Deep Learning–Based Prediction of Refractive Error Using Photorefraction Images Captured by a Smartphone: Model Development and Validation Study

Abstract

Background Accurately predicting refractive error in children is crucial for detecting amblyopia, which can lead to permanent visual impairment, but is potentially curable if detected early. Various tools have been adopted to more easily screen a large number of patients for amblyopia risk. Objective For efficient screening, easy access to screening tools and an accurate prediction algorithm are the most important factors. In this study, we developed an automated deep learning–based system to predict the range of refractive error in children (mean age 4.32 years, SD 1.87 years) using 305 eccentric photorefraction images captured with a smartphone. Methods Photorefraction images were divided into seven classes according to their spherical values as measured by cycloplegic refraction. Results The trained deep learning model had an overall accuracy of 81.6%, with the following accuracies for each refractive error class: 80.0% for ≤−5.0 diopters (D), 77.8% for >−5.0 D and ≤−3.0 D, 82.0% for >−3.0 D and ≤−0.5 D, 83.3% for >−0.5 D and <+0.5 D, 82.8% for ≥+0.5 D and <+3.0 D, 79.3% for ≥+3.0 D and <+5.0 D, and 75.0% for ≥+5.0 D. These results indicate that our deep learning–based system performed sufficiently accurately. Conclusions This study demonstrated the potential of precise smartphone-based prediction systems for refractive error using deep learning and further yielded a robust collection of pediatric photorefraction images.

Deep Learning for Classification of Pediatric Otitis Media

“…Recently, AI diagnosis systems have been explored with CNNs using smartphone images such as skin cancer, 11 refractive error, 23 as well as middle ear diseases. Moshtaghi et al 24 have reported 100% sensitivity in abnormal TM detection using smartphone‐enabled otoscopes and developed a model to achieve the overall accuracy of 98.7% for the TM side and 91% for the perforation.…”

Deep Learning-Based Estimation of Axial Length and Subfoveal Choroidal Thickness From Color Fundus Photographs

“…Deep learning, known as a subset of artificial intelligence, allows computational systems to learn representations directly from a large number of images without designing explicit hand-crafted features (LeCun et al, 2015). The applications of deep-learning techniques trained on color fundus images have produced systems with competitive or close-to-expert performance for an automatic detection of ophthalmic diseases, including diabetic retinopathy (Cao et al, 2020;Gargeya and Leng, 2017;Ting et al, 2017), age-related macular degeneration (Burlina et al, 2017;Grassmann et al, 2018;González-Gonzalo et al, 2020), retinopathy of prematurity (Wang et al, 2018;Mao et al, 2020), glaucoma (Hemelings et al, 2020), and other disorders (Shah et al, 2020); assessment of ocular and systemic risk factors such as age, gender, body mass index, and blood pressure; estimation of the refractive error (Poplin et al, 2018;Varadarajan et al, 2018;Chun et al, 2020).…”

Prediction of Subjective Refraction From Anterior Corneal Surface, Eye Lengths, and Age Using Machine Learning Algorithms

“…This procedure takes time and, consequently, slows down the diagnosis process. To reduce the time needed for this process, machine learning has been recently used to predict refractive prescription from physical eye data obtained by wavefront aberrometers, 19 , 20 photorefraction images, 21 retinal fundus images, 22 other ophthalmologic devices, 23 and intraocular lenses characteristics. 24 The aim of this work is to develop a machine learning regression model that predicts patients’ subjective refractive prescription from the anterior corneal surface and ocular biometry.…”