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.

Health Equity and Disparities in ROP Care: A Need for Systematic Evaluation.

Retinopathy of prematurity (ROP) is a vasoproliferative retinal disorder that can have devastating visual sequelae if not managed appropriately. From an ophthalmology standpoint, ROP care is complex, since it spans multiple care settings and providers, including those in the neonatal intensive care unit (NICU), step down nurseries, and the outpatient clinic setting. This requires coordination and communication between providers, ancillary staff, and most importantly, effective communication with the patient's family members and caregivers. Often, factors related to the social determinants of health play a significant role in effective communication and care coordination with the family, and it is important for ophthalmologists to recognize these risk factors. The aim of this article is to (1) review the literature related to disparities in preterm birth outcomes and infants at risk for ROP; (2) identify barriers to ROP care and appropriate follow up, and (3) describe patient-oriented solutions and future directions for improving ROP care through a health equity lens.

The Association of Cognitive and Visual Function in a Nationally Representative Study of Older Adults in India.

INTRODUCTION: Due to population aging, India is poised to experience a large increase in the burden of both dementia and vision impairment (VI). Prior studies from other settings suggest that VI may be a modifiable risk factor for cognitive decline and dementia. However, to date, no studies have examined the association of impaired visual acuity and cognition in India. METHODS: A total of 3,784 participants in wave 1 of the population-based Diagnostic Assessment of Dementia for the Longitudinal Aging Study in India underwent visual acuity testing and a cognitive test battery. Multivariable linear regression was used to model the cross-sectional associations of mild (<6/12-6/16), moderate (<6/18-6/60), and severe visual acuity impairment/blindness (<6/60) with cognitive performance scores corresponding to total cognition, orientation, memory, language/fluency, executive function, and informant-reported cognitive status. Models were adjusted for demographic, socioeconomic, and health characteristics. RESULTS: The weighted percentage of participants with any VI was 52.6%. VI was independently associated with lower cognitive scores across all domains, even after adjustment for known dementia risk factors. In fully adjusted models of total cognition (mean score: 130.7), mild, moderate, and severe VI/blindness were associated with a significant change of -3.5 (95% CI: -6.3, -0.6), -8.2 (95% CI -10.5, -5.6), and -16.8 (95% CI -22.3, -11.3) units, respectively. A dose-response association between level of VI and cognitive function was observed for all cognitive outcomes except for language/fluency domain scores. Associations were robust when cognitive tests dependent on visual function were excluded. Across each fully adjusted model of total, domain-specific, and informant-reported cognitive performance, moderate VI was equivalent to 5-9 years of cognitive aging. DISCUSSION/CONCLUSION: This study illustrates that VI is cross-sectionally associated with lower cognitive performance, largely in a dose-response pattern, across various cognitive domains in the Indian population. These findings are important for informing future longitudinal and interventional studies.

Self-reported Eye Care Use Among US Adults Aged 50 to 80 Years.

IMPORTANCE: Contemporary data on use of eye care by US adults are critical, as the prevalence of age-related eye disease and vision impairment are projected to increase in the coming decades. OBJECTIVES: To provide nationally representative estimates on self-reported use of eye care by adults aged 50 to 80 years, and to describe the reasons that adults do and do not seek eye care. DESIGN, SETTING, AND PARTICIPANTS: The National Poll on Healthy Aging, a cross-sectional, nationally representative online survey was conducted from March 9 to 24, 2018, among 2013 individuals aged 50 to 80 years. MAIN OUTCOMES AND MEASURES: The proportion of US adults who received an eye examination within the past 2 years as well as the sociodemographic and economic factors associated with receipt of eye care. RESULTS: Among 2013 adults aged 50 to 80 years (survey-weighted proportion of women, 52.5%; white non-Hispanic, 71.1%; mean [SD] age, 62.1 [9.0] years), the proportion reporting that they underwent an eye examination in the past year was 58.5% (95% CI, 56.1%-60.8%) and in the past 2 years was 82.4% (95% CI, 80.4%-84.2%). Among those with diabetes, 72.2% (95% CI, 67.2%-76.8%) reported undergoing an eye examination in the past year and 91.3% (95% CI, 87.7%-93.9%) in the past 2 years. The odds of having undergone an eye examination within the past 2 years were higher among women (adjusted odds ratio [AOR], 2.00; 95% CI, 1.50-2.67), respondents with household incomes of $30 000 or more (AOR, 1.57; 95% CI, 1.08-2.29), and those with a diagnosed age-related eye disease (AOR, 3.67; 95% CI, 2.37-5.69) or diabetes (AOR, 2.30; 95% CI, 1.50-3.54). The odds were lower for respondents who were unmarried (AOR, 0.71; 95% CI, 0.53-0.96), from the Midwest (AOR, 0.55; 95% CI, 0.34-0.87) or West (AOR, 0.60; 95% CI, 0.38-0.94), or reported fair or poor vision (AOR, 0.43; 95% CI, 0.28-0.65). Reasons reported for not undergoing a recent eye examination included having no perceived problems with their eyes or vision (41.5%), cost (24.9%), or lack of insurance coverage (23.4%). CONCLUSIONS AND RELEVANCE: In this study, the rate of eye examinations was generally high among US adults aged 50 to 80 years, yet there were several significant demographic and socioeconomic differences in the use of eye care. These findings may be relevant to health policy efforts to address disparities in eye care and to promote care for those most at risk for vision problems.