Purpose: To evaluate ocular function and systemic development in premature infants treated with intravitreal bevacizumab injections for retinopathy of prematurity over a period of 5 years. Methods: A prospective, interventional, noncomparative case study. The primary outcome measure was visual acuity. The secondary outcomes were structural assessment, other ocular functional measurements, and developmental state. Results: Eighteen eyes of 13 consecutive patients were divided into 3 groups: Group 1, Stage 4 unresponsive to previous conventional treatment (n = 4); Group 2, in which conventional treatment was difficult or impossible because of inadequate visualization of the retina (n = 5); and Group 3, newly diagnosed high-risk prethreshold or threshold retinopathy of prematurity (n = 9). All patients showed initial regression of neovascularization. One patient was diagnosed with recurrence of neovascularization and was treated with intravitreal bevacizumab. Visual acuity was preserved, and median vision was 20/25 (excluding 2 operated eyes). Twelve eyes developed mainly low myopia over the years, with an overall mean value of 3.2 diopters. Electroretinograph was normal in 4 eyes that had no previous detachment. One patient showed delay in growth and neurodevelopment, whereas all the others were within the normal range. Conclusion: Five years of follow-up in a small series suggest that intravitreal bevacizumab for retinopathy of prematurity results in apparently preserved ocular function and systemic development.
Background: The automated screening of patients at risk of developing diabetic retinopathy represents an opportunity to improve their midterm outcome and lower the public expenditure associated with direct and indirect costs of common sight-threatening complications of diabetes. Objective: This study aimed to develop and evaluate the performance of an automated deep learning–based system to classify retinal fundus images as referable and nonreferable diabetic retinopathy cases, from international and Mexican patients. In particular, we aimed to evaluate the performance of the automated retina image analysis (ARIA) system under an independent scheme (ie, only ARIA screening) and 2 assistive schemes (ie, hybrid ARIA plus ophthalmologist screening), using a web-based platform for remote image analysis to determine and compare the sensibility and specificity of the 3 schemes. Methods: A randomized controlled experiment was performed where 17 ophthalmologists were asked to classify a series of retinal fundus images under 3 different conditions. The conditions were to (1) screen the fundus image by themselves (solo); (2) screen the fundus image after exposure to the retina image classification of the ARIA system (ARIA answer); and (3) screen the fundus image after exposure to the classification of the ARIA system, as well as its level of confidence and an attention map highlighting the most important areas of interest in the image according to the ARIA system (ARIA explanation). The ophthalmologists’ classification in each condition and the result from the ARIA system were compared against a gold standard generated by consulting and aggregating the opinion of 3 retina specialists for each fundus image. Results: The ARIA system was able to classify referable vs nonreferable cases with an area under the receiver operating characteristic curve of 98%, a sensitivity of 95.1%, and a specificity of 91.5% for international patient cases. There was an area under the receiver operating characteristic curve of 98.3%, a sensitivity of 95.2%, and a specificity of 90% for Mexican patient cases. The ARIA system performance was more successful than the average performance of the 17 ophthalmologists enrolled in the study. Additionally, the results suggest that the ARIA system can be useful as an assistive tool, as sensitivity was significantly higher in the experimental condition where ophthalmologists were exposed to the ARIA system’s answer prior to their own classification (93.3%), compared with the sensitivity of the condition where participants assessed the images independently (87.3%; P=.05). Conclusions: These results demonstrate that both independent and assistive use cases of the ARIA system present, for Latin American countries such as Mexico, a substantial opportunity toward expanding the monitoring capacity for the early detection of diabetes-related blindness.
1 February 2004 in American Journal of Ophthalmology
Purpose: To evaluate diabetic retinopathy (DR) prevalence and risk factors, and the effectiveness of nonmydriatic fundus camera as a screening tool for the detection of DR, in a safety net hospital. Methods: This was a retrospective, population-based, cross-sectional study. Diabetic patients, referred by their primary care physicians to a DR community screening program, were included. A Topcon TRC NW-6S camera was used to obtain 45-degree digital color fundus images. Images were interpreted by retina specialists using a quality rating system. Patients with retinal findings or unreadable photographs were referred for a complete examination. Outcome measures were attendance rates, photograph quality, DR prevalence, and associated risk factors. Results: A total of 948 diabetic patients were sent for camera screening, with an attendance rate of 65.6%, which increased during the study period. The mean age was 55.8 ± 11.6 years, the majority (56.9%) were Hispanic, and 43.5% were uninsured. Overall photograph quality rating was relatively high, with 81.7% graded as good or fair. Thirty photographs (2.9%) were unreadable. The prevalence of newly diagnosed DR was 11.1%. Independent DR-associated risk factors included Hispanic race (odds ratio [OR] = 2.29), lack of health insurance (OR = 2.49), longer duration of diabetes (OR = 1.07), higher HbA1c levels (OR = 1.19), presence of diabetic complications (OR = 2.93), and lack of previous eye examination (OR = 13.22). Conclusions: Nonmydriatic fundus camera is an effective and feasible screening tool for the early detection of DR in a safety net institution. It should be considered in areas with limited access to health care to improve quality of care and potentially reduce vision loss rates.