Ophthalmology. Glaucoma最新文献

{"title":"Leveraging natural language processing to assess follow-up patterns in glaucoma care.","authors":"Andrew M Williams, Hai-Wei Liang, Chenyu Li, Yanshan Wang","doi":"10.1016/j.ogla.2026.04.009","DOIUrl":"https://doi.org/10.1016/j.ogla.2026.04.009","url":null,"abstract":"<p><strong>Purpose: </strong>To develop a natural language processing (NLP) algorithm that identifies follow-up recommendations from the free text of clinical glaucoma clinic notes, and to determine the proportion of patients who lapse beyond recommended follow-up intervals.</p><p><strong>Design: </strong>Retrospective cohort study.</p><p><strong>Participants: </strong>Adult glaucoma patients treated from January 2016 through December 2022 at our academic ophthalmology practice.</p><p><strong>Methods: </strong>Structured demographic and diagnosis data were extracted alongside the free text of clinical notes. An NLP algorithm was developed to identify recommended follow-up intervals from note free text. Lapses in care were defined as absence of a return visit within 125% of the recommended follow-up interval. Generalized estimating equations with a Poisson distribution and log link were used to identify risk factors for lapsing in care. Results are reported as adjusted risk ratios (aRRs) with 95% confidence intervals (CIs).</p><p><strong>Main outcome measures: </strong>NLP algorithm performance and proportion of patients with an identified lapse in care.</p><p><strong>Results: </strong>In total, 221,378 clinical notes were assessed, representing 66,228 visits by 6452 unique glaucoma patients. The NLP algorithm identified a follow-up interval for 47,084 of 66,228 (71.1%) patient visits and demonstrated high performance compared to gold-standard chart review (F1 score 0.905, precision 0.948, recall 0.867). The proportion of visits that exceeded 125% of the preceding recommended follow-up interval was 20.0% [interquartile range (IQR): 10.0-33.3]. The median excess duration of the lapsed interval compared to recommended follow-up was 52.9 days (IQR: 22.0-111.5 days). The proportion of patients with any event of lapsing in follow-up was 73.7% (4754/6452). Risk factors for having at least one lapse in care included Black race (aRR=1.29, 95%CI: 1.22-1.37, compared to White race) and Hispanic ethnicity (aRR=1.53, 95%CI: 1.26-1.87), with lower risk for older age (aRR=0.91, 95%CI: 0.86-0.97, age 71-80 years compared to ≤60 years). Among the 4,754 patients with at least one lapse in care, 1,183 (24.9%) never returned after lapsing.</p><p><strong>Conclusions: </strong>NLP can reliably detect lapses in glaucoma care using individualized follow-up intervals. Identifying lapses in care may facilitate referrals to resources to mitigate risk of loss to follow-up.</p>","PeriodicalId":56368,"journal":{"name":"Ophthalmology. Glaucoma","volume":" ","pages":""},"PeriodicalIF":3.2,"publicationDate":"2026-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147857782","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluating The Need For Anti-Inflammatory Medication Post Laser Peripheral Iridotomy.","authors":"Ari Leshno, Eran Levanon, Reut Singer, Mordechai Goldenfeld, Hani Levkovitch-Verbin","doi":"10.1016/j.ogla.2026.04.007","DOIUrl":"https://doi.org/10.1016/j.ogla.2026.04.007","url":null,"abstract":"<p><strong>Purpose: </strong>To evaluate whether the administration of topical steroids is beneficial after elective laser peripheral iridotomy (LPI).</p><p><strong>Design: </strong>Prospective, randomized, double-masked, placebo-controlled clinical trial.</p><p><strong>Participants: </strong>Twenty-eight patients (56 eyes) with anatomical narrow angles and no other ocular diseases requiring bilateral LPI.</p><p><strong>Methods: </strong>Participants underwent LPI in both eyes one week apart. Following the first LPI, eyes were randomized to receive either topical steroid (prednisolone acetate 1%) or placebo eye drops (artificial tears) four times daily for four days. The fellow eye received the alternative treatment after the second LPI.</p><p><strong>Main outcome measures: </strong>Intraocular pressure (IOP), iridotomy patency, anterior segment inflammation, and symptoms assessed via the Ocular Surface Disease Index (OSDI) questionnaire.</p><p><strong>Results: </strong>Baseline characteristics and laser parameters were similar between arms. At 1 week, anterior chamber inflammation was absent in all control eyes and present in 2 steroid-treated eyes (7.4%); at 1 month, no eyes had inflammation. Iridotomy was not patent in 3 control eyes (10.7%) and 4 steroid eyes (14.3%) at 1 month (P > 0.99). OSDI scores were low and similar between arms at each visit. Mean IOP did not change significantly from baseline across visits (overall P = 0.603) and did not differ between arms (overall P = 0.243). In multivariable analyses, baseline IOP was the only variable independently associated with follow-up IOP at all time points; treatment assignment had no effect.</p><p><strong>Conclusions: </strong>Our study suggests no clear advantage to topical steroids after high-powered pulsed laser peripheral iridotomy. These findings should be confirmed in larger, multicenter studies.</p>","PeriodicalId":56368,"journal":{"name":"Ophthalmology. Glaucoma","volume":" ","pages":""},"PeriodicalIF":3.2,"publicationDate":"2026-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147846790","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A staged approach to the number and frequency of visual field testing for detecting glaucoma progression.","authors":"Jack Phu, Henrietta Wang, Michael Kalloniatis","doi":"10.1016/j.ogla.2026.04.006","DOIUrl":"https://doi.org/10.1016/j.ogla.2026.04.006","url":null,"abstract":"<p><strong>Purpose: </strong>To assess a staged visual field review model (initially intensive, then downtitrated) for detecting cases of glaucoma progression (especially catastrophic and fast), in comparison to clinical standard, fixed review approaches.</p><p><strong>Design: </strong>Computer simulation study.</p><p><strong>Subjects: </strong>100,000 subjects.</p><p><strong>Methods: </strong>100,000 subjects were simulated to undergo four VF tests in one \"eye\" per visit, 3 monthly, over 30 years. The staged visual field model consisted of an initial intensive review (e.g. three tests per eye per visit, 3 monthly) that was then downtitrated as 90% of progressors within a rate bin (e.g. catastrophic <-2 dB/year) was detected. The test number and review cadence were systematically downtitrated with 90% of successive progression rate bins detected until the end of the 30 year follow up. Comparator models were fixed reviews: one test 12 monthly, one test 6 monthly, two tests 6 monthly (\"frontloading\") and three tests 24 monthly (\"wait-and-see\"). To reduce false positives, an immediate subsequent confirmatory progression result was required for all conditions.</p><p><strong>Main outcome measures: </strong>Number of progressors detected and number of tests/visits required per case of progression detected.</p><p><strong>Results: </strong>All staged review approaches detected 90% of catastrophic (21-36 months) and fast (36-60 months) progression bins sooner compared to all fixed methods (catastrophic: 66-108 months; fast: 84-132 months) except fixed frontloading. Detection of 50% of all progressors was also achieved sooner for the staged approaches (21-36 months) compared to all fixed methods (60-96 months), except for fixed frontloading (36 months). When using one test 12 monthly as a reference standard, the staged approaches were 66%-251% more likely to detect progression. The two tests per visit at 3 monthly and 6 monthly staged intervals were the most efficient with the lowest number of visits (10.6 and 8.6 at 5 years) and tests (15.8 and 12.9 at 5 years) per case detected over time.</p><p><strong>Conclusions: </strong>A staged visual field review model starting with intensive testing (such as two tests per visit at 3 or 6 monthly intervals) with downtitration at 30-36 months may increase the likelihood of detecting progressors and may provide long-term efficiencies in case detection, in comparison to conventional fixed approaches.</p>","PeriodicalId":56368,"journal":{"name":"Ophthalmology. Glaucoma","volume":" ","pages":""},"PeriodicalIF":3.2,"publicationDate":"2026-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147846758","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Two-Year Outcomes of Visco Circumferential Suture Trabeculotomy vs Rigid Probe Hemi-Trabeculotomy in Late-Onset Primary Congenital Glaucoma.","authors":"Ahmed S Elwehidy, Mostafa A Elwehidy, Rasha M Elzeini, Mohammed Elashry, Ghada H Allam, Mostafa Damlakhi, Abdelrahman M Elhusseiny","doi":"10.1016/j.ogla.2026.04.008","DOIUrl":"https://doi.org/10.1016/j.ogla.2026.04.008","url":null,"abstract":"<p><strong>Objective: </strong>To compare the two-year outcomes of Visco Circumferential Suture Trabeculotomy (VCST) versus Rigid Probe Hemi-Trabeculotomy (RPHT) in late-onset primary congenital glaucoma (LPCG).</p><p><strong>Design: </strong>A retrospective cohort study.</p><p><strong>Subjects: </strong>LPCG patients who underwent VCST or RPHT.</p><p><strong>Methods: </strong>A retrospective chart review was conducted of LPCG patients who underwent VCST or RPHT between January 2014 and December 2023 and had a minimum of two years of postoperative follow-up.</p><p><strong>Main outcome measures: </strong>The primary outcome was surgical success, defined as complete success-intraocular pressure (IOP) ≤17 mmHg with ≥30% reduction from baseline, without glaucoma medications, and without anatomical evidence of glaucoma progression-or qualified success (meeting IOP criteria while requiring topical glaucoma medications [maximum of three agents]). The use of oral carbonic anhydrase inhibitors was considered a failure. Secondary outcomes included longitudinal changes in IOP, number of glaucoma medications, and complication rates.</p><p><strong>Results: </strong>A total of 79 eyes (79 patients) met the inclusion criteria (40 in the VCST group and 39 in the RPHT group in each group). Baseline demographics were comparable between the two groups (mean age of 3.2 ± 0.3 years in the VCST vs. 3.1 ± 0.2 years in the RPHT, p = 0.42 years). At 24-months postoperatively, the overall success (complete and qualified) rate was significantly higher with VCST (95.00%) than with RPHT (84.66%; p = 0.04). Both procedures led to significant reductions in IOP from baseline, but eyes in the VCST group consistently exhibited lower mean IOP over the 24-month follow-up, with differences reaching statistical significance from the sixth month onward (e.g., 13.1 ± 2.5 mmHg vs. 14.6 ± 3.4 mmHg at 6 months; p = 0.03). Transient hyphema was the most common complication that occurred in 66 of 79 eyes (83.5%) overall, more frequent in the VCST than in the RPHT group (relative risk: 1.24; 95% confidence interval: 1.01-1.53; p = 0.04).</p><p><strong>Conclusion: </strong>In this cohort, VCST achieved higher two-year surgical success rates and more sustained IOP reduction compared with RPHT.</p>","PeriodicalId":56368,"journal":{"name":"Ophthalmology. Glaucoma","volume":" ","pages":""},"PeriodicalIF":3.2,"publicationDate":"2026-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147846838","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Association Between Open-Angle Glaucoma Progression and Cardiovascular Risk Predicted by a Deep Learning-Based Fundus Imaging Model.","authors":"Jooyoung Yoon, Jaewon Seo, Dongjin Nam, Eun Hee Hong, Yong Un Shin, Min Ho Kang, Sunjin Hwang, Won June Lee","doi":"10.1016/j.ogla.2026.04.004","DOIUrl":"https://doi.org/10.1016/j.ogla.2026.04.004","url":null,"abstract":"<p><strong>Purpose: </strong>This study investigated the association between the RetiCAC score, a deep learning-derived estimate of systemic atherosclerotic burden from retinal photographs, and glaucomatous visual field (VF) progression.</p><p><strong>Design: </strong>A retrospective cohort study PARTICIPANTS: A total of 192 eyes from 192 patients diagnosed with open-angle glaucoma at Hanyang University Seoul and Guri Hospitals.</p><p><strong>Methods: </strong>RetiCAC scores were estimated from fundus photographs using a deep learning model, and patients were stratified into low-to-moderate vs high-risk groups using a cutoff of 41 based on the RetiCAC-derived 5-year cardiovascular disease risk classification. Generalized estimating equations (GEE) were applied to identify factors associated with VF progression. Progression-free survival was compared between risk groups using Kaplan-Meier analysis. Relationships between RetiCAC and VF change rates were examined using scatter plots with locally weighted scatterplot smoothing (LOWESS) curves.</p><p><strong>Main outcome measures: </strong>The primary outcome was the association between the RetiCAC score and glaucomatous VF progression.</p><p><strong>Results: </strong>Higher RetiCAC scores (P = 0.029), elevated peak intraocular pressure (IOP; P = 0.006), and the longer follow-up duration (P = 0.048) were independently associated with VF progression in the GEE model. Kaplan-Meier analysis demonstrated a significantly higher probability of VF progression in the high-risk group compared to that of the low-to-moderate risk group (P = 0.030). LOWESS analyses identified an inflection point consistent with accelerated VF deterioration at a RetiCAC score of 51.1.</p><p><strong>Conclusions: </strong>The RetiCAC score, derived from retinal photographs, showed a significant association with glaucoma progression, independent of traditional risk factors such as IOP. This noninvasive marker of systemic vascular health may be useful for predicting glaucoma progression and may reflect vascular dysfunction contributing to disease progression.</p>","PeriodicalId":56368,"journal":{"name":"Ophthalmology. Glaucoma","volume":" ","pages":""},"PeriodicalIF":3.2,"publicationDate":"2026-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147790443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Geographic Distribution and Drive Times to Glaucoma Specialists in the United States A National Geospatial Access Analysis and Drive-Time Study.","authors":"Joshua Wang, Jean Adomfeh, Agnes C Owete, Shivani Kamat, Mary Qiu, Kelly W Muir","doi":"10.1016/j.ogla.2026.04.005","DOIUrl":"https://doi.org/10.1016/j.ogla.2026.04.005","url":null,"abstract":"<p><strong>Background: </strong>Access to glaucoma specialists varies substantially across the United States, and geographic barriers may delay and limit care. Using publicly available spatial data, we estimated travel burden by calculating county-level drive times to the nearest practicing glaucoma specialist and summarized results at the state, U.S. Census region, and Rural-Urban Commuting Area (RUCA) core-type levels.</p><p><strong>Design: </strong>Cross-sectional geospatial analysis SUBJECTS: County-level geographic units in the contiguous United States.</p><p><strong>Methods: </strong>This analysis was conducted in Python 3.9.6 using U.S. Census Bureau county-level data and practice locations of glaucoma specialists obtained from the American Glaucoma Society (AGS), limited to those with provisional or active membership practicing in the United States. County geographic centroids were linked to the nearest specialist practice location across county and state boundaries Approximate drive times from county centroids to the closest specialist were computed, and state-, census region-, and Rural-Urban Commuting Area (RUCA)-level summaries were generated.</p><p><strong>Main outcome measures: </strong>Estimated drive time RESULTS: Across the contiguous 48 states, mean drive times to the nearest glaucoma specialist ranged from 0.04 hours in the District of Columbia to 3.77 hours in North Dakota, while median drive times ranged from 0.04-4.40 hours over the same jurisdictions. The proportion of counties with drive times below their state's mean also varied widely, from 2 percent in Delaware and Rhode Island to roughly 80 percent in Georgia, reflecting marked intrastate heterogeneity. Regional analyses showed the shortest median drive times in the Northeast (0.66 hours) and the longest in the West (1.85 hours), with the Midwest and South demonstrating intermediate medians of 1.38 hours and 1.23 hours, respectively. When stratified by RUCA core type, Metro core counties had the lowest median drive time (0.23 hours), whereas small town cores and rural counties experienced considerably longer medians (1.16 hours and 1.02, respectively).</p><p><strong>Conclusion: </strong>Access to glaucoma specialists shows striking geographic disparities. Northeastern and metropolitan counties benefit from relatively short travel times, whereas western and rural counties face substantially longer drives. These findings highlight the need for targeted outreach, teleophthalmology expansion, and workforce planning to reduce geographic barriers to glaucoma care.</p>","PeriodicalId":56368,"journal":{"name":"Ophthalmology. Glaucoma","volume":" ","pages":""},"PeriodicalIF":3.2,"publicationDate":"2026-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147790389","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Visual field testing on the Envision head-mounted perimeter with and without gaming elements.","authors":"Emmanouil Tsamis, Iván Marín-Franch, William H Swanson, Michael Chaglasian, Anne Rozwat, Brittney Brady, Donald C Hood, Nicholas Neissa, Ridwan Shabsigh, Lama A Al-Aswad","doi":"10.1016/j.ogla.2026.04.002","DOIUrl":"https://doi.org/10.1016/j.ogla.2026.04.002","url":null,"abstract":"<p><strong>Objective: </strong>To evaluate a new virtual reality (VR) head-mounted perimeter (Envision) with two test modes-a standard test (ENV) and a gaming-based test (ENVg)-by assessing their test-retest variability, comparing their results to the Humphrey Field Analyzer (HFA), and evaluating test duration and patient preferences.</p><p><strong>Study design: </strong>This was a two-part clinical trial. Part 1 involved data collection from the Envision and HFA from all participants. Part 2 was a test-retest variability study, where a subset of healthy participants (HCs) performed each Envision test twice.</p><p><strong>Participants: </strong>Thirty HCs and 30 glaucoma patients with varying disease severity.</p><p><strong>Methods: </strong>In Part 1, all 60 participants underwent visual field testing with the HFA, ENV, and ENVg tests. Patient preference surveys were also administered. In Part 2, HCs were retested with the ENV and ENVg to assess repeatability. Test-retest variability analysis was conducted on 19 HCs and 25 glaucoma participants who had reliable test results. Function-function and structure-function concordance were also evaluated in the glaucoma cohort, based on two approaches: 1) a clinician's evaluation and 2) a Reading Center approach.</p><p><strong>Main outcome measures: </strong>Key measures included: test-retest variability of pointwise Total Deviation (TD) and unweighted Mean Deviation (MD) values; comparison of TD/MD values between devices; test duration; concordance evaluation; and patient preference.</p><p><strong>Results: </strong>Both the ENV and ENVg tests demonstrated low test-retest variability (mean±SD TD: 0.05±3.58 dB, and 0.21±3.70 dB, respectively, in HCs; 0.15 ± 4.81 dB, ENV only, in glaucomas), comparable to the HFA. TD and MD values were similar between ENV, ENVg and HFA. The Envision tests had shorter and more consistent durations for patients with moderate and advanced glaucoma as compared to HFA. Function-function concordance was high, while both ENV and HFA had similar levels of structure-function agreement. Patient surveys indicated a strong preference for the ENVg test, which was perceived as more engaging and shorter in duration.</p><p><strong>Conclusions: </strong>The Envision VR perimeter shows high repeatability and is comparable to the HFA. The ENVg was strongly preferred by patients, suggesting a promising avenue for improving patient engagement and compliance. The system's portability and consistent test duration make it a viable alternative for visual field testing in various clinical and non-traditional settings.</p>","PeriodicalId":56368,"journal":{"name":"Ophthalmology. Glaucoma","volume":" ","pages":""},"PeriodicalIF":3.2,"publicationDate":"2026-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147719019","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting 10-2 Swedish Interactive Thresholding Algorithm Standard from 24-2C SITA Faster: Development and Validation of Deep24-2C.","authors":"Kei Sano, Euido Nishijima, Shunsuke Sumi, Yuka Igari, Gary C Lee, Aiko Iwase, Tadashi Nakano","doi":"10.1016/j.ogla.2026.04.001","DOIUrl":"10.1016/j.ogla.2026.04.001","url":null,"abstract":"<p><strong>Purpose: </strong>To develop and validate Deep24-2C, a machine learning (ML) model that reconstructs comprehensive Humphrey Field Analyzer (HFA) 10-2 visual field (VF) thresholds from HFA 24-2C.</p><p><strong>Design: </strong>A retrospective study.</p><p><strong>Participants: </strong>A total of 3653 HFA 24-2C tests, including 181 actual tests from 136 eyes of 130 patients with glaucoma or suspected glaucoma, and 3472 synthesized tests at the Jikei University School of Medicine were included. Thirty-five actual HFA 24-2C tests from 24 eyes of 21 patients at Tajimi Iwase Eye Clinic were used for pilot external validation.</p><p><strong>Methods: </strong>The HFA 24-2C testing grid incorporates 10 additional central test points into the conventional 24-2 pattern. Deep24-2C was trained to predict all 68 threshold values of the HFA 10-2 test using subsets of 24-2C points (22-26 within the 10° region) along with age. Three ML architectures-random forest (RF), XGBoost, and multilayer perceptron (MLP)-were developed, and their ensemble combination was evaluated. Model training and internal validation were conducted using the Jikei dataset, while external validation used the Tajimi dataset. Data augmentation was applied using synthesized 24-2C tests, which combined paired HFA 24-2 and 10-2 tests. Model performance was evaluated using mean absolute error (MAE).</p><p><strong>Main outcome measures: </strong>Mean absolute error for 10-2 point-wise thresholds and mean deviation.</p><p><strong>Results: </strong>We first trained and validated Deep24-2C using the Jikei dataset. Incorporating synthesized data improved predictive accuracy from MAE 2.52 ± 0.07 dB to 2.42 ± 0.07 dB. Furthermore, models utilizing additional central test points outperformed those based on conventional 24-2 points across all ML architectures (RF, XGBoost, and MLP); the best-performing XGBoost model achieved MAE 2.30 ± 0.01 dB for predicting 10-2 thresholds. Subsequently, we performed external validation on the Tajimi dataset using an ensemble model that combined all models utilizing 10 additional central test points; the ensemble model yielded MAE 1.81 (95% confidence interval [1.69-1.93]) dB.</p><p><strong>Conclusions: </strong>Deep24-2C enables reconstruction of 10-2 VF thresholds from a 24-2C Swedish Interactive Thresholding Algorithm Faster test. Incorporating additional central points enhances predictive performance compared with conventional 24-2 grids. Deep24-2C may serve as a practical and efficient tool for evaluating central VF defects, reducing testing burden, and supporting individualized glaucoma management.</p><p><strong>Financial disclosure(s): </strong>Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.</p>","PeriodicalId":56368,"journal":{"name":"Ophthalmology. Glaucoma","volume":" ","pages":""},"PeriodicalIF":3.2,"publicationDate":"2026-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147678779","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Trabeculectomy Remains Essential for Glaucoma Care.","authors":"Kuldev Singh, Tin Aung, Fotis Topouzis, Remo Susanna","doi":"10.1016/j.ogla.2026.03.001","DOIUrl":"https://doi.org/10.1016/j.ogla.2026.03.001","url":null,"abstract":"","PeriodicalId":56368,"journal":{"name":"Ophthalmology. Glaucoma","volume":" ","pages":""},"PeriodicalIF":3.2,"publicationDate":"2026-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147610522","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Double Trouble: Tamponade-Induced Secondary Glaucoma in a Colobomatous Eye.","authors":"Sagarika Snehi, Vandana Iyer, Anusua Kar","doi":"10.1016/j.ogla.2026.02.004","DOIUrl":"https://doi.org/10.1016/j.ogla.2026.02.004","url":null,"abstract":"","PeriodicalId":56368,"journal":{"name":"Ophthalmology. Glaucoma","volume":" ","pages":""},"PeriodicalIF":3.2,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147596512","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}