Intravitreal Antibiotics versus Early Vitrectomy plus Intravitreal Antibiotics for Post-Injection Endophthalmitis: an IRIS® Registry (Intelligent Research in Sight).

PURPOSE: To determine if intravitreal injection of antibiotics alone versus early pars plana vitrectomy (PPV) plus injection of intravitreal antibiotics predicted better or worse visual outcomes for patients with endophthalmitis after anti-vascular endothelial growth factor (anti-VEGF) injections. DESIGN: Retrospective cohort study PARTICIPANTS: Patients developing endophthalmitis after receiving an intravitreal anti-VEGF injection from the American Academy of Ophthalmology IRIS® Registry between 2016 and 2020. METHODS: Inclusion criteria were endophthalmitis diagnosis within 1 to 28 days after anti-VEGF injection and a recorded visual acuity (VA) at baseline, on the day of diagnosis, and post-treatment. Patients in the Injection Only group underwent intravitreal injection of antibiotics alone and in the Early Vitrectomy group received PPV with intravitreal antibiotics or intravitreal injection followed by PPV within 2 days of diagnosis. Patients were excluded if they had cataract surgery during the study, intravitreal steroids before endophthalmitis, or intermediate/posterior uveitis or cystoid macular edema. The study created a 1:1 matched cohort using Mahalanobis Distance Matching, accounting for the differences in VA at baseline and diagnosis. MAIN OUTCOME MEASURES: Post-treatment logMAR VA RESULTS: 1,044 patients diagnosed with post-injection endophthalmitis met the inclusion and exclusion criteria. In the unmatched cohort, there were 935 patients in the Injection Only and 109 in the Early Vitrectomy group. In 1:1 matched cohort 218 patients (109 in each group) were included; the median logMAR VAs were 0.32 [20/40-20/50] at baseline, 0.88 [∼20/150] at diagnosis, and 0.57 [20/70-20/80] post-treatment. There were no statistically significant differences in the visual outcomes between the two matched treatment groups (b = 0.05, p = 0.23); including the subgroup of patients with VA worse than 1.0 logMAR (b = 0.05, p = 0.452). CONCLUSIONS: There was no significant difference in final VA outcomes between patients receiving Injection Only and those treated with Early Vitrectomy for post-injection endophthalmitis. The findings support the use of either treatment strategy.

Transformer-Based Deep Learning Prediction of 10-Degree Humphrey Visual Field Tests From 24-Degree Data.

Purpose: To predict 10-2 Humphrey visual fields (VFs) from 24-2 VFs and associated non-total deviation features using deep learning. Methods: We included 5189 reliable 24-2 and 10-2 VF pairs from 2236 patients, and 28,409 reliable pairs of macular OCT scans and 24-2 VF from 19,527 eyes of 11,560 patients. We developed a transformer-based deep learning model using 52 total deviation values and nine VF test features to predict 68 10-2 total deviation values. The mean absolute error, root mean square error, and the R2 were evaluation metrics. We further evaluated whether the predicted 10-2 VFs can improve the structure-function relationship between macular thinning and paracentral VF loss in glaucoma. Results: The average mean absolute error and R2 for 68 10-2 VF test points were 3.30 ± 0.52 dB and 0.70 ± 0.11, respectively. The accuracy was lower in the inferior temporal region. The model placed greater emphasis on 24-2 VF points near the central fixation point when predicting the 10-2 VFs. The inclusion of nine VF test features improved the mean absolute error and R2 up to 0.17 ± 0.06 dB and 0.01 ± 0.01, respectively. Age was the most important 24-2 VF test parameter for 10-2 VF prediction. The predicted 10-2 VFs achieved an improved structure-function relationship between macular thinning and paracentral VF loss, with the R2 at the central 4, 12, and 16 locations of 24-2 VFs increased by 0.04, 0.05 and 0.05, respectively (P < 0.001). Conclusions: The 10-2 VFs may be predicted from 24-2 data. Translational Relevance: The predicted 10-2 VF has the potential to improve glaucoma diagnosis.

Impact of Demographics on Regional Visual Field Loss and Deterioration in Glaucoma.

Purpose: To elucidate the impact of demographics, including gender, race, ethnicity, and preferred language, on regional visual field (VF) loss and progression in glaucoma. Methods: Multivariable linear mixed regressions were performed to determine the impact of race, ethnicity, and preferred language on regional VF loss with adjustment for age and gender. Regional VF loss was defined by pointwise total deviation values and VF loss patterns quantified by an unsupervised machine learning method termed archetypal analysis. All cross-sectional and longitudinal analyses were performed both without and with adjustment for VF mean deviation, which represented overall VF loss severity. P values were corrected for multiple comparisons. Results: All results mentioned had corrected P values less than 0.05. Asian and Black patients showed worse pointwise VF loss than White patients with superior hemifield more affected. Patients with a preferred language other than English demonstrated worse pointwise VF loss than patients with English as their preferred language. Longitudinal analyses revealed Black patients showed worse VF loss/year compared to White patients. Patients with a preferred language other than English demonstrated worse VF loss/year compared to patients preferring English. Conclusions: Blacks and non-English speakers have more severe VF loss, with superior hemifield being more affected and faster VF worsening. Translational Relevance: This study furthered our understanding of racial, ethnic, and socioeconomic disparities in glaucoma outcomes. Understanding the VF loss burden in different racial, ethnic, and socioeconomic groups may guide more effective glaucoma screening and community outreach efforts. This research could help reduce vision loss and improve quality of life in disproportionately affected populations by guiding public health efforts to promote glaucoma awareness and access to care.

Complications After Pediatric Penetrating Keratoplasty: An IRIS Registry Study.

PURPOSE: To describe the frequency of postoperative complications in children undergoing penetrating keratoplasty (PK). METHODS: This retrospective cohort study included pediatric patients (aged 0-18 years) in the Intelligent Research in Sight (IRIS) Registry who underwent primary PK between January 2013 and December 2020. Patients were identified using Current Procedure Terminology codes. Postoperative complications were identified using International Classification of Diseases Revision 9 and 10 codes and categorized as complications affecting the anterior segment (epithelial defect, infectious keratitis, neurotrophic keratitis, and glaucoma) or posterior segment (vitreous hemorrhage, retinal detachment, choroid detachment, choroidal hemorrhage, endophthalmitis, epiretinal membrane, and proliferative vitreoretinopathy). RESULTS: Of the 544 pediatric patients undergoing PK, 259 (47.6%) experienced postoperative complications. Anterior segment complications (n = 222, 40.8%) were more common than posterior segment complications (n = 96, 17.6%). The most common anterior complication was infectious keratitis (n = 163, 30.0%) with a median onset time of 275 days (IQR 50-560 days) after surgery. Vitreous hemorrhage (n = 52, 9.6%) and retinal detachment (n = 48, 8.8%) were the most common posterior segment complications. CONCLUSIONS: Infectious keratitis was the most common postoperative complication in children undergoing PK. More complications occurred in the anterior segment (70%) of the eye as compared with the posterior segment (30%). These findings demonstrate the challenges associated with pediatric PK and may help guide postoperative monitoring and management.

Factors Associated with Missing Sociodemographic Data in the IRIS® (Intelligent Research in Sight) Registry.

Purpose: To describe the prevalence of missing sociodemographic data in the IRIS® (Intelligent Research in Sight) Registry and to identify practice-level characteristics associated with missing sociodemographic data. Design: Cross-sectional study. Participants: All patients with clinical encounters at practices participating in the IRIS Registry prior to December 31, 2020. Methods: We describe geographic and temporal trends in the prevalence of missing data for each sociodemographic variable (age, sex, race, ethnicity, geographic location, insurance type, and smoking status). Each practice contributing data to the registry was categorized based on the number of patients, number of physicians, geographic location, patient visit frequency, and patient population demographics. Main Outcome Measures: Multivariable linear regression was used to describe the association of practice-level characteristics with missing patient-level sociodemographic data. Results: This study included the electronic health records of 66 477 365 patients receiving care at 3306 practices participating in the IRIS Registry. The median number of patients per practice was 11 415 (interquartile range: 5849-24 148) and the median number of physicians per practice was 3 (interquartile range: 1-7). The prevalence of missing patient sociodemographic data were 0.1% for birth year, 0.4% for sex, 24.8% for race, 30.2% for ethnicity, 2.3% for 3-digit zip code, 14.8% for state, 5.5% for smoking status, and 17.0% for insurance type. The prevalence of missing data increased over time and varied at the state-level. Missing race data were associated with practices that had fewer visits per patient (P < 0.001), cared for a larger nonprivately insured patient population (P = 0.001), and were located in urban areas (P < 0.001). Frequent patient visits were associated with a lower prevalence of missing race (P < 0.001), ethnicity (P < 0.001), and insurance (P < 0.001), but a higher prevalence of missing smoking status (P < 0.001). Conclusions: There are geographic and temporal trends in missing race, ethnicity, and insurance type data in the IRIS Registry. Several practice-level characteristics, including practice size, geographic location, and patient population, are associated with missing sociodemographic data. While the prevalence and patterns of missing data may change in future versions of the IRIS registry, there will remain a need to develop standardized approaches for minimizing potential sources of bias and ensure reproducibility across research studies. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Classifying and quantifying changes in papilloedema using machine learning.

Background: Machine learning (ML) can differentiate papilloedema from normal optic discs using fundus photos. Currently, papilloedema severity is assessed using the descriptive, ordinal Frisén scale. We hypothesise that ML can quantify papilloedema and detect a treatment effect on papilloedema due to idiopathic intracranial hypertension. Methods: We trained a convolutional neural network to assign a Frisén grade to fundus photos taken from the Idiopathic Intracranial Hypertension Treatment Trial (IIHTT). We applied modified subject-based fivefold cross-validation to grade 2979 longitudinal images from 158 participants' study eyes (ie, the eye with the worst mean deviation) in the IIHTT. Compared with the human expert-determined grades, we hypothesise that ML-estimated grades can also demonstrate differential changes over time in the IIHTT study eyes between the treatment (acetazolamide (ACZ) plus diet) and placebo (diet only) groups. Findings: The average ML-determined grade correlated strongly with the reference standard (r=0.76, p<0.001; mean absolute error=0.54). At the presentation, treatment groups had similar expert-determined and ML-determined Frisén grades. The average ML-determined grade for the ACZ group (1.7, 95% CI 1.5 to 1.8) was significantly lower (p=0.0003) than for the placebo group (2.3, 95% CI 2.0 to 2.5) at the 6-month trial outcome. Interpretation: Supervised ML of fundus photos quantified the degree of papilloedema and changes over time reflecting the effects of ACZ. Given the increasing availability of fundus photography, neurologists will be able to use ML to quantify papilloedema on a continuous scale that incorporates the features of the Frisén grade to monitor interventions.

Corneal Opacity in the United States: An American Academy of Ophthalmology IRIS® Registry (Intelligent Research in Sight) Study.

PURPOSE: This study assesses the case frequencies, underlying causes, and vision outcomes in patients with a diagnosis of corneal opacity in the United States. DESIGN: Retrospective cohort study. PARTICIPANTS: Patients in the IRIS® Registry (Intelligent Research in Sight) who received a diagnosis of corneal opacity between January 1, 2013, and November 30, 2020. METHODS: The IRIS Registry contains demographic and clinical data of 79 887 324 patients who sought treatment at eye clinics during the study period. We identified patients with corneal opacity using International Classification of Diseases (ICD), Ninth and Tenth Revisions, codes of 371 (corneal scar) and H17 (corneal opacity), respectively. The analyzed data comprised demographic parameters including age, sex, race, ethnicity, and geographical location. We evaluated clinical data including laterality, cause, disease descriptors, and best-corrected visual acuity (VA) up to 1 year before the onset (± 30 days), at the time of diagnosis, and at 1 year after diagnosis (± 30 days). MAIN OUTCOME MEASURES: Case frequencies, causes, and vision outcomes in patients with a diagnosis of corneal opacity. RESULTS: We identified 5 220 382 patients who received a diagnosis of corneal opacity and scars using H17 (ICD, Tenth Revision) and 371.0 (ICD, Ninth Revision) codes over 7 years. The case frequency of corneal opacity during the study period was 6535 cases per 100 000 patients (6.5%). The mean age of the patients was 63.36 ± 18.14 years, and most were female (57.6%). In the cohort, 38.39% and 30.00% of patients had bilateral and unilateral corneal opacity, respectively. Most of the patients affected by corneal opacity were White (69.13%), followed by Black or African American (6.84%). Corneal dystrophies (64.66%) were the most common cause of corneal opacity in the study cohort. Visual acuity of the patients worsened significantly because of corneal opacity (0.46 ± 0.74 logarithm of the minimum angle of resolution [logMAR]) and did not improve to the baseline (0.37 ± 0.68 logMAR) after management (0.43 ± 0.77 logMAR). The multiple linear regression analysis showed worse vision outcomes in female patients (compared with male patients), and Asian, Black or African American, and American Indian or Alaska Native (compared with White) patients. Additionally, worse vision outcomes were observed in patients with opacity associated with corneal malformation, degenerative disorders, edema, injury, and ulcer compared with those with hereditary corneal dystrophy. CONCLUSIONS: Our study showed that corneal opacity was diagnosed in 6.5% of patients in the IRIS Registry and primarily associated with corneal dystrophies. The final vision outcomes in patients with corneal opacity were significantly worse compared with baseline. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

The Association of Race, Ethnicity, and Insurance Status with the Visual Acuity of Retinoblastoma Survivors in the IRIS® Registry.

PURPOSE: To identify sociodemographic factors associated with the visual outcomes of retinoblastoma survivors. METHODS: Retrospective cohort study using a US-based clinical data registry. All individuals < 18 years of age with a history of retinoblastoma in the Intelligent Research in Sight (IRIS®) Registry (1/1/2013-12/31/2020). The primary outcome was visual acuity below the threshold for legal blindness (20/200 or worse) in at least one eye. Multivariable logistic regression was used to evaluate the association between visual outcomes and age, sex, laterality, race, ethnicity, type of insurance, and geographic location. RESULTS: This analysis included 1545 children with a history of retinoblastoma. The median length of follow-up was 4.1 years (IQR, 2.2-5.9 years) and the median age at most recent clinical visit was 12 years (IQR, 8-16 years). Retinoblastoma was unilateral in 54% of cases. Poor vision in at least one eye was identified in 78% of all children and poor vision in both eyes in 17% of those with bilateral disease. Poor visual outcomes were associated with unilateral diagnosis (OR, 1.55; 95% CI,1.13-2.12; p = .007), Black race (OR, 2.03; 95% CI, 1.19-3.47; p = .010), Hispanic ethnicity (OR, 1.65; 95% CI, 1.16-2.37; p = .006), and non-private insurance (OR, 1.47; 95% CI, 1.02-2.10; p = .037). CONCLUSIONS: Poor visual outcomes appear to be more common among Black, Hispanic, and publicly insured children with a history of retinoblastoma, raising concerns regarding healthcare inequities. Primary care physicians should ensure that young children receive red reflex testing during routine visits and consider retinoblastoma in the differential diagnosis of abnormal eye exams.

Glucose tolerance and insulin resistance/sensitivity associate with retinal layer characteristics: the LIFE-Adult-Study.

AIMS/HYPOTHESIS: As the prevalence of insulin resistance and glucose intolerance is increasing throughout the world, diabetes-induced eye diseases are a global health burden. We aim to identify distinct optical bands which are closely related to insulin and glucose metabolism, using non-invasive, high-resolution spectral domain optical coherence tomography (SD-OCT) in a large, population-based dataset. METHODS: The LIFE-Adult-Study randomly selected 10,000 participants from the population registry of Leipzig, Germany. Cross-sectional, standardised phenotyping included the assessment of various metabolic risk markers and ocular imaging, such as SD-OCT-derived thicknesses of ten optical bands of the retina. Global and Early Treatment Diabetic Retinopathy Study (ETDRS) subfield-specific optical retinal layer thicknesses were investigated in 7384 healthy eyes of 7384 participants from the LIFE-Adult-Study stratified by normal glucose tolerance, prediabetes (impaired fasting glucose and/or impaired glucose tolerance and/or HbA1c 5.7-6.4% [39-47 mmol/mol]) and diabetes. The association of optical retinal band characteristics with different indices of glucose tolerance (e.g. fasting glucose, area under the glucose curve), insulin resistance (e.g. HOMA2-IR, triglyceride glucose index), or insulin sensitivity (e.g. estimated glucose disposal rate [eGDR], Stumvoll metabolic clearance rate) was determined using multivariable linear regression analyses for the individual markers adjusted for age, sex and refraction. Various sensitivity analyses were performed to validate the observed findings. RESULTS: In the study cohort, nine out of ten optical bands of the retina showed significant sex- and glucose tolerance-dependent differences in band thicknesses. Multivariable linear regression analyses revealed a significant, independent, and inverse association between markers of glucose intolerance and insulin resistance (e.g. HOMA2-IR) with the thickness of the optical bands representing the anatomical retinal outer nuclear layer (ONL, standardised ß=-0.096; p<0.001 for HOMA2-IR) and myoid zone (MZ; ß=-0.096; p<0.001 for HOMA2-IR) of the photoreceptors. Conversely, markers of insulin sensitivity (e.g. eGDR) positively and independently associated with ONL (ß=0.090; p<0.001 for eGDR) and MZ (ß=0.133; p<0.001 for eGDR) band thicknesses. These global associations were confirmed in ETDRS subfield-specific analyses. Sensitivity analyses further validated our findings when physical activity, neuroanatomical cell/tissue types and ETDRS subfield categories were investigated after stratifying the cohort by glucose homeostasis. CONCLUSIONS/INTERPRETATION: An impaired glucose homeostasis associates with a thinning of the optical bands of retinal ONL and photoreceptor MZ. Changes in ONL and MZ thicknesses might predict early metabolic retinal alterations in diabetes.

Polygenic Risk Scores for Glaucoma Onset in the Ocular Hypertension Treatment Study.

Importance: Primary open-angle glaucoma (POAG) is a highly heritable disease, with 127 identified risk loci to date. Polygenic risk score (PRS) may provide a clinically useful measure of aggregate genetic burden and improve patient risk stratification. Objective: To assess whether a PRS improves prediction of POAG onset in patients with ocular hypertension. Design, Setting, and Participants: This was a post hoc analysis of the Ocular Hypertension Treatment Study. Data were collected from 22 US sites with a mean (SD) follow-up of 14.0 (6.9) years. A total of 1636 participants were followed up from February 1994 to December 2008; 1077 participants were enrolled in an ancillary genetics study, of which 1009 met criteria for this analysis. PRS was calculated using summary statistics from the largest cross-ancestry POAG meta-analysis, with weights trained using 8 813 496 variants from 449 186 cross-ancestry participants in the UK Biobank. Data were analyzed from July 2022 to December 2023. Exposures: From February 1994 to June 2002, participants were randomized to either topical intraocular pressure-lowering medication or close observation. After June 2002, both groups received medication. Main Outcomes and Measures: Outcome measures were hazard ratios for POAG onset. Concordance index and time-dependent areas under the receiver operating characteristic curve were used to compare the predictive performance of multivariable Cox proportional hazards models. Results: Of 1009 included participants, 562 (55.7%) were female, and the mean (SD) age was 55.9 (9.3) years. The mean (SD) PRS was significantly higher for 350 POAG converters (0.24 [0.95]) compared with 659 nonconverters (-0.12 [1.00]) (P < .001). POAG risk increased 1.36% (95% CI, 1.08-1.64) with each higher PRS decile, with conversion ranging from 9.52% (95% CI, 7.09-11.95) in the lowest PRS decile to 21.81% (95% CI, 19.37-24.25) in the highest decile. Comparison of low-risk and high-risk PRS tertiles showed a 2.0-fold increase in 20-year POAG risk for participants of European and African ancestries. In the subgroup randomized to delayed treatment, each increase in PRS decile was associated with a 0.52-year (95% CI, 0.01-1.03) decrease in age at diagnosis (P = .047). No significant linear association between PRS and age at POAG diagnosis was present in the early treatment group. Prediction models significantly improved with the addition of PRS as a covariate (C index = 0.77) compared with the Ocular Hypertension Treatment Study baseline model (C index = 0.75) (P < .001). Each 1-SD higher PRS conferred a mean hazard ratio of 1.25 (95% CI, 1.13-1.44) for POAG onset. Conclusions and Relevance: Higher PRS was associated with increased risk for POAG in patients with ocular hypertension. The inclusion of a PRS improved the prediction of POAG onset. Trial Registration: ClinicalTrials.gov Identifier: NCT00000125.

Effectiveness of Angle-Based Minimally Invasive Glaucoma Surgery after Laser Trabeculoplasty: An Analysis of the IRIS® Registry (Intelligent Research in Sight).

OBJECTIVE: Angle-based minimally invasive glaucoma surgery (ab-MIGS) has grown substantially, although long-term efficacy is poorly understood. We analyze ab-MIGS effectiveness with and without preceding laser trabeculoplasty (LTP). DESIGN: Retrospective cohort study. SUBJECTS: Eyes undergoing ab-MIGS (Canaloplasty, Goniotomy, Trabectome, and iStent) with and without prior laser trabeculoplasty (< 2 years preceding MIGS) were identified in the IRIS® Registry (Intelligent Research in Sight) 2013 to 2018. METHODS: Propensity score matching (PSM) was undertaken to define the following 4 cohorts: (1) standalone ab-MIGS, no prior LTP vs. (2) standalone ab-MIGS, with prior LTP; and (3) ab-MIGS + phacoemulsification, no prior LTP vs. (4) ab-MIGS + phacoemulsification, with prior LTP. MAIN OUTCOME MEASURES: Failure was defined as subsequent glaucoma reoperation after ab-MIGS (either MIGS or traditional glaucoma surgery). Time-to-event outcome and incidence rates were calculated using survival analysis, and adjusted hazard ratios (aHRs) were generated using multivariate Cox proportional hazards models. Medication data were not available for analysis. RESULTS: A total of 164 965 unique MIGS procedures were performed, from 2013 to 2018. After PSM, we identified 954 eyes undergoing standalone ab-MIGS and 7522 undergoing ab-MIGS + phacoemulsification. For eyes undergoing standalone ab-MIGS, those with prior LTP (n = 477) were more likely to undergo reoperation vs. those without LTP (n = 477) at 6 and 12 months. In multivariable models, those with prior LTP were more likely to undergo reoperation over the 36-month period vs. those without prior LTP (aHR, 1.53; CI, 1.15-2.04; P = 0.004). For eyes undergoing ab-MIGS + phacoemulsification, those with prior LTP (n = 3761) were more likely to undergo reoperation vs. those without LTP (n = 3761) at 12, 24, and 36 months. In multivariable models, those with prior LTP were more likely to undergo reoperation over the 36-month period vs. those without prior LTP (aHR, 1.53 CI, 1.15-2.04; P = 0.004). CONCLUSIONS: Prior LTP may be associated with a higher chance of subsequent glaucoma surgery following ab-MIGS, either with or without concurrent phacoemulsification. These findings have important implications for understanding who may benefit most from ab-MIGS, and for guiding patient and surgeon treatment expectations. FINANCIAL DISCLOSURES: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Harvard Glaucoma Fairness: A Retinal Nerve Disease Dataset for Fairness Learning and Fair Identity Normalization.

Fairness (also known as equity interchangeably) in machine learning is important for societal well-being, but limited public datasets hinder its progress. Currently, no dedicated public medical datasets with imaging data for fairness learning are available, though underrepresented groups suffer from more health issues. To address this gap, we introduce Harvard Glaucoma Fairness (Harvard-GF), a retinal nerve disease dataset including 3,300 subjects with both 2D and 3D imaging data and balanced racial groups for glaucoma detection. Glaucoma is the leading cause of irreversible blindness globally with Blacks having doubled glaucoma prevalence than other races. We also propose a fair identity normalization (FIN) approach to equalize the feature importance between different identity groups. Our FIN approach is compared with various state-of-the-art fairness learning methods with superior performance in the racial, gender, and ethnicity fairness tasks with 2D and 3D imaging data, demonstrating the utilities of our dataset Harvard-GF for fairness learning. To facilitate fairness comparisons between different models, we propose an equity-scaled performance measure, which can be flexibly used to compare all kinds of performance metrics in the context of fairness. The dataset and code are publicly accessible via https://ophai.hms.harvard.edu/datasets/harvard-gf3300/.

RNFLT2Vec: Artifact-corrected representation learning for retinal nerve fiber layer thickness maps.

Optical coherence tomography imaging provides a crucial clinical measurement for diagnosing and monitoring glaucoma through the two-dimensional retinal nerve fiber layer (RNFL) thickness (RNFLT) map. Researchers have been increasingly using neural models to extract meaningful features from the RNFLT map, aiming to identify biomarkers for glaucoma and its progression. However, accurately representing the RNFLT map features relevant to glaucoma is challenging due to significant variations in retinal anatomy among individuals, which confound the pathological thinning of the RNFL. Moreover, the presence of artifacts in the RNFLT map, caused by segmentation errors in the context of degraded image quality and defective imaging procedures, further complicates the task. In this paper, we propose a general framework called RNFLT2Vec for unsupervised learning of vectorized feature representations from RNFLT maps. Our method includes an artifact correction component that learns to rectify RNFLT values at artifact locations, producing a representation reflecting the RNFLT map without artifacts. Additionally, we incorporate two regularization techniques to encourage discriminative representation learning. Firstly, we introduce a contrastive learning-based regularization to capture the similarities and dissimilarities between RNFLT maps. Secondly, we employ a consistency learning-based regularization to align pairwise distances of RNFLT maps with their corresponding thickness distributions. Through extensive experiments on a large-scale real-world dataset, we demonstrate the superiority of RNFLT2Vec in three different clinical tasks: RNFLT pattern discovery, glaucoma detection, and visual field prediction. Our results validate the effectiveness of our framework and its potential to contribute to a better understanding and diagnosis of glaucoma.

Racial Disparities in Glaucoma Vision Outcomes and Eye Care Utilization: An IRIS Registry Analysis.

PURPOSE: To evaluate racial disparities in vision outcomes and eye care utilization among glaucoma patients. DESIGN: Retrospective cohort study. METHODS: In this population-based IRIS Registry (Intelligent Research in Sight) study, we included patients with minimum one diagnosis code for glaucoma at least 6 months prior to January 1, 2015 and at least one eye exam, visual field (VF), optical coherence tomography (OCT), or eye-related inpatient or emergency department (ED) code in 2015. Multivariable logistic and negative binomial regression models were used to assess vision and utilization outcomes, respectively, across race and ethnicity from January 1, 2015 to January 1, 2020. Vision outcomes included cup-to-disc ratio (CDR) progression > 0.80, poor vision (visual acuity 20/200 or worse), low vision codes, and need for glaucoma filtering surgery. Utilization outcomes included outpatient eye exams, OCTs, VFs, inpatient/ED encounters, and lasers/surgeries. RESULTS: Among 996,297 patients, 73% were non-Hispanic White, 15% non-Hispanic Black, 9% Hispanic, 3% Asian/Pacific Islander, and 0.3% Native American/Alaska Native. Compared to White eyes, Black and Hispanic eyes had higher adjusted odds of CDR progression (odds ratio [OR] = 1.12, 95% confidence interval [CI] = 1.08-1.17; OR = 1.28, 95% CI = 1.22-1.34), poor vision (OR = 1.26, 95% CI = 1.22-1.29; OR = 1.26, 95% CI = 1.22-1.31), glaucoma filtering surgery (rate ratio (RR) = 1.47, 95% CI = 1.42-1.51; RR = 1.13, 95% CI = 1.09-1.18). Hispanic eyes also had increased odds of low vision diagnoses (Hispanic OR = 1.18, 95% CI = 1.07-1.30). Black and Hispanic patients were less likely to have eye exams (RR = 0.94, 95% CI = 0.94-0.95; RR = 0.99, 95% CI = 0.99-0.99) and OCTs (RR = 0.86, 95% CI = 0.85-0.86; RR = 0.97, 95% CI = 0.96-0.98), yet Black patients had higher odds of inpatient/ED encounters (RR = 1.64, 95% CI = 1.37-1.96) compared to White patients. Native American patients were more likely to have poor vision (OR = 1.17, 95% CI = 1.01-1.36) and less likely to have outpatient visits (RR = 0.89, 95% CI = 0.86-0.91), OCTs (RR = 0.85, 95% CI = 0.82-0.89), visual fields (RR = 0.91, 95% CI = 0.88-0.94) or lasers/surgeries (RR = 0.87, 95% CI = 0.79-0.96) compared to White patients. CONCLUSIONS: We found that significant disparities in US eye care exist with Black, Hispanic, and Native American patients having worse vision outcomes and less disease monitoring. Glaucoma may be undertreated in these racial and ethnic minority groups, increasing risk for glaucoma-related vision loss.

Fellow Eyes Conversion Rates in Patients With Unilateral Exudative Age-Related Macular Degeneration: An Academy IRIS® Registry Analysis.

BACKGROUND AND OBJECTIVE: This study aimed to examine conversion rates from non-exudative to exudative age-related macular degeneration (AMD) in the fellow eye of patients with unilateral exudative AMD using the Academy IRIS® Registry. PATIENTS AND METHODS: This study was a retrospective, cohort analysis from 2016 to 2019. Patient and disease characteristics including initial AMD stage were collected. Cox proportional-hazard (PH) and logistic regression modeling were performed. RESULTS: The risk of conversion was lower for men relative to women and for Asians and Blacks relative to Whites. Compared to never-smokers, active smokers were at increased risk of conversion, and compared to initially early non-exudative AMD eyes, intermediate and advanced non-exudative AMD eyes had higher rates of conversion. Compared to active choroidal neovascularization eyes, eyes with inactive choroidal neovascularization and inactive scars had lower rates of fellow eye conversion. CONCLUSIONS: In this cohort analysis of unilateral exudative AMD patients, women, Whites, and active smokers had higher rates of non-exudative to exudative AMD conversion in the fellow eye. [Ophthalmic Surg Lasers Imaging Retina 2024;55:220-226.].

Machine Learning-Derived Baseline Visual Field Patterns Predict Future Glaucoma Onset in the Ocular Hypertension Treatment Study.

Purpose: The Ocular Hypertension Treatment Study (OHTS) identified risk factors for primary open-angle glaucoma (POAG) in patients with ocular hypertension, including pattern standard deviation (PSD). Archetypal analysis, an unsupervised machine learning method, may offer a more interpretable approach to risk stratification by identifying patterns in baseline visual fields (VFs). Methods: There were 3272 eyes available in the OHTS. Archetypal analysis was applied using 24-2 baseline VFs, and model selection was performed with cross-validation. Decomposition coefficients for archetypes (ATs) were calculated. A penalized Cox proportional hazards model was implemented to select discriminative ATs. The AT model was compared to the OHTS model. Associations were identified between ATs with both POAG onset and VF progression, defined by mean deviation change per year. Results: We selected 8494 baseline VFs. Optimal AT count was 19. The highest prevalence ATs were AT9, AT11, and AT7. The AT-based prediction model had a C-index of 0.75 for POAG onset. Multivariable models demonstrated that a one-interquartile range increase in the AT5 (hazard ratio [HR] = 1.14; 95% confidence interval [CI], 1.04-1.25), AT8 (HR = 1.22; 95% CI, 1.09-1.37), AT15 (HR = 1.26; 95% CI, 1.12-1.41), and AT17 (HR = 1.17; 95% CI, 1.03-1.31) coefficients conferred increased risk of POAG onset. AT5, AT10, and AT14 were significantly associated with rapid VF progression. In a subgroup analysis by high-risk ATs (>95th percentile or <75th percentile coefficients), PSD lost significance as a predictor of POAG in the low-risk group. Conclusions: Baseline VFs, prior to detectable glaucomatous damage, contain occult patterns representing early changes that may increase the risk of POAG onset and VF progression in patients with ocular hypertension. The relationship between PSD and POAG is modified by the presence of high-risk patterns at baseline. An AT-based prediction model for POAG may provide more interpretable glaucoma-specific information in a clinical setting.

The Incidence of Strabismus After Upper and Lower Blepharoplasty in the United States.

PURPOSE: To compare the incidence of strabismus after upper and lower blepharoplasty in the United States. METHODS: Retrospective cohort study of adults (age ≥18 years) in the IRIS Registry (Intelligent Research in Sight) who underwent blepharoplasty between January 1, 2013 and December 31, 2020. The primary outcome was the Kaplan-Meier estimated cumulative incidence of strabismus diagnosis and surgery within 3 years of blepharoplasty. Multivariable Cox regression was used to determine the association of blepharoplasty type with strabismus diagnosis and surgery, adjusting for patient age, sex, and geographic region. RESULTS: Blepharoplasty was performed in 368,623 patients (median [interquartile range] age, 69 [63-75] years, and 69% female). Compared with those undergoing upper eyelid blepharoplasty, patients treated with lower eyelid blepharoplasty were slightly younger (median age, 66 vs. 69 years; p < 0.001) and more likely to be female (71% vs. 69%; p < 0.001). There was a greater 3-year incidence of strabismus diagnosis (2.0% vs. 1.5%; p < 0.001) and a greater 3-year incidence of strabismus surgery (0.15% vs. 0.06%; p = 0.003) for individuals undergoing lower vs. upper blepharoplasty. After adjusting for age, sex, and geographic region, lower blepharoplasty was associated with a higher 3-year risk of strabismus diagnosis (HR, 1.49; 95% CI, 1.23-1.81; p < 0.001) and surgery (HR, 2.53; 95% CI, 1.27-5.03; p = 0.008). CONCLUSIONS: This registry-based analysis found that individuals undergoing lower eyelid blepharoplasty were at higher risk of strabismus compared with those undergoing upper eyelid blepharoplasty. Using large databases to understand the incidence of complications of frequently performed procedures may improve ophthalmologists' ability to provide data-driven counseling on surgical risks prior to intervention.

The epidemiology of pediatric dry eye disease in the United States: An IRIS® registry (Intelligent Research in Sight) analysis.

PURPOSE: Dry-eye disease (DED) is a chronic progressive ocular surface disorder with limited studies in the pediatric population. The Academy of Ophthalmology's IRIS® Registry was leveraged to investigate the prevalence of DED in the pediatric population (PDED, patients <18 years old) and the demographic differences of DED between pediatric and adult patients (ADED). METHODS: Retrospective cohort study. Patients with DED between January 1st, 2013 and December 31st, 2019 (N = 4,795,979) were included. Descriptive statistics, Pearson's chi-squared tests and two-sample proportions tests were conducted to compare key demographic distributions between the ADED and PDED cohorts. RESULTS: The average age at onset for ADED patients was 61.06 (±14.75) years and for PDED patients was 12.51 (±3.86). The overall tests for independence and the individual tests of proportions of each category were statistically significant for all demographic characteristics (p < 0.001). Characteristics with the largest discrepancies between patients of PDED and the IRIS Registry pediatric patient pool (PIRIS) included female sex (58.08 % vs. 50.60 %), male sex (41.58 % vs. 48.78 %) and Asian race (6.02 % vs. 3.11 %) respectively. Within the PDED cohort, females were at higher risk of PDED (58 % vs. 42 %). PDED was more prevalent in children with refractive errors (76 %) and eyelid/conjunctival disorders (41 %). Characteristics with the largest discrepancies between PDED and ADED patients included female sex (58.08 % vs. 68.12 %), male sex (41.58 % vs. 31.55 %) and Caucasian race (50.24 % vs. 67.06 %) respectively. CONCLUSIONS: Significant differences in the PDED cohort are demonstrated in this study. PDED was more prevalent in the female sex and Caucasian race compared to PIRIS and was more commonly associated with refractive errors and eyelid/conjunctival disorders.