Smartphone applications for early screening of retinoblastoma: a scoping review
摘要
Retinoblastoma is the most common intraocular malignancy in childhood, typically presenting before five years of age. Early detection is essential in improving survival and visual outcomes. However, delayed diagnosis remains a significant challenge globally, often resulting in advanced disease at presentation and the need for enucleation. Smartphone-based applications have recently been explored as potential tools for screening leukocoria, an early clinical sign of retinoblastoma. This scoping review aims to identify existing smartphone applications used for the early screening of retinoblastoma.
MethodsThis review was conducted in accordance with the Preferred Reporting Items for Systematic Review and Meta-Analysis Extension for Scoping Reviews (PRISMA-ScR) guidelines. Searches of PubMed and Scopus yielded 647 records, and one additional record was identified through manual searching. Following screening and eligibility assessment, 19 full-text articles were selected for review. In total, seven studies met the inclusion criteria and were included in the final synthesis.
ResultsFive smartphone applications for retinoblastoma screening were identified: ComputeR-Assisted Detector of LEukocoria (CRADLE), MDEyeCare, Apollo Infant Sight (AIS), Retino, and EyeScreen. Study designs, target populations, screening methods, and outcome measures varied across studies. Overall, the findings highlighted themes related to usability, accessibility, and feasibility for screening, while also demonstrating variable diagnostic performance and limitations, including small sample sizes and heterogeneous study quality.
ConclusionSmartphone applications may assist in the early identification of signs suggestive of retinoblastoma; however, further high-quality studies are required to establish their reliability, clinical validity, and practical utility in real-world settings.