EyeArt artificial intelligence analysis of diabetic retinopathy in retinal screening events.

PURPOSE: Early detection and treatment of diabetic retinopathy (DR) are critical for decreasing the risk of vision loss and preventing blindness. Community vision screenings may play an important role, especially in communities at higher risk for diabetes. To address the need for increased DR detection and referrals, we evaluated the use of artificial intelligence (AI) for screening DR. METHODS: Patient images of 124 eyes were obtained using a 45° Canon Non-Mydriatic CR-2 Plus AF retinal camera in the Department of Endocrinology Clinic (Newark, NJ) and in a community screening event (Newark, NJ). Images were initially classified by an onsite grader and uploaded for analysis by EyeArt, a cloud-based AI software developed by Eyenuk (California, USA). The images were also graded by an off-site retina specialist. Using Fleiss kappa analysis, a correlation was investigated between the three grading systems, the AI, onsite grader, and a US board-certified retina specialist, for a diagnosis of DR and referral pattern. RESULTS: The EyeArt results, onsite grader, and the retina specialist had a 79% overall agreement on the diagnosis of DR: 86 eyes with full agreement, 37 eyes with agreement between two graders, 1 eye with full disagreement. The kappa value for concordance on a diagnosis was 0.69 (95% CI 0.61-0.77), indicating substantial agreement. Referral patterns by EyeArt, the onsite grader, and the ophthalmologist had an 85% overall agreement: 96 eyes with full agreement, 28 eyes with disagreement. The kappa value for concordance on "whether to refer" was 0.70 (95% CI 0.60-0.80), indicating substantial agreement. Using the board-certified retina specialist as the gold standard, EyeArt had an 81% accuracy (101/124 eyes) for diagnosis and 83% accuracy (103/124 eyes) in referrals. For referrals, the sensitivity of EyeArt was 74%, specificity was 87%, positive predictive value was 72%, and negative predictive value was 88%. CONCLUSIONS: This retrospective cross-sectional analysis offers insights into use of AI in diabetic screenings and the significant role it will play in automated detection of DR. The EyeArt readings were beneficial with some limitations in a community screening environment. These limitations included a decreased accuracy in the presence of cataracts and the functional cost of EyeArt uploads in a community setting.

Measuring the Mueller matrix of an arbitrary optical element with a universal SU(2) polarization gadget.

We propose a new method for determining the Mueller matrix of an arbitrary optical element and verify it with three known optical elements. This method makes use of two universal SU(2) polarization gadgets to obtain the projection matrix directly from the experiment. It allows us to determine the Mueller matrix without precalibration of the setup, since the generated polarization states are fully determined by the azimuths of the wave plates. We calculate errors in determining the Mueller matrix and compare with other techniques.

Hyphema and vitreous hemorrhage after micropulse cyclophotocoagulation a case report.

INTRODUCTION: We present two cases of vitreous hemorrhage after micropulse cyclophotocoagulation one of which had concurrent hyphema. To the best of our knowledge, these are the first cases of vitreous hemorrhage due to micropulse CPC in the United States. CASE DESCRIPTION: The first case is an 82-year-old woman with bilateral severe primary open angle glaucoma. BCVA in the right eye was 20/25, and 10-2 Humphrey visual field showed severe peripheral defects. The patient underwent MPCPC of the right eye and at one week, a settled 2 mm hyphema and vitreous hemorrhage confirmed by B-scan were noted. At three months, the patient had a BCVA of 20/80 with an IOP of 12 and retina consultation deferred a PPV. The second case is of a patient with bilateral moderate stage POAG who underwent MPCPC in both eyes. His original VA was 20/200 bilaterally. At 2 weeks, RE VA was count fingers at one foot and LE was 20/150-1. At two months, a RE B scan revealed dense vitreous opacities. Retina consultation revealed vitreous hemorrhage but a PPV was deferred. CONCLUSION: Clinicians should be aware of the risks of bleeding and the potential need for additional surgical interventions after MPCPC.

Low Amount and Intensity of Leisure-time Physical Activity in Asian Indian Adults.

PURPOSE: We sought to describe leisure-time, aerobic, and muscle strengthening physical activity (PA) patterns in U.S. Asian Indians, in comparison to other races/ethnicities. DESIGN, SETTING, AND SAMPLE: We utilized the 2011-2018 National Health Interview Surveys, a set of cross-sectional, nationally representative surveys of the U.S. noninstitutionalized population. Our study population included 257 652 adults who answered PA questions. MEASURES: PA was classified per 2008 U.S. guidelines and continuously per estimated metabolic equivalents (METs). Race was classified into White, Black, Asian Indian, Other Asian, and American Indian/Alaskan Native/Multiracial. ANALYSIS: We used survey design-adjusted, multivariable logistic regression to determine odds of sufficient and highly active physical activity levels, adjusting for predisposing, enabling, need, and health care service factors as guided by the Anderson Model. We also used linear regression to determine racial differences in average MET-minutes/week. Analysis was additionally stratified by comorbidity status. RESULTS: While Asian Indians (N = 3049) demonstrated similar odds of sufficient aerobic PA as Whites (aOR [95% CI]: .97 [.88,1.07]), Asian Indians had 22% lower odds of meeting highly active aerobic PA levels (.78 [.71,0.87]) and 18% lower odds of meeting sufficient muscle strengthening PA levels (.82 [.73,0.91]). This translated to an average 172 (95% CI: 45 300) fewer MET-minutes. Furthermore, this decrease in MET-minutes/week was especially apparent in those without hypertension (ß[95% CI]: -164 [-314,-15]) without diabetes (-185 [-319,-52]), and low/normal BMI (-422 [-623,-222]). CONCLUSION: Asian Indians, especially those without comorbidities, are less likely to engage in high-intensity physical activity than Whites.