language models, evaluate alternative prompting strategies, and investigate multimodal systems that integrate text, clinical photographs, periocular anatomy, and patient symptoms.</p>","PeriodicalId":73096,"journal":{"name":"Frontiers in ophthalmology","volume":"6 ","pages":"1718017"},"PeriodicalIF":2.4,"publicationDate":"2026-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13626896/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119301","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Emerging mechanisms in dry eye disease: apoptosis-associated tear MicroRNAs and toxicant-related alterations of the glycocalyx and lipid rafts.","authors":"Mazyar Yazdani","doi":"10.3389/fopht.2026.1924390","DOIUrl":"https://doi.org/10.3389/fopht.2026.1924390","url":null,"abstract":"<p><strong>Background: </strong>Dry eye disease (DED), a multifactorial condition of the ocular surface, is marked by disruption of tear film homeostasis that can result in ocular discomfort, visual impairment, and potential epithelial damage. Its high prevalence and impact on quality of life and healthcare utilization underscore the need to better understand its underlying mechanisms. Although current research has clarified several key contributors, including tear film instability, ocular surface inflammation, and neural dysfunction, the complex pathophysiology of DED remains only partly understood. Moreover, new mechanistic insights are needed to advance diagnostic and therapeutic approaches.</p><p><strong>Hypothesis: </strong>This article highlights three emerging and underexplored mechanisms that may contribute to DED, based on a combination of disease-associated observations, indirect evidence, and mechanistic inference: (i) apoptosis-related tear microRNAs (miRNAs) as potential regulators of epithelial damage, (ii) ocular surface glycocalyx alterations potentially associated with environmental pollutants, and (iii) lipid raft disruption as a plausible mediator of toxicant-induced responses in ocular surface cells.</p><p><strong>Supporting evidence: </strong>First, apoptosis-related miRNAs in tears, traditionally viewed as potential biomarkers of the disease, are discussed as candidate regulators of epithelial damage through modulation of apoptotic pathways, although direct evidence in DED causation/development remains limited. Second, glycocalyx alterations potentially associated with environmental pollutants, such as airborne nanoparticles and reactive volatile compounds, are considered. This consideration draws in part on findings from non-ocular and non-DED systems. Third, lipid raft disruption is presented as a plausible but as yet untested mechanism in the context of the ocular surface and DED, potentially linking toxicant exposure to downstream cellular responses.</p><p><strong>Conclusion: </strong>By distinguishing between established knowledge, disease-associated findings, and forward-looking hypotheses, this work aims to broaden current perspectives on DED pathophysiology and suggest novel directions for future research.</p>","PeriodicalId":73096,"journal":{"name":"Frontiers in ophthalmology","volume":"6 ","pages":"1924390"},"PeriodicalIF":2.4,"publicationDate":"2026-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13627036/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119406","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analysis of clinical factors affecting corneal endothelial cell density in eye bank donors.","authors":"Lan Yu, Wei Ming, Shangcao Wu, Qiaoqiao Dong, Jingwei Li, Jiao Qin, Qingyan Zeng","doi":"10.3389/fopht.2026.1952825","DOIUrl":"https://doi.org/10.3389/fopht.2026.1952825","url":null,"abstract":"<p><strong>Purpose: </strong>To systematically analyze factors influencing corneal endothelial cell density (ECD) in eye bank donors and provide robust evidence for optimizing donor screening strategies.</p><p><strong>Methods: </strong>A retrospective analysis was conducted on 1438 corneas from 782 donors (2013-2025). Associations between ECD and donor age, sex, laterality, cause and season of death, cataract surgery, cancer, Diabetes Mellitus (DM), and death-to-preservation time (DTP) were evaluated using univariate analysis and a generalized linear mixed model (GLMM).</p><p><strong>Results: </strong>Univariate analysis showed ECD was significantly associated with age, cataract surgery, DTP, cause of death, and death season (all <i>P</i> < 0.05). The GLMM indicated that age, cataract surgery, and DTP were highly significant independent predictors (all <i>P</i> < 0.001): ECD was 287.737 cells/mm² higher in donors without cataract surgery (95% CI: 177.109-398.365), and decreased by 3.847 cells/mm² (95% CI: -5.561 to -2.134) per year of age and 18.342 cells/mm² (95% CI: -27.623 to -9.062) per hour increase in preservation time. Among causes of death, only the cardiovascular/cerebrovascular disease group differed significantly from the chronic organ failure group (<i>P</i> = 0.013); other factors including sex, eye laterality, cancer, DM, and death season showed no independent effects (all <i>P</i>>0.05).</p><p><strong>Conclusion: </strong>Advanced age, prior cataract surgery, and prolonged death-to-preservation time were independently associated with lower ECD. Cause of death was not an independent predictor overall, although donors who died from CCVDs had significantly higher ECD than those with chronic organ failure. These findings provide a robust evidence base for clinical donor screening and allocation, thereby maximizing the utility of scarce donor corneas.</p>","PeriodicalId":73096,"journal":{"name":"Frontiers in ophthalmology","volume":"6 ","pages":"1952825"},"PeriodicalIF":2.4,"publicationDate":"2026-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13623622/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119245","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artificial intelligence in corneal endothelial disease and endothelial keratoplasty: current evidence, clinical readiness, and future directions.","authors":"Anđela Jukić, Kata Čulina, Vedran Markušić, Sanja Masnec, Suzana Matić, Miro Kalauz","doi":"10.3389/fopht.2026.1951354","DOIUrl":"10.3389/fopht.2026.1951354","url":null,"abstract":"<p><p>Corneal endothelial disease generates high-dimensional imaging and longitudinal data, making it well suited to artificial intelligence (AI). This review follows AI across the endothelial care pathway and judges each application by translational maturity rather than discrimination alone, drawing on a targeted PubMed/MEDLINE search of studies published between 2011 and July 2026. Technical performance is strongest when the task is measurement against a reproducible human reference: endothelial cell segmentation, image quality control, edema and pachymetric mapping, and quantification of Descemet membrane endothelial keratoplasty (DMEK) detachment. However, performance declines as tasks become prognostic or when models cross devices, surgeons, and centers. External validation reduced the area under the curve from 0.96 to 0.77 in one Fuchs endothelial corneal dystrophy (FECD) detection model, and a 2025 systematic review identified external validation in only three of 19 FECD studies. Calibration, uncertainty quantification, decision curve analysis, and prospective human-AI comparison remain uncommon. The most mature applications are therefore measurement and quality-control tasks, including automated donor endothelial cell density assessment in eye banking. FECD staging, prediction of decompensation after cataract surgery, the need for rebubbling (reinjection of air or gas into the anterior chamber to promote graft reattachment), rejection, and long-term graft survival remain investigational. By covering the full clinical pathway together with eye banking, regenerative therapies, foundation models, language models, an explicit clinical-readiness framework, and the European regulatory context, this review outlines the current requirements for clinical translation: multicenter external validation, transparent reporting, safe abstention, and prospective clinical impact studies.</p>","PeriodicalId":73096,"journal":{"name":"Frontiers in ophthalmology","volume":"6 ","pages":"1951354"},"PeriodicalIF":2.4,"publicationDate":"2026-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13620467/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149082925","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Editorial: Telemedicine in ophthalmology: cost-effectiveness and barriers to widespread adoption.","authors":"Ahmed M Sayed, Nasif Zaman, Padmaja Kumari Rani","doi":"10.3389/fopht.2026.1976103","DOIUrl":"https://doi.org/10.3389/fopht.2026.1976103","url":null,"abstract":"","PeriodicalId":73096,"journal":{"name":"Frontiers in ophthalmology","volume":"6 ","pages":"1976103"},"PeriodicalIF":2.4,"publicationDate":"2026-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13619488/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149082833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}