Translational Vision Science & Technology最新文献

{"title":"Machine Learning and Metabolomics to Characterize Warburg-Like Metabolic Subtypes in Human Retinal Endothelial Cells Exposed to Risk Factors Associated With Proliferative Diabetic Retinopathy.","authors":"Oase Sbei, Shaimaa Eltanani, Sara Ibrahim, Thangal Yumnamcha, Sangly P Srinivas, Ahmed S Ibrahim","doi":"10.1167/tvst.15.8.26","DOIUrl":"10.1167/tvst.15.8.26","url":null,"abstract":"<p><strong>Purpose: </strong>High glucose (HG), hypoxia (Hyp), and their combination are major risk factors for proliferative diabetic retinopathy (PDR). Although these conditions induce features of the Warburg-like metabolic reprogramming in human retinal endothelial cells (HRECs), it remains unclear whether they produce distinct metabolic and angiogenic subtypes. This study aimed to characterize the Warburg-like-associated metabolic heterogeneity induced by these PDR-related risk factors and evaluate the ability of supervised machine-learning models to distinguish these subtypes.</p><p><strong>Methods: </strong>HRECs were cultured under normoglycemic, HG, Hyp (2% O2), and combined HG-Hyp conditions. Untargeted LC-MS/MS metabolomics quantified metabolites spanning carbohydrates, amino acids, nucleotides, and lipids. Principal component analysis (PCA) assessed overall metabolic variation, and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis identified metabolic pathways associated with angiogenesis. In vitro angiogenesis assays measured endothelial tube formation and branching. Nine supervised classifiers (decision tree, logistic regression, naïve Bayes, random forest, K-Nearest Neighbors, neural network, gradient boosting, AdaBoost, and Support Vector Machine) were trained on the highest-ranked metabolites selected by the Information Gain Ratio feature-ranking approach. Model performance was evaluated using 10-fold cross-validation, leave-one-out cross-validation (LOOCV), permutation testing, and a classifier stability analysis under biologically meaningful distributional shift using an independent chemically induced hypoxia model (CoCl2).</p><p><strong>Results: </strong>PCA revealed partial separation of metabolic profiles across conditions, indicating different Warburg-like metabolic subtypes. The combined HG-Hyp condition exhibited enhanced angiogenic potential relative to either HG or Hyp alone. KEGG pathway enrichment analysis identified fatty acid biosynthesis and elongation among the most significantly enriched pathways in HRECs under combined HG-Hyp conditions, alongside amino sugar and nucleotide sugar metabolism, glycerophospholipid metabolism, the pentose phosphate pathway, and glycolysis/gluconeogenesis. Supervised machine-learning classifiers distinguished these metabolic subtypes, with AdaBoost and gradient Boosting showing the most balanced, reproducible performance across 10-fold cross-validation, LOOCV, and permutation testing, and remaining the most reliable classifiers under domain-shift testing (area under the curve = 0.88, P = 0.0061).</p><p><strong>Conclusions: </strong>In this exploratory analysis, HG, Hyp, and their combination drive metabolically and functionally distinct subtypes of Warburg-like metabolic reprogramming in HRECs, with HG-Hyp in combination producing a highly angiogenic phenotype. Boosting-based ensemble classifiers provide a promising framework for detecting these subtypes even ","PeriodicalId":23322,"journal":{"name":"Translational Vision Science & Technology","volume":"15 8","pages":"26"},"PeriodicalIF":2.7,"publicationDate":"2026-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13533292/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148819749","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Use of a Retinal Phantom to Facilitate Adaptive Optics Scanning Light Ophthalmoscopy Imaging in a Multicenter Clinical Trial.","authors":"Joseph Kreis, Jessica Wong, Yushan Yang, Palash Bharadwaj, Robert F Cooper, Mina Gaffney, Nivedhitha Govindasamy, Amy L Green, Brian P Higgins, Yu You Jiang, Angelos Kalitzeos, Michel Michaelides, Jessica I W Morgan, Jason Porter, Jeremy D Rogers, Ian Rosenthal, Ramkumar Sabesan, Kaitlyn A Sapoznik, Alexander W Schill, Ryan D Sochol, Yiyi Wang, Raymond L Warner, Emma Warr, Benjamin J Wendel, Niamh Wynne, Peiluo Xu, Sergey Tarima, Daniel X Hammer, Anant Agrawal, Jacque L Duncan, Joseph Carroll","doi":"10.1167/tvst.15.8.20","DOIUrl":"10.1167/tvst.15.8.20","url":null,"abstract":"<p><strong>Purpose: </strong>To describe the use of a model eye-mounted retinal phantom to support adaptive optics scanning light ophthalmoscope (AOSLO) imaging in a multicenter clinical trial (NCT05537220).</p><p><strong>Methods: </strong>Six three-dimensional-printed retinal phantoms were mounted in model eyes. These phantoms contain equally spaced arrays of reflective \"cone-like\" structures mimicking foveal cone photoreceptor spacing. Intrasession repeatability of phantom imaging was assessed for all six phantoms on two custom AOSLOs. One phantom was also imaged on two additional AOSLOs to assess interdevice reproducibility. Lastly, each of the six phantoms was imaged longitudinally at their respective trial sites.</p><p><strong>Results: </strong>Intrasession repeatability of phantom-derived horizontal \"cone\" spacing measures was high for two different AOSLOs. However, intersystem differences were found in the average horizontal \"cone\" spacing of five of eight patches assessed. Across four unique AOSLOs, intersystem differences were found in the average horizontal \"cone\" spacing of seven of eight patches assessed. A linear regression analysis of longitudinal phantom imaging with a single AOSLO revealed few significant changes in horizontal \"cone\" spacing over the course of about 2 years. Similar results were observed for vertical \"cone\" spacing measures across the three experiments.</p><p><strong>Conclusions: </strong>Longitudinal spacing measurements were generally stable in our study. However, small but significant differences in spacing were observed between systems. The approach described here may facilitate combining cone metrics extracted from images acquired using different AOSLOs in multicenter studies.</p><p><strong>Translational relevance: </strong>Cross-system validation strategies can support the use of AOSLO imaging in multicenter clinical trials.</p>","PeriodicalId":23322,"journal":{"name":"Translational Vision Science & Technology","volume":"15 8","pages":"20"},"PeriodicalIF":2.7,"publicationDate":"2026-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13543627/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148809083","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing Diagnostic Precision in Fuchs Dystrophy: Comparative Evaluation of REVO HR and FC130 OCT Systems.","authors":"Dominika Szkodny, Adam Wylegala, Patrycja Potrawa, Edward Wylegala","doi":"10.1167/tvst.15.8.1","DOIUrl":"10.1167/tvst.15.8.1","url":null,"abstract":"<p><strong>Purpose: </strong>To compare the diagnostic performance of two anterior segment optical coherence tomography devices, REVO FC130 and REVO HR, in patients with Fuchs endothelial corneal dystrophy (FECD).</p><p><strong>Methods: </strong>This prospective cross-sectional study included 33 patients with FECD. Each patient was imaged with both devices. Eleven corneal features were graded independently by two evaluators. A third grader resolved disagreements. Agreement between graders and between devices was quantified by calculating the proportion of concordant assessments, including agreement for both detected and non-detected features, with corresponding 95% confidence intervals.</p><p><strong>Results: </strong>REVO HR provided better visualization of key corneal structures, including Descemet's membrane, Bowman's layer, and hyperreflective basal changes. Hyperreflective basal features were detected 11 times more often with REVO HR. Bowman's layer was identified 2.06 times more frequently with REVO HR compared to REVO FC130. Interoperator agreement was high for REVO HR (PropOverall ≥ 0.97 in 10 of 11 features). FC130 showed lower and more variable agreement, especially in low-contrast regions. Interdevice comparisons indicated systematic differences in detection capability.</p><p><strong>Conclusions: </strong>REVO HR showed higher sensitivity and reproducibility in detecting corneal microstructural changes in FECD. Improved image resolution allows better identification of subtle abnormalities, which may support more accurate disease staging and better timing of surgical intervention. For follow-up, the same OCT device should be used consistently.</p><p><strong>Translational relevance: </strong>This study demonstrates that improved OCT resolution enhances detection of corneal microstructural abnormalities in Fuchs endothelial corneal dystrophy, improving diagnostic precision, disease staging, and clinical decision-making in routine clinical practice.</p>","PeriodicalId":23322,"journal":{"name":"Translational Vision Science & Technology","volume":"15 8","pages":"1"},"PeriodicalIF":2.7,"publicationDate":"2026-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13440641/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148664465","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Functional and Structural Characterization of a Large Animal Model of RDH5-Associated Retinopathy.","authors":"Laura M Ford, Laurence M Occelli, Mary E Enfield, Nastassia A Benjamin, Kelian Sun, Nate Pasmanter, Simon M Petersen-Jones","doi":"10.1167/tvst.15.8.2","DOIUrl":"10.1167/tvst.15.8.2","url":null,"abstract":"<p><strong>Purpose: </strong>Inherited retinal diseases are a group of hereditary diseases that cause variable levels of blindness and affect a multitude of adults and children. One such disease is fundus albipunctatus (FA). FA is caused by autosomal recessive retinol dehydrogenase 5 (RDH5) mutations and results in rod dysfunction leading to night blindness and, in a subset of patients, macular degeneration (MD). We previously reported a spontaneous feline model of FA due to an RDH5 missense mutation. The affected cats showed rod dysfunction and a proportion developed degeneration of the area centralis (AC), equivalent to MD in humans.</p><p><strong>Methods: </strong>We used fundus confocal scanning laser ophthalmoscopy and spectral-domain optical coherence tomography imaging, six different electroretinography protocols, immunohistochemistry, and histology/transmission electron microscopy to further characterize this large-animal cat model.</p><p><strong>Results: </strong>In addition to rod dysfunction, cone recovery from intense stimulation was impaired. For RDH5-/- cats that developed AC degeneration, an initial elongation of rod outer segments with disorganization of the distal tips was initially detected in the AC and visual streak, suggestive of impaired shedding/phagocytosis. With progression, photoreceptors degenerated in the AC, matching the MD seen in some human patients.</p><p><strong>Conclusions: </strong>The RDH5-/- cat model recapitulates features of both rod and cone dysfunction seen in human patients with RDH5 mutations.</p><p><strong>Translational relevance: </strong>The RDH5-/- cat model offers a unique opportunity to further understand the mechanisms of RDH5-associated retinopathies and to investigate potential therapeutic approaches.</p>","PeriodicalId":23322,"journal":{"name":"Translational Vision Science & Technology","volume":"15 8","pages":"2"},"PeriodicalIF":2.7,"publicationDate":"2026-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13450645/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148674085","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Retinal Layer Changes With Aging and Cognitive Decline in Rhesus Macaques.","authors":"Yin Allison Liu, Mrinal Prabhakar, Emma McIntyre, Tzu-Ni Sin, Carol Villafuerte-Trisolini, Erin Kinnally, Lesly C Ceniceros, Ashlee M Cruz, Ashley D Cunningham, Hong Li, Kevin Choy, Sina Farsiu, Sara M Thomasy, Glenn Yiu","doi":"10.1167/tvst.15.8.14","DOIUrl":"https://doi.org/10.1167/tvst.15.8.14","url":null,"abstract":"<p><strong>Purpose: </strong>Nonhuman primates (NHPs) are powerful animal models of aging and neurodegeneration. We hypothesize that age-related retinal thinning measured by optical coherence tomography (OCT) may correlate with cognitive and behavioral decline. Here, we evaluate the relationship between neurocognitive function in rhesus macaques and retinal layer thickness on OCT.</p><p><strong>Methods: </strong>We evaluated 110 older rhesus macaques (mean age, 19.5 ± 3.3 years; range, 11-30 years) with an array of behavioral assessments, including visual acuity, decision-making, working memory, spatial memory, problem-solving, and social learning. We collected spectral domain OCT scans and measured retinal layer thicknesses in macular and peripapillary areas using custom segmentation software. Multivariate linear regression with generalized estimating equations was used to assess the association between retinal layer thicknesses and cognitive function.</p><p><strong>Results: </strong>OCT measurements of retinal layers were consistent with published data from humans and NHPs. Thinning of the macular nerve fiber layer (mNFL; P = 0.001) and photoreceptor segments (PSs; P = 0.014) were associated with slower decision-making, whereas thinner inner nuclear layer (INL) was linked to slower problem-solving and less problem-solving flexibility (P = 0.023). Thinner outer plexiform layer (OPL; P = 0.022) and PSs (P = 0.001) were associated with better visual prediction, and thinning of the mNFL (P = 0.038), OPL (P = 0.039), total retinal thickness (P = 0.015), and peripapillary NFL (P = 0.002) were associated with better social learning.</p><p><strong>Conclusions: </strong>Older rhesus macaques demonstrated measurable changes in behavior and retinal anatomy, but the relationship between retinal thinning and cognitive performance was modest, suggesting a unique relationship between retinal thinning and executive function, or a reflection of age-related decline and compensatory mechanisms.</p><p><strong>Translational relevance: </strong>Identifying noninvasive measures of age-related cognitive and behavioral decline using OCT measurements of retinal anatomy in NHPs may help accelerate future preclinical testing of novel treatments for neurodegenerative diseases in these animal models.</p>","PeriodicalId":23322,"journal":{"name":"Translational Vision Science & Technology","volume":"15 8","pages":"14"},"PeriodicalIF":2.7,"publicationDate":"2026-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13496269/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148798303","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prediction of Maximum Keratometry Progression With Stratified Progression Criteria in Keratoconus Patients Using Machine Learning.","authors":"Andreas Schlatter, Leon Pomberger, Andreas Honeder, Johannes Zeilinger, Ahmed Hamdoun, Nino Hirnschall, Martin Kronschläger, Oliver Findl","doi":"10.1167/tvst.15.8.27","DOIUrl":"10.1167/tvst.15.8.27","url":null,"abstract":"<p><strong>Purpose: </strong>The aim of this study was to use machine learning to predict 12-months progression of maximum keratometry (Kmax) within stratified repeatability limits based on a baseline topography/optical coherence tomography measurement in patients with keratoconus (KC).</p><p><strong>Methods: </strong>This study included patients with diagnosed KC in which baseline and follow-up measurements were performed with a Placido disc topographer combined with optical coherence tomography (OCT) at a time interval of at least 7 months. Eyes were classified as \"progressive\" or \"stable\" based on the repeatability-adjusted difference in Kmax between the baseline measurement and a follow-up measurement. Nested cross-validation was used to train different algorithms, and the algorithm with the best area under the curve (AUC) value was used as final model.</p><p><strong>Results: </strong>A total of 102 eyes of 65 patients were included. Mean age was 33.2 ± 13.0 years. Predictors with high outer fold stability included specific KC markers such as the CSIB index and posterior K values. Within the internal folds, the model achieved an AUC of 0.82, a sensitivity of 62.2%, and a specificity of 83.2% and, in the outer left-out folds, a sensitivity of 65.6%, a specificity of 84.3%, and thus an accuracy of 78.4%.</p><p><strong>Conclusions: </strong>Progression of Kmax can be predicted with decent accuracy using a single OCT-based topographic measurement. Nested cross-validation represents a valuable tool in small datasets.</p><p><strong>Translational relevance: </strong>Machine learning-based prediction of Kmax progression may aid in scheduling risk-adapted follow-up appointments, potentially leading to more rapid identification of progression-suspect KC cases.</p>","PeriodicalId":23322,"journal":{"name":"Translational Vision Science & Technology","volume":"15 8","pages":"27"},"PeriodicalIF":2.7,"publicationDate":"2026-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13533299/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148832713","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Quantitative Ciliary Body Imaging Using Image-Registered Swept-Source AS-OCT and Ultrasound Biomicroscopy.","authors":"Michie Namba, Anna Heur, Lucas L Humayun, Alexander Ko, Galo Apolo, Alex S Huang, Qifa Zhou, Benjamin Y Xu","doi":"10.1167/tvst.15.8.4","DOIUrl":"10.1167/tvst.15.8.4","url":null,"abstract":"<p><strong>Purpose: </strong>The purpose of this study was to evaluate inter- and intra-device agreement of ciliary body (CB) biometric parameters measured by image-registered swept-source anterior segment optical coherence tomography (AS-OCT; ANTERION, Heidelberg Engineering, Heidelberg, Germany) and ultrasound biomicroscopy (UBM; Insight 100, ArcScan).</p><p><strong>Methods: </strong>Patients undergoing anterior segment imaging were prospectively enrolled. Horizontal scans were acquired under standardized illumination. One eye per participant was randomly selected for analysis. Maximum ciliary muscle thickness (CMTMAX), maximum CB thickness (CBTMAX), sulcus-to-sulcus (STS) distance, and scleral spur-to-scleral spur (SSS) distance were manually measured. Eyes with pupillary diameter differences ≥15% were excluded. Inter- and intra-device agreement were assessed using intraclass correlation coefficients (ICCs), linear regression, and Bland-Altman analysis.</p><p><strong>Results: </strong>Seventy-eight eyes from 78 subjects (mean age = 61.9 ± 12.6 years) were analyzed. Inter-device agreement was good to excellent (ICC = 0.60-0.85). Mean absolute inter-device differences were 57.6 ± 36.6 µm for CBTMAX, 40.6 ± 44.7 µm for CMTMAX, 0.28 ± 0.23 mm for SSS, and 0.18 ± 0.16 mm for STS; corresponding mean absolute relative inter-device differences were 4.8% for CBTMAX, 5.9% for CMTMAX, 1.5% for SSS, and 2.5% for STS. Greater baseline CBTMAX was the only factor consistently associated with inter-device differences in CBTMAX or CMTMAX (P < 0.001). Intra-device repeatability was excellent across all parameters for both systems (ICC = 0.78-0.90 for ANTERION and 0.80-0.94 for Insight).</p><p><strong>Conclusions: </strong>Image-registered AS-OCT and UBM provided largely concordant and highly repeatable CB measurements, although systematic inter-device differences across the two modalities suggest they cannot be considered fully interchangeable.</p><p><strong>Translational relevance: </strong>Modern image-registered swept-source AS-OCT provides a viable, non-contact alternative to UBM for quantitative CB assessment.</p>","PeriodicalId":23322,"journal":{"name":"Translational Vision Science & Technology","volume":"15 8","pages":"4"},"PeriodicalIF":2.7,"publicationDate":"2026-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13456063/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148685934","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Topology-Aware Extension of Guttae Area Ratio in Fuchs Endothelial Corneal Dystrophy.","authors":"Molly Orlick, Henry Bair","doi":"10.1167/tvst.15.8.11","DOIUrl":"https://doi.org/10.1167/tvst.15.8.11","url":null,"abstract":"","PeriodicalId":23322,"journal":{"name":"Translational Vision Science & Technology","volume":"15 8","pages":"11"},"PeriodicalIF":2.7,"publicationDate":"2026-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13496271/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148798317","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Large Pigment Epithelial Detachments Associated With Type 1 Macular Neovascularization: Do Swept-Source OCT Angiography Devices Detect the Same Thing?","authors":"Kamal El Majdoubi El Idrissi, Marco R Pastore, Carl-Joe Mehanna, Alexandra Miere, Eric H Souied","doi":"10.1167/tvst.15.8.25","DOIUrl":"10.1167/tvst.15.8.25","url":null,"abstract":"<p><strong>Purpose: </strong>Large pigment epithelial detachments (PEDs) compromise automated swept-source optical coherence tomography angiography (SS-OCTA) segmentation, leading to false-negative type 1 macular neovascularization (MNV) in neovascular age-related macular degeneration. We compared the diagnostic sensitivity of two SS-OCTA platforms from different generations to assess whether technological advances offset segmentation limitations.</p><p><strong>Methods: </strong>This was a prospective comparative study of 82 eyes with type 1 MNV and PED height ≥ 250 µm. Each eye underwent dual SS-OCTA imaging with a first-generation 1050-nm (100-kHz) system and a next-generation 1060-nm (400-kHz) system. Two masked readers evaluated automated versus manually adjusted segmentation slabs across PED height categories.</p><p><strong>Results: </strong>On the 1050-nm system, detection improved from 22.0% with automated segmentation to 81.7% after manual adjustment (P < 0.001). The 1060-nm system showed higher automated detection (68.3%), with a modest increase to 75.6% after manual segmentation. Stratified analysis showed superior automated performance of the 1060-nm device in shallow PEDs, whereas intermediate PEDs were most challenging for both systems. In very large PEDs, manual segmentation yielded similar detection rates on both devices.</p><p><strong>Conclusions: </strong>Detection of type 1 MNV beneath large PEDs is significantly device dependent. Although next-generation SS-OCTA systems improve automated detection, manual segmentation remains crucial for optimal sensitivity and accuracy. Device-specific protocols integrating routine manual review are warranted to avoid false-negative findings and treatment delays.</p><p><strong>Translational relevance: </strong>Manual segmentation remains essential to prevent false-negative detection of type 1 MNV beneath large PEDs, even with next-generation SS-OCTA devices. This has direct implications for diagnostic protocols and treatment decisions in nAMD.</p>","PeriodicalId":23322,"journal":{"name":"Translational Vision Science & Technology","volume":"15 8","pages":"25"},"PeriodicalIF":2.7,"publicationDate":"2026-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13533301/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148819697","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting Vision-Threatening Retinopathy in Patients With Diabetes Using Patient-Reported Data: Impact on Reading Center Workflow Efficiency.","authors":"Mohamed Ashraf, Amira Mostafa, Bassma Al-Bayoumy, Enas Khamis, Heba Abdelaziz, Merna Mostafa, Mostafa El Manhaly, Mohamed Ghoneim, Nadine Khaled, Ahmed Souka, Paolo Silva, Lloyd Paul Aiello","doi":"10.1167/tvst.15.8.15","DOIUrl":"https://doi.org/10.1167/tvst.15.8.15","url":null,"abstract":"<p><strong>Purpose: </strong>First-come, first-served (FCFS) image review may delay identification of patients with vision-threatening diabetic retinopathy (VTDR). We developed a machine learning triage model using patient-reported clinical data to predict VTDR and evaluated its potential effect on reading-center workflow.</p><p><strong>Methods: </strong>We developed an ensemble model using XGBoost, CatBoost, and LightGBM in 9403 patients with diabetes imaged at the Alexandria iCare Retina Reading Center. Analyses were performed at the patient level using a worse-eye definition, with VTDR defined as severe nonproliferative DR or worse or diabetic macular edema. Predictors included demographic variables, comorbidities, smoking status, diabetes therapy, and hemoglobin A1c (HbA1c) when available. Model performance was evaluated with and without HbA1c. After model development, workflow simulations compared standard FCFS review with model-based prioritization and model plus prior-treatment prioritization.</p><p><strong>Results: </strong>The ensemble model achieved an area under the receiver operating characteristic curve of 0.89 with HbA1c and 0.87 without. With HbA1c, sensitivity was 74.8%, specificity was 88.6%, positive predictive value was 80.3%, and negative predictive value was 85.0%. In the 6-month workflow simulation, the mean time to evaluation for confirmed VTDR decreased from 57.08 ± 18.11 minutes with FCFS review to 48.86 ± 16.02 minutes with model-only prioritization and 43.01 ± 15.89 minutes with model plus prior-treatment prioritization.</p><p><strong>Conclusions: </strong>A patient-reported machine learning triage model identified patients at higher risk of VTDR and improved prioritization in simulated reading-center workflows.</p><p><strong>Translational relevance: </strong>Patient-reported triage may help reading centers to prioritize high-risk patients while preserving human grading.</p>","PeriodicalId":23322,"journal":{"name":"Translational Vision Science & Technology","volume":"15 8","pages":"15"},"PeriodicalIF":2.7,"publicationDate":"2026-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13496268/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148798300","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}