Deep Learning for Vision Screening in Resource-Limited Settings: Development of Multi-Branch CNN for Refractive Error Detection Based on Smartphone Image

Muhammad Syauqie^1,2*Harry Patria³Sutanto Priyo Hastono²Kemal Nazaruddin Siregar²Nila Djuwita Farieda Moeloek⁴

• ¹Faculty of Medicine, Andalas University, Padang, Indonesia
• ²Faculty of Public Health, University of Indonesia, Depok, West Java, Indonesia
• ³Strathclyde Business School, Glasgow, Scotland, United Kingdom
• ⁴Faculty of Medicine, University of Indonesia, Jakarta, Papua, Indonesia

Globally, uncorrected refractive errors are the leading cause of preventable vision impairment, disproportionately affecting individuals in low-resource regions. Despite the availability of economical treatments, challenges in timely diagnosis and screening access persist, particularly in underserved communities. This study introduces a novel deep learning-based system for automated refractive error classification using photorefractive images acquired via a standard smartphone camera. A multi-branch convolutional neural network (CNN) was developed and trained on a dataset of 2,139 corneal images from an Indonesian sample, enabling the model to classify refractive errors into four categories: significant myopia, significant hypermetropia, and insignificant refractive error, and not applicable to classified. The 3-branch CNN architecture demonstrated superior performance, achieving an overall test accuracy of 91%, precision of 96%, and recall of 98%, with an area under the curve (AUC) score of 0.9896. Its multi-scale feature extraction pathways were pivotal in addressing overlapping red reflex patterns and subtle variations between classes. The dataset, collected from a public eye hospital in Indonesia, reflects real-world diversity and strengthens the model's reliability for deployment in resource-limited settings. Grad-CAM visualization provided insights into the model's interpretability, enhancing its clinical applicability. This study establishes the feasibility of smartphone-based photorefractive assessment integrated with artificial intelligence for scalable and cost-effective vision screening. This system offers a reliable solution for early refractive error detection by training the CNN model with data representative of Southeast Asian populations, with significant implications for improving accessibility to eye care services.