Limitations in cataract surgical services for children in Ethiopia: a nationwide survey of pediatric cataract surgeons.

BACKGROUND: Bilateral cataract is a significant cause of blindness in children in Ethiopia. This study aimed to identify the resources available for cataract surgery in children, and to assess current surgical practices, surgical output and factors affecting the outcome of surgery in Ethiopia. METHODS: A Google Forms mobile phone questionnaire was emailed to nine ophthalmologists known to perform cataract surgery in young children (0-5 years). RESULTS: All nine responded. All but one had received either 12- or 3-5-month's training in pediatric ophthalmology with hands-on surgical training. The other surgeon had received informal training from an experienced colleague and visiting ophthalmologists. The surgeons were based in seven health facilities: five in the capital (Addis Ababa) and eight in six public referral hospitals and one private center. Over 12 months (2017-2018) 508 children (592 eyes) aged 0-18 years (most < 15 years) were operated by these surgeons. 84 (17%) had bilateral cataract, and 424 (83%) had unilateral cataract mainly following trauma. A mean of 66 (range 18-145) eyes were operated per surgeon. Seventy-one additional children aged > 5 years were operated by other surgeons. There were substantially fewer surgeons per million population (nine for 115 million population) than recommended by the World Health Organization and they were unevenly distributed across the country. Methylcellulose and rigid intraocular lenses were generally available but less than 50% of facilities had a sharp vitrectomy cutter and cohesive viscoelastic. Mean travel time outside Addis Ababa to a facility offering pediatric cataract surgery was 10 h. CONCLUSION: Despite the high number of cases per surgeon, the output for bilateral cataracts was far lower than required. More well-equipped pediatric ophthalmology teams are urgently required, with deployment to under-served areas.

EyeScreen: Development and Potential of a Novel Machine Learning Application to Detect Leukocoria.

Purpose: Early diagnosis and treatment of retinoblastoma are of paramount importance for a positive clinical outcome. The most common sign of retinoblastoma is leukocoria, or white pupil. Effective, easy-to-perform, community-based screening is needed to improve outcomes in lower-income regions. The EyeScreen (developed by Joshua Meyer from the University of Michigan) Android (Google LLC) smartphone application is an important step toward addressing this need. The purpose of this study was to examine the potential of the novel use of low-cost technologies-a cell phone application and machine learning-to identify leukocoria. Design: A cell phone application was developed and refined with the feedback from on-site, single-population use in Ethiopia. Application performance was evaluated in this technology validation study. Participants: One thousand four hundred fifty-seven participants were recruited from ophthalmology and pediatric clinics in Addis Ababa, Ethiopia. Methods: Photographs obtained with inexpensive Android smartphones running the EyeScreen Application were used to train an ImageNet (ResNet) machine learning model and to measure the performance of the app. Eighty percent of the images were used in training the model, and 20% were reserved for testing. Main Outcome Measures: Performance of the model was measured in terms of sensitivity, specificity, receiver operating characteristic (ROC) curve, and precision-recall curve. Results: Analyses of the participant images resulted in the following at the participant level: sensitivity, 87%; specificity, 73%; area under the ROC curve, 0.93; and area under the precision-recall curve, 0.77. Conclusions: EyeScreen has the potential to serve as an effective screening tool in the areas of the world most affected by delayed retinoblastoma diagnosis. The relatively high initial performance of the machine learning model with small training datasets in this early-phase study can serve as a proof of concept for future use of machine learning and artificial intelligence in ophthalmic applications.