Evaluation of a Free Public Smartphone Application to Detect Leukocoria in High-Risk Children Aged 1 to 6 Years

Purpose: To determine whether a white-eye detector smartphone application (app) can be used as a screening tool to detect early signs of leukocoria in a clinical practice.Methods: A prospective, single-visit study of children aged 1 to 6 years presenting to the University Eye Clinic of Genova for a complete pediatric ophthalmologic examination was conducted. All children who met the enrollment criteria were screened by an orthoptist with the CRADLE (Computer Assisted Detector of Leukocoria) smartphone app for an iPhone operating system (iOS) (iPhone 7; Apple, Cupertino, CA). Cycloplegic retinoscopy and fundus examination were performed 30 minutes after one to two drops of a pediatric combination drop, comprising tropicamide 1% and phenylephrine 2.5%, were instilled. A comparison between the two methods yielded sensitivity, specificity, and negative likelihood ratio values.Results: A total of 244 eyes of 122 children were included in the study. Nine eyes of 244 (3.6%) had leukocoria evaluable by penlight caused by amblyogenic cataract, 1 (0.4%) patient had retinopathy of prematurity stage 5, and 3 (1.2%) patients had retinoblastoma. The sensitivity of the white-eye detector app was 15.38% (95% confidence interval [CI]: 1.92% to 45.45%), the specificity was 100% (95% CI: 98.48% to 100.00%), and the negative likelihood ratio was 0.85 (95% CI: 0.67 to 1.07).Conclusions: A smartphone photoscreening app able to detect leukocoria may provide valuable support for children's parents. However, it cannot be considered an alternative to the ophthalmoscope for children.