iGWAS: Image-based genome-wide association of self-supervised deep phenotyping of retina fundus images.

Existing imaging genetics studies have been mostly limited in scope by using imaging-derived phenotypes defined by human experts. Here, leveraging new breakthroughs in self-supervised deep representation learning, we propose a new approach, image-based genome-wide association study (iGWAS), for identifying genetic factors associated with phenotypes discovered from medical images using contrastive learning. Using retinal fundus photos, our model extracts a 128-dimensional vector representing features of the retina as phenotypes. After training the model on 40,000 images from the EyePACS dataset, we generated phenotypes from 130,329 images of 65,629 British White participants in the UK Biobank. We conducted GWAS on these phenotypes and identified 14 loci with genome-wide significance (p<5×10-8 and intersection of hits from left and right eyes). We also did GWAS on the retina color, the average color of the center region of the retinal fundus photos. The GWAS of retina colors identified 34 loci, 7 are overlapping with GWAS of raw image phenotype. Our results establish the feasibility of this new framework of genomic study based on self-supervised phenotyping of medical images.

Factors Associated with Follow-Up Adherence After Teleophthalmology for Diabetic Eye Screening Before and During the COVID-19 Pandemic.

Abstract Background: Follow-up adherence with in-person care is critical for achieving improved clinical outcomes in telemedicine screening programs. We sought to quantify the impact of the COVID-19 pandemic upon follow-up adherence and factors associated with follow-up adherence after teleophthalmology for diabetic eye screening. Methods: We retrospectively reviewed medical records of adults screened in a clinical teleophthalmology program at urban and rural primary care clinics between May 2015 and December 2020. We defined follow-up adherence as medical record documentation of an in-person eye exam within 1 year among patients referred for further care. Regression models were used to identify factors associated with follow-up adherence. Results: Among 948 patients, 925 (97.6%) had health insurance and 170 (17.9%) were referred for follow-up. Follow-up adherence declined from 62.7% (n = 52) prepandemic to 46.0% (n = 40) during the pandemic (p = 0.04). There was a significant decline in follow-up adherence among patients from rural (p < 0.001), but not urban (p = 0.72) primary care clinics. Higher median household income (odds ratio [OR] 1.68, 95% confidence interval [CI]: 1.19-2.36) and obtaining care from an urban clinic (OR 5.29, 95% CI: 2.09-13.43) were associated with greater likelihood of follow-up during the pandemic. Discussion: Follow-up adherence remains limited after teleophthalmology screening even in a highly insured patient population, with a further decline observed during the COVID-19 pandemic. Our results suggest that rural patients and those with lower socioeconomic status experienced greater barriers to follow-up eye care during the COVID-19 pandemic. Conclusions: Addressing barriers to in-person follow-up care is needed to effectively improve clinical outcomes after teleophthalmology screening.

Artificial Intelligence Algorithms in Diabetic Retinopathy Screening.

PURPOSE OF REVIEW: In this review, we focus on artificial intelligence (AI) algorithms for diabetic retinopathy (DR) screening and risk stratification and factors to consider when implementing AI algorithms in the clinic. RECENT FINDINGS: AI algorithms have been adopted, and have received regulatory approval, for automated detection of referable DR with clinically acceptable diagnostic performance. While these metrics are an important first step, performance metrics that go beyond measures of technical accuracy are needed to fully evaluate the impact of AI algorithm on patient outcomes. Recent advances in AI present an exciting opportunity to improve patient care. Using DR as an example, we have reviewed factors to consider in the implementation of AI algorithms in real-world clinical practice. These include real-world evaluation of safety, efficacy, and equity (bias); impact on patient outcomes; ethical, logistical, and regulatory factors.

Pediatric Diabetic Retinopathy: Updates in Prevalence, Risk Factors, Screening, and Management.

PURPOSE OF REVIEW: Diabetic retinopathy (DR) is a microvascular complication of diabetes mellitus and a major cause of vision loss worldwide. The purpose of this review is to provide an update on the prevalence of diabetic retinopathy in youth, discuss risk factors, and review recent advances in diabetic retinopathy screening. RECENT FINDINGS: While DR has long been considered a microvascular complication, recent data suggests that retinal neurodegeneration may precede the vascular changes associated with DR. The prevalence of DR has decreased in type 1 diabetes (T1D) patients following the results of the Diabetes Control and Complications Trial and implementation of intensive insulin therapy, with prevalence ranging from 14-20% before the year 2000 to 3.7-6% after 2000. In contrast, the prevalence of diabetic retinopathy in pediatric type 2 diabetes (T2D) is higher, ranging from 9.1-50%. Risk factors for diabetic retinopathy are well established and include glycemic control, diabetes duration, hypertension, and hyperlipidemia, whereas diabetes technology use including insulin pumps and continuous glucose monitors has been shown to have protective effects. Screening for DR is recommended for youth with T1D once they are aged ≥ 11 years or puberty has started and diabetes duration of 3-5 years. Pediatric T2D patients are advised to undergo screening at or soon after diagnosis, and annually thereafter, due to the insidious nature of T2D. Recent advances in DR screening methods including point of care and artificial intelligence technology have increased access to DR screening, while being cost-saving to patients and cost-effective to healthcare systems. While the prevalence of diabetic retinopathy in youth with T1D has been declining over the last few decades, there has been a significant increase in the prevalence of DR in youth with T2D. Improving access to diabetic retinopathy screening using novel screening methods may help improve detection and early treatment of diabetic retinopathy.

Single transient intraocular pressure elevations cause prolonged retinal ganglion cell dysfunction and retinal capillary abnormalities in mice.

Transient intraocular pressure (IOP) elevations are likely to occur in certain forms of glaucoma and after intravitreal injections to treat various retinal diseases. However, the impact of these transient IOP elevations on the physiology of individual retinal ganglion cells (RGCs) is unknown. In this report, we explore how transient IOP elevations in mice affect RGC physiology, RGC anatomy, and retinal arteriole and capillary structure. Transient IOP elevation was induced in 12-week old wild type C57BL6J mice by injecting sodium hyaluronate into the anterior chamber. IOP was measured immediately after the injection and again 1 and 7 days later. Average peak IOP after injection was ~50 mmHg and subsequent IOPs returned to normal. RGC physiology was assessed with a multielectrode array (MEA) by calculating a spike triggered average (STA) at the same time points. RGC counts and retinal vascular structure were assessed 14 days after injection with immunohistochemistry to label RGCs and blood vessels. Transient IOP elevation caused a marked reduction of scotopic STA presence and delayed center and surround STA peak times that did not recover. Transient IOP elevation also caused a reduced photopic receptive field size and spontaneous firing rate, both of which showed some recovery with time. Transient IOP elevation also induced vascular remodeling: the number of capillary branches was decreased within the superficial and intermediate vascular plexi. RGC counts, retinal arteriole diameter, and deep capillary plexus branching were unaffected. These previously unappreciated findings suggest that transient IOP elevation may cause unrecognized and potentially long-term pathology to RGCs and associated neurovascular units which should be accounted for in clinical practice.

Alterations in the retinal vasculature occur in multiple sclerosis and exhibit novel correlations with disability and visual function measures.

BACKGROUND: The retinal vasculature may be altered in multiple sclerosis (MS), potentially acting as a biomarker of disease processes. OBJECTIVE: To compare retinal vascular plexus densities in people with MS (PwMS) and healthy controls (HCs), and examine correlations with visual function and global disability. METHODS: In this cross-sectional study, 111 PwMS (201 eyes) and 50 HCs (97 eyes) underwent optical coherence tomography angiography (OCTA). Macular superficial vascular plexus (SVP) and deep vascular plexus (DVP) densities were quantified, and poor quality images were excluded according to an artifact-rating protocol. RESULTS: Mean SVP density was 24.1% (SD = 5.5) in MS eyes (26.0% (SD = 4.7) in non-optic neuritis (ON) eyes vs. 21.7% (SD = 5.5) in ON eyes, p < 0.001), as compared to 29.2% (SD = 3.3) in HC eyes (p < 0.001 for all MS eyes and multiple sclerosis optic neuritis (MSON) eyes vs. HC eyes, p = 0.03 for MS non-ON eyes vs. HC eyes). DVP density did not differ between groups. In PwMS, lower SVP density was associated with higher levels of disability (expanded disability status scale (EDSS): R2 = 0.26, p = 0.004; multiple sclerosis functional composite (MSFC): R2 = 0.27, p = 0.03) and lower letter acuity scores (100% contrast: R2 = 0.29; 2.5% contrast: R2 = 0.40; 1.25% contrast: R2 = 0.31; p < 0.001 for all). CONCLUSIONS: Retinal SVP density measured by OCTA is reduced across MS eyes, and correlates with visual function, EDSS, and MSFC scores.

Prevalence of diabetic retinopathy in children and adolescents at an urban tertiary eye care center.

BACKGROUND: Diabetic retinopathy (DR) is a serious complication that can progress to sight-threatening disease. The prevalence of DR in youth with diabetes has been reported to be 3.8% to 20%. OBJECTIVE: We aimed to evaluate the prevalence of DR among youth with diabetes at a large ophthalmologic referral center. Secondary goals were to determine the risk factors for DR and severity of disease. METHODS: Retrospective chart review of 343 patients with diabetes, <21 years of age, seen at a tertiary referral eye care center from 2013 to 2018. RESULTS: The study included 343 patients, of which 293 had type 1 diabetes (T1D) and 50 had type 2 diabetes (T2D). Thirteen of 343 patients had DR, with an overall incidence of 3.8% (3.4% in T1D and 6% T2D). DR severity included nine with mild non-proliferative, three moderate non-proliferative, and one with proliferative DR. Patients with hemoglobin A1c (HbA1c) > 8% had a higher risk of DR (P = .049). In this cohort, none of the patients with an HbA1c <8% had DR. In the multivariate analysis, a higher systolic blood pressure was marginally associated with risk for DR (P = .07). CONCLUSIONS: We found lower prevalence of DR in youth with diabetes than previously reported. The incidence of DR was higher among patients with T2D and occurred with a shorter duration of disease, as compared with T1D. While the incidence of DR in youth with T1D is low, with the increasing incidence of T2D in adolescents and early risk for DR, early screening must be emphasized.

Different Factors Associated with 2-Year Outcomes in Patients with Branch versus Central Retinal Vein Occlusion Treated with Ranibizumab.

PURPOSE: To investigate characteristics associated with visual and anatomic outcomes in branch and central retinal vein occlusion (BRVO and CRVO) patients treated with ranibizumab. DESIGN: Post hoc analysis of patients with BRVO and CRVO from 2 multicenter clinical trials who completed month 12 of the HORIZON extension trial. PARTICIPANTS: 205 patients with BRVO and 181 patients with CRVO who completed month 12 of the extension trial. METHODS: With the use of logistic regression, covariates with a P value < 0.20 from univariate analysis were included in multivariate models to identify independent factors associated with a given outcome (at P < 0.05), with preset variables of disease duration and original treatment assignment. MAIN OUTCOME MEASURES: Best-corrected visual acuity (BCVA) ≥20/40 (≥70 letters), gain ≥15 letters, and central subfield thickness (CST) ≤250 µm at HORIZON month 12. RESULTS: In patients with BRVO, good baseline BCVA (odds ratio [OR], 1.53; 95% confidence interval [CI], 1.30-1.79), male sex (OR, 2.48; 95% CI, 1.20-5.13), and normal hematocrit (low vs. normal, OR, 0.26; 95% CI, 0.12-0.59) predicted BCVA ≥20/40; high central foveal thickness (OR, 1.03; 95% CI, 1.01-1.04) and normal hematocrit (low vs. normal, OR, 0.31; 95% CI, 0.15-0.66) predicted BCVA improvement ≥15 letters; and extensive baseline subretinal fluid modestly predicted CST ≤250 µm (OR, 1.08; 95% CI, 1.00-1.16). In patients with CRVO, good baseline BCVA (OR, 1.59; 95% CI, 1.35-1.89), never smoking (OR, 2.80; 95% CI, 1.27-6.17), and young age (OR, 0.58; 95% CI, 0.41-0.82) predicted BCVA ≥20/40; never smoking (OR, 2.13; 95% CI, 1.03-4.39), young age (OR, 0.41; 95% CI, 0.28-0.59), poor baseline BCVA (OR, 0.82; 95% CI, 0.73-0.93), hypertension (OR, 4.47; 95% CI, 1.70-11.75), and low diastolic ocular perfusion pressure (OPP) throughout the study (OR, 0.39; 95% CI, 0.21-0.72) predicted BCVA improvement ≥15 letters; and young age (OR, 0.65; 95% CI, 0.47-0.90), lower mean hematocrit (low vs. normal, OR, 2.81; 95% CI, 1.06-7.49), high systolic OPP throughout the study (OR, 1.61; 95% CI, 1.14-2.27), large areas of central hemorrhage (OR, 1.44; 95% CI, 1.04-2.00), and no subretinal fluid (OR, 2.15; 95% CI, 1.06-4.40) predicted CST ≤250 µm. CONCLUSIONS: There are substantial differences in good outcome factors in CRVO versus BRVO, suggesting differences in pathophysiology. Young age, never smoking, hemodilution, and hypertension/high systolic perfusion pressure are more beneficial in CRVO, suggesting that avoidance of sluggish blood flow and maintenance of perfusion may be particularly important in CRVO.

Retinal Neurodegeneration as an Early Manifestation of Diabetic Eye Disease and Potential Neuroprotective Therapies.

PURPOSE OF REVIEW: Diabetic retinopathy (DR) is a major cause of visual impairment and blindness throughout the world. Microvascular changes have long been regarded central to disease pathogenesis. In recent years, however, retinal neurodegeneration is increasingly being hypothesized to occur prior to the vascular changes classically associated with DR and contribute to disease pathogenesis. RECENT FINDINGS: There is growing structural and functional evidence from human and animal studies that suggests retinal neurodegeneration to be an early component of DR. Identification of new therapeutic targets is an ongoing area of research with several different molecules undergoing testing in animal models for their neuroprotective properties and for possible use in humans. Retinal neurodegeneration may play a central role in DR pathogenesis. As new therapies are developed, it will be important to develop criteria for clinically defining retinal neurodegeneration. A standardization of the methods for monitoring neurodegeneration along with more sensitive means of detecting preclinical damage is also needed.

Estimating the Global Demand and Delivery of Cancer Surgery.

BACKGROUND: Cancer is a leading cause of death and disability globally. While surgery remains a vital part of cancer management, access to surgical care remains inconsistent. Our objective was to estimate the global need for cancer-related surgery and to identify disparities in the surgeon workforce. METHODS: The World Health Organization International Agency for Research on Cancer and the Global Cancer Observatory were queried for estimates on national incidences of 35 different malignancies. The proportion of patients requiring surgery for each of these cancers was extrapolated from the United States Surveillance, Epidemiology and End-Result database. The number of people requiring cancer surgery in each country was calculated and compared with the surgical workforce. Estimates were presented as choropleth maps. Associations were tested with country development indicators. RESULTS: An estimated 9,464,214 (95% CI 4,364,196-14,564,230) patients required cancer-related surgical care in 2018. An overall 1.24 people needed cancer surgery per 1000 population. This was related to income status (p < 0.01) and Human Development Index (r = 0.86, p < 0.001), with the largest need being in high-income countries. The number of people requiring cancer surgery per surgeon (CP-S ratio) ranged from 7.3 in the European region to 80 in the African regions. The CP-S ratio was 10 times higher for low- versus high-income countries (p < 0.001) and was inversely related to healthcare expenditure (r = -0.59, p < 0.001). CONCLUSIONS: An estimated 9.5 million people required cancer surgery globally. Low- and middle-income countries experience a severe and acute shortage of surgeons to provide for the cancer surgery needs of the population.

Robotic Vitreoretinal Surgery.

PURPOSE: To review the current literature on robotic assistance for ophthalmic surgery, especially vitreoretinal procedures. METHODS: MEDLINE, Embase, and Web of Science databases were searched from inception to August, 2016, for articles relevant to the review topic. Queries included combinations of the terms: robotic eye surgery, ophthalmology, and vitreoretinal. RESULTS: In ophthalmology, proof-of-concept papers have shown the feasibility of performing many delicate anterior segment and vitreoretinal surgical procedures accurately with robotic assistance. Multiple surgical platforms have been designed and tested in animal eyes and phantom models. These platforms have the capability to measure forces generated and velocities of different surgical movements. "Smart" instruments have been designed to improve certain tasks such as membrane peeling and retinal vessel cannulations. CONCLUSION: Ophthalmic surgery, particularly vitreoretinal surgery, might have reached the limits of human physiologic performance. Robotic assistance can help overcome biologic limitations and improve our surgical performance. Clinical studies of robotic-assisted surgeries are needed to determine safety and feasibility of using this technology in patients.

Dipeptidyl peptidase 4 inhibitors, sodium glucose cotransporter 2 inhibitors, and glucagon-like peptide 1 receptor agonists do not worsen diabetic macular edema.

AIMS: There are limited studies on dipeptidyl-peptidase 4 inhibitor (DPP-4i), sodium glucose cotransporter 2 inhibitor (SGLT2-i), and glucagon-like peptide 1 (GLP-1) receptor agonist use and occurrence of diabetic macular edema (DME). The objective of this study was to determine the association between DPP-4i, SGLT2-i, and GLP-1 receptor agonist use and occurrence of DME. METHODS: Proportional hazard models were used to evaluate the change in hazard of developing DME associated with DPP-4i, SGLT2-i, or GLP-1 receptor agonist use. Models accounted for age at DR diagnosis, DR severity (proliferative vs non-proliferative stage), time-weighted average of HbA1c level, sex, and self-reported race/ethnicity. A p-value ≤ 0.05 was considered statistically significant. RESULTS: The hazard ratio of developing DME after diagnosis of DR was 1.2 (CI = 0.75 to 1.99; p = 0.43) for DPP-4i use, 0.93 (CI = 0.54 to 1.61; p = 0.81) for GLP-1 receptor agonist use, 0.82 (CI = 0.20 to 3.34; p = 0.78) for SGLT2-i use, 1.1 (CI = 0.75 to 1.59; p = 0.66) for any one medication use, 1.1 (CI = 0.62 to 2.09; p = 0.68) and for any two or more medications use. CONCLUSIONS: We did not find an association between DPP-4i, SGLT2-i, or GLP-1 receptor agonist use and increased hazard of development of DME among patients with DR.

Comparison of Standard 7-Field, Clarus, and Optos Ultrawidefield Imaging Systems for Diabetic Retinopathy (COCO Study).

Purpose: The purpose of this study was to compare diabetic retinopathy (DR) severity levels assessed from 7 standard-field stereoscopic color photographs on a 35° fundus camera to both Clarus and Optos ultrawidefield color images. Design: Cross-sectional, comparative imaging study. Participants: Participants with DR imaged at a single-center retina practice. Methods: Participants were imaged on 3 cameras at a single visit with the Topcon 35° fundus camera, Clarus, and Optos. The DR Severity Scale (DRSS) level was determined within the 7-field (7F) area of each image set using the ETDRS scale. An additional global DRSS was assigned for both Clarus and Optos images using the entire visible retina. Weighted kappa (wκ) measured the agreement between cameras. Main Outcome Measures: The primary outcome was a 3-way comparison of DRSS level within the 7F area imaged on the 3 cameras. Secondary outcomes included a comparison of the DRSS obtained with standard 7F imaging to the global DRSS of Clarus and Optos and a comparison of the global DRSS between Clarus and Optos only. Results: Ninety-seven eyes (50 participants) were evaluated. Agreement within 1-step of ETDRS levels between standard 7F imaging and Clarus 7F was 90.1% (wκ = 0.65), and with Optos 7F in 85.9%, (wκ = 0.58). Agreement within 1-step between standard 7F imaging and Clarus global was 88.9% of eyes (wκ = 0.63), and Optos global was 85.7%, (wκ = 0.54). Agreement between Clarus and Optos global DR level within 1-step was 89.1% (wκ = 0.68). Intergrader agreement for the 7F ETDRS level was 96% for standard 7F imaging, 98% for Clarus, and 95.5% for Optos. Conclusions: These findings suggest that when evaluating the 7F area on Clarus and Optos, DR severity grades are comparable to standard 7F imaging. However, it is important to understand the unique attributes and differences of each fundus camera when changing the type of system used in a clinical setting due to upgrading equipment. Additionally, if the facility has access to > 1 device, there should not be an exchange between cameras for the same patient. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

A New Approach to Staging Diabetic Eye Disease: Staging of Diabetic Retinal Neurodegeneration and Diabetic Macular Edema.

Topic: The goal of this review was to summarize the current level of evidence on biomarkers to quantify diabetic retinal neurodegeneration (DRN) and diabetic macular edema (DME). Clinical relevance: With advances in retinal diagnostics, we have more data on patients with diabetes than ever before. However, the staging system for diabetic retinal disease is still based only on color fundus photographs and we do not have clear guidelines on how to incorporate data from the relatively newer modalities into clinical practice. Methods: In this review, we use a Delphi process with experts to identify the most promising modalities to identify DRN and DME. These included microperimetry, full-field flash electroretinogram, spectral-domain OCT, adaptive optics, and OCT angiography. We then used a previously published method of determining the evidence level to complete detailed evidence grids for each modality. Results: Our results showed that among the modalities evaluated, the level of evidence to quantify DRN and DME was highest for OCT (level 1) and lowest for adaptive optics (level 4). Conclusion: For most of the modalities evaluated, prospective studies are needed to elucidate their role in the management and outcomes of diabetic retinal diseases. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Autonomous Artificial Intelligence Increases Access and Health Equity in Underserved Populations with Diabetes.

Diabetic eye disease (DED) is a leading cause of blindness in the world. Early detection and treatment of DED have been shown to be both sight-saving and cost-effective. As such, annual testing for DED is recommended for adults with diabetes and is a Healthcare Effectiveness Data and Information Set (HEDIS) measure. However, adherence to this guideline has historically been low, and access to this sight-saving intervention has particularly been limited for specific populations, such as Black or African American patients. In 2018, the US Food and Drug Agency (FDA) De Novo cleared autonomous artificial intelligence (AI) for diagnosing DED in a primary care setting. In 2020, Johns Hopkins Medicine (JHM), an integrated healthcare system with over 30 primary care sites, began deploying autonomous AI for DED testing in some of its primary care clinics. In this retrospective study, we aimed to determine whether autonomous AI implementation was associated with increased adherence to annual DED testing, and whether this was different for specific populations. JHM primary care sites were categorized as "non-AI" sites (sites with no autonomous AI deployment over the study period and where patients are referred to eyecare for DED testing) or "AI-switched" sites (sites that did not have autonomous AI testing in 2019 but did by 2021). We conducted a difference-in-difference analysis using a logistic regression model to compare change in adherence rates from 2019 to 2021 between non-AI and AI-switched sites. Our study included all adult patients with diabetes managed within our health system (17,674 patients for the 2019 cohort and 17,590 patients for the 2021 cohort) and has three major findings. First, after controlling for a wide range of potential confounders, our regression analysis demonstrated that the odds ratio of adherence at AI-switched sites was 36% higher than that of non-AI sites, suggesting that there was a higher increase in DED testing between 2019 and 2021 at AI-switched sites than at non-AI sites. Second, our data suggested autonomous AI improved access for historically disadvantaged populations. The adherence rate for Black/African Americans increased by 11.9% within AI-switched sites whereas it decreased by 1.2% within non-AI sites over the same time frame. Third, the data suggest that autonomous AI improved health equity by closing care gaps. For example, in 2019, a large adherence rate gap existed between Asian Americans and Black/African Americans (61.1% vs. 45.5%). This 15.6% gap shrank to 3.5% by 2021. In summary, our real-world deployment results in a large integrated healthcare system suggest that autonomous AI improves adherence to a HEDIS measure, patient access, and health equity for patients with diabetes - particularly in historically disadvantaged patient groups. While our findings are encouraging, they will need to be replicated and validated in a prospective manner across more diverse settings.

Strong versus Weak Data Labeling for Artificial Intelligence Algorithms in the Measurement of Geographic Atrophy.

Purpose: To gain an understanding of data labeling requirements to train deep learning models for measurement of geographic atrophy (GA) with fundus autofluorescence (FAF) images. Design: Evaluation of artificial intelligence (AI) algorithms. Subjects: The Age-Related Eye Disease Study 2 (AREDS2) images were used for training and cross-validation, and GA clinical trial images were used for testing. Methods: Training data consisted of 2 sets of FAF images; 1 with area measurements only and no indication of GA location (Weakly labeled) and the second with GA segmentation masks (Strongly labeled). Main Outcome Measures: Bland-Altman plots and scatter plots were used to compare GA area measurement between ground truth and AI measurements. The Dice coefficient was used to compare accuracy of segmentation of the Strong model. Results: In the cross-validation AREDS2 data set (n = 601), the mean (standard deviation [SD]) area of GA measured by human grader, Weakly labeled AI model, and Strongly labeled AI model was 6.65 (6.3) mm2, 6.83 (6.29) mm2, and 6.58 (6.24) mm2, respectively. The mean difference between ground truth and AI was 0.18 mm2 (95% confidence interval, [CI], -7.57 to 7.92) for the Weakly labeled model and -0.07 mm2 (95% CI, -1.61 to 1.47) for the Strongly labeled model. With GlaxoSmithKline testing data (n = 156), the mean (SD) GA area was 9.79 (5.6) mm2, 8.82 (4.61) mm2, and 9.55 (5.66) mm2 for human grader, Strongly labeled AI model, and Weakly labeled AI model, respectively. The mean difference between ground truth and AI for the 2 models was -0.97 mm2 (95% CI, -4.36 to 2.41) and -0.24 mm2 (95% CI, -4.98 to 4.49), respectively. The Dice coefficient was 0.99 for intergrader agreement, 0.89 for the cross-validation data, and 0.92 for the testing data. Conclusions: Deep learning models can achieve reasonable accuracy even with Weakly labeled data. Training methods that integrate large volumes of Weakly labeled images with small number of Strongly labeled images offer a promising solution to overcome the burden of cost and time for data labeling. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Risk Factors for Nondiagnostic Imaging in a Real-World Deployment of Artificial Intelligence Diabetic Retinal Examinations in an Integrated Healthcare System: Maximizing Workflow Efficiency Through Predictive Dilation.

OBJECTIVE: In the pivotal clinical trial that led to Food and Drug Administration De Novo "approval" of the first fully autonomous artificial intelligence (AI) diabetic retinal disease diagnostic system, a reflexive dilation protocol was used. Using real-world deployment data before implementation of reflexive dilation, we identified factors associated with nondiagnostic results. These factors allow a novel predictive dilation workflow, where patients most likely to benefit from pharmacologic dilation are dilated a priori to maximize efficiency and patient satisfaction. METHODS: Retrospective review of patients who were assessed with autonomous AI at Johns Hopkins Medicine (8/2020 to 5/2021). We constructed a multivariable logistic regression model for nondiagnostic results to compare characteristics of patients with and without diagnostic results, using adjusted odds ratio (aOR). P < .05 was considered statistically significant. RESULTS: Of 241 patients (59% female; median age = 59), 123 (51%) had nondiagnostic results. In multivariable analysis, type 1 diabetes (T1D, aOR = 5.82, 95% confidence interval [CI]: 1.45-23.40, P = .01), smoking (aOR = 2.86, 95% CI: 1.36-5.99, P = .005), and age (every 10-year increase, aOR = 2.12, 95% CI: 1.62-2.77, P < .001) were associated with nondiagnostic results. Following feature elimination, a predictive model was created using T1D, smoking, age, race, sex, and hypertension as inputs. The model showed an area under the receiver-operator characteristics curve of 0.76 in five-fold cross-validation. CONCLUSIONS: We used factors associated with nondiagnostic results to design a novel, predictive dilation workflow, where patients most likely to benefit from pharmacologic dilation are dilated a priori. This new workflow has the potential to be more efficient than reflexive dilation, thus maximizing the number of at-risk patients receiving their diabetic retinal examinations.

Use of Diabetes Technologies and Retinopathy in Adults With Type 1 Diabetes.

Importance: Diabetic retinopathy (DR) is a complication of diabetes that can lead to vision loss. Outcomes of continuous glucose monitoring (CGM) and insulin pump use in DR are not well understood. Objective: To assess the use of CGM, insulin pump, or both, and DR and proliferative diabetic retinopathy (PDR) in adults with type 1 diabetes (T1D). Design, Setting, and Participants: A retrospective cohort study of adults with T1D in a tertiary diabetes center and ophthalmology center was conducted from 2013 to 2021, with data analysis performed from June 2022 to April 2023. Exposure: Use of diabetes technologies, including insulin pump, CGM, and both CGM and insulin pump. Main Outcomes and Measures: The primary outcome was development of DR or PDR. A secondary outcome was the progression of DR for patients in the longitudinal cohort. Multivariable logistic regression models assessed for development of DR and PDR and association with CGM and insulin pump use. Results: A total of 550 adults with T1D were included (median age, 40 [IQR, 28-54] years; 54.4% female; 24.5% Black or African American; and 68.4% White), with a median duration of diabetes of 20 (IQR, 10-30) years, and median hemoglobin A1c (HbA1c) of 7.8% (IQR, 7.0%-8.9%). Overall, 62.7% patients used CGM, 58.2% used an insulin pump, and 47.5% used both; 44% (244 of 550) of the participants had DR at any point during the study. On univariate analysis, CGM use was associated with lower odds of DR and PDR, and CGM with pump was associated with lower odds of PDR (all P < .05), compared with no CGM use. Multivariable logistic regression adjusting for age, sex, race and ethnicity, diabetes duration, microvascular and macrovascular complications, insurance type, and mean HbA1c, showed that CGM was associated with lower odds of DR (odds ratio [OR], 0.52; 95% CI, 0.32-0.84; P = .008) and PDR (OR, 0.42; 95% CI, 0.23-0.75; P = .004), compared with no CGM use. In the longitudinal analysis of participants without baseline PDR, 79 of 363 patients (21.8%) had progression of DR during the study. Conclusions and Relevance: In this cohort study of adults with T1D, CGM use was associated with lower odds of developing DR and PDR, even after adjusting for HbA1c. These findings suggest that CGM may be useful for diabetes management to mitigate risk for DR and PDR.

Autonomous artificial intelligence increases screening and follow-up for diabetic retinopathy in youth: the ACCESS randomized control trial.

Diabetic retinopathy can be prevented with screening and early detection. We hypothesized that autonomous artificial intelligence (AI) diabetic eye exams at the point-of-care would increase diabetic eye exam completion rates in a racially and ethnically diverse youth population. AI for Children's diabetiC Eye ExamS (NCT05131451) is a parallel randomized controlled trial that randomized youth (ages 8-21 years) with type 1 and type 2 diabetes to intervention (autonomous artificial intelligence diabetic eye exam at the point of care), or control (scripted eye care provider referral and education) in an academic pediatric diabetes center. The primary outcome was diabetic eye exam completion rate within 6 months. The secondary outcome was the proportion of participants who completed follow-through with an eye care provider if deemed appropriate. Diabetic eye exam completion rate was significantly higher (100%, 95%CI: 95.5%, 100%) in the intervention group (n = 81) than the control group (n = 83) (22%, 95%CI: 14.2%, 32.4%)(p < 0.001). In the intervention arm, 25/81 participants had an abnormal result, of whom 64% (16/25) completed follow-through with an eye care provider, compared to 22% in the control arm (p < 0.001). Autonomous AI increases diabetic eye exam completion rates in youth with diabetes.