Developing a Continuous Severity Scale for Macular Telangiectasia Type 2 Using Deep Learning and Implications for Disease Grading.

PURPOSE: Deep learning (DL) models have achieved state-of-the-art medical diagnosis classification accuracy. Current models are limited by discrete diagnosis labels, but could yield more information with diagnosis in a continuous scale. We developed a novel continuous severity scaling system for macular telangiectasia (MacTel) type 2 by combining a DL classification model with uniform manifold approximation and projection (UMAP). DESIGN: We used a DL network to learn a feature representation of MacTel severity from discrete severity labels and applied UMAP to embed this feature representation into 2 dimensions, thereby creating a continuous MacTel severity scale. PARTICIPANTS: A total of 2003 OCT volumes were analyzed from 1089 MacTel Project participants. METHODS: We trained a multiview DL classifier using multiple B-scans from OCT volumes to learn a previously published discrete 7-step MacTel severity scale. The classifiers' last feature layer was extracted as input for UMAP, which embedded these features into a continuous 2-dimensional manifold. The DL classifier was assessed in terms of test accuracy. Rank correlation for the continuous UMAP scale against the previously published scale was calculated. Additionally, the UMAP scale was assessed in the κ agreement against 5 clinical experts on 100 pairs of patient volumes. For each pair of patient volumes, clinical experts were asked to select the volume with more severe MacTel disease and to compare them against the UMAP scale. MAIN OUTCOME MEASURES: Classification accuracy for the DL classifier and κ agreement versus clinical experts for UMAP. RESULTS: The multiview DL classifier achieved top 1 accuracy of 63.3% (186/294) on held-out test OCT volumes. The UMAP metric showed a clear continuous gradation of MacTel severity with a Spearman rank correlation of 0.84 with the previously published scale. Furthermore, the continuous UMAP metric achieved κ agreements of 0.56 to 0.63 with 5 clinical experts, which was comparable with interobserver κ values. CONCLUSIONS: Our UMAP embedding generated a continuous MacTel severity scale, without requiring continuous training labels. This technique can be applied to other diseases and may lead to more accurate diagnosis, improved understanding of disease progression, and key imaging features for pathologic characteristics. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Race, Ethnicity, Insurance, and Population Density Associations with Pediatric Strabismus and Strabismic Amblyopia in the IRIS® Registry.

PURPOSE: To evaluate the associations of sociodemographic factors with pediatric strabismus diagnosis and outcomes. DESIGN: Retrospective cohort study. PARTICIPANTS: American Academy of Ophthalmology IRIS® Registry (Intelligent Research in Sight) patients with strabismus diagnosed before the age of 10 years. METHODS: Multivariable regression models evaluated the associations of race and ethnicity, insurance, population density, and ophthalmologist ratio with age at strabismus diagnosis, diagnosis of amblyopia, residual amblyopia, and strabismus surgery. Survival analysis evaluated the same predictors of interest with the outcome of time to strabismus surgery. MAIN OUTCOME MEASURES: Age at strabismus diagnosis, rate of amblyopia and residual amblyopia, and rate of and time to strabismus surgery. RESULTS: The median age at diagnosis was 5 years (interquartile range, 3-7) for 106 723 children with esotropia (ET) and 54 454 children with exotropia (XT). Amblyopia diagnosis was more likely with Medicaid insurance than commercial insurance (odds ratio [OR], 1.05 for ET; 1.25 for XT; P < 0.01), as was residual amblyopia (OR, 1.70 for ET; 1.53 for XT; P < 0.01). For XT, Black children were more likely to develop residual amblyopia than White children (OR, 1.34; P < 0.01). Children with Medicaid were more likely to undergo surgery and did so sooner after diagnosis (hazard ratio [HR], 1.23 for ET; 1.21 for XT; P < 0.01) than those with commercial insurance. Compared with White children, Black, Hispanic, and Asian children were less likely to undergo ET surgery and received surgery later (all HRs < 0.87; P < 0.01), and Hispanic and Asian children were less likely to undergo XT surgery and received surgery later (all HRs < 0.85; P < 0.01). Increasing population density and clinician ratio were associated with lower HR for ET surgery (P < 0.01). CONCLUSIONS: Children with strabismus covered by Medicaid insurance had increased odds of amblyopia and underwent strabismus surgery sooner after diagnosis compared with children covered by commercial insurance. After adjusting for insurance status, Black, Hispanic, and Asian children were less likely to receive strabismus surgery with a longer delay between diagnosis and surgery compared with White children. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Sociodemographic and Visual Outcomes of Juvenile Idiopathic Arthritis Uveitis: IRIS® Registry Study.

Purpose: Understanding sociodemographic factors associated with poor visual outcomes in children with juvenile idiopathic arthritis-associated uveitis may help inform practice patterns. Patients and Methods: Retrospective cohort study on patients <18 years old who were diagnosed with both juvenile idiopathic arthritis and uveitis based on International Classification of Diseases tenth edition codes in the Intelligent Research in Sight Registry through December 2020. Surgical history was extracted using current procedural terminology codes. The primary outcome was incidence of blindness (20/200 or worse) in at least one eye in association with sociodemographic factors. Secondary outcomes included cataract and glaucoma surgery following uveitis diagnosis. Hazard ratios were calculated using multivariable-adjusted Cox proportional hazards models. Results: Median age of juvenile idiopathic arthritis-associated uveitis diagnosis was 11 (Interquartile Range: 8 to 15). In the Cox models adjusting for sociodemographic and insurance factors, the hazard ratios of best corrected visual acuity 20/200 or worse were higher in males compared to females (HR 2.15; 95% CI: 1.45-3.18), in Black or African American patients compared to White patients (2.54; 1.44-4.48), and in Medicaid-insured patients compared to commercially-insured patients (2.23; 1.48-3.37). Conclusion: Sociodemographic factors and insurance coverage were associated with varying levels of risk for poor visual outcomes in children with juvenile idiopathic arthritis-associated uveitis.

Artificial Intelligence and Diabetic Retinopathy: AI Framework, Prospective Studies, Head-to-head Validation, and Cost-effectiveness.

Current guidelines recommend that individuals with diabetes receive yearly eye exams for detection of referable diabetic retinopathy (DR), one of the leading causes of new-onset blindness. For addressing the immense screening burden, artificial intelligence (AI) algorithms have been developed to autonomously screen for DR from fundus photography without human input. Over the last 10 years, many AI algorithms have achieved good sensitivity and specificity (>85%) for detection of referable DR compared with human graders; however, many questions still remain. In this narrative review on AI in DR screening, we discuss key concepts in AI algorithm development as a background for understanding the algorithms. We present the AI algorithms that have been prospectively validated against human graders and demonstrate the variability of reference standards and cohort demographics. We review the limited head-to-head validation studies where investigators attempt to directly compare the available algorithms. Next, we discuss the literature regarding cost-effectiveness, equity and bias, and medicolegal considerations, all of which play a role in the implementation of these AI algorithms in clinical practice. Lastly, we highlight ongoing efforts to bridge gaps in AI model data sets to pursue equitable development and delivery.

Ethnicity is not biology: retinal pigment score to evaluate biological variability from ophthalmic imaging using machine learning.

Background: Few metrics exist to describe phenotypic diversity within ophthalmic imaging datasets, with researchers often using ethnicity as an inappropriate marker for biological variability. Methods: We derived a continuous, measured metric, the retinal pigment score (RPS), that quantifies the degree of pigmentation from a colour fundus photograph of the eye. RPS was validated using two large epidemiological studies with demographic and genetic data (UK Biobank and EPIC-Norfolk Study). Findings: A genome-wide association study (GWAS) of RPS from UK Biobank identified 20 loci with known associations with skin, iris and hair pigmentation, of which 8 were replicated in the EPIC-Norfolk cohort. There was a strong association between RPS and ethnicity, however, there was substantial overlap between each ethnicity and the respective distributions of RPS scores. Interpretation: RPS serves to decouple traditional demographic variables, such as ethnicity, from clinical imaging characteristics. RPS may serve as a useful metric to quantify the diversity of the training, validation, and testing datasets used in the development of AI algorithms to ensure adequate inclusion and explainability of the model performance, critical in evaluating all currently deployed AI models. The code to derive RPS is publicly available at: https://github.com/uw-biomedical-ml/retinal-pigmentation-score. Funding: The authors did not receive support from any organisation for the submitted work.

Estimating Uncertainty of Geographic Atrophy Segmentations with Bayesian Deep Learning.

Purpose: To apply methods for quantifying uncertainty of deep learning segmentation of geographic atrophy (GA). Design: Retrospective analysis of OCT images and model comparison. Participants: One hundred twenty-six eyes from 87 participants with GA in the SWAGGER cohort of the Nonexudative Age-Related Macular Degeneration Imaged with Swept-Source OCT (SS-OCT) study. Methods: The manual segmentations of GA lesions were conducted on structural subretinal pigment epithelium en face images from the SS-OCT images. Models were developed for 2 approximate Bayesian deep learning techniques, Monte Carlo dropout and ensemble, to assess the uncertainty of GA semantic segmentation and compared to a traditional deep learning model. Main Outcome Measures: Model performance (Dice score) was compared. Uncertainty was calculated using the formula for Shannon Entropy. Results: The output of both Bayesian technique models showed a greater number of pixels with high entropy than the standard model. Dice scores for the Monte Carlo dropout method (0.90, 95% confidence interval 0.87-0.93) and the ensemble method (0.88, 95% confidence interval 0.85-0.91) were significantly higher (P < 0.001) than for the traditional model (0.82, 95% confidence interval 0.78-0.86). Conclusions: Quantifying the uncertainty in a prediction of GA may improve trustworthiness of the models and aid clinicians in decision-making. The Bayesian deep learning techniques generated pixel-wise estimates of model uncertainty for segmentation, while also improving model performance compared with traditionally trained deep learning models. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.