A study in China showed artificial intelligence (AI) can accurately identify myopia, strabismus and ptosis in children aged six to 12 years old from smartphone images.
Writing in JAMA Network Open, researchers led by Dr Qin Shu, Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology and Shanghai Ninth People’s Hospital, used 1,419 facial photographs from 476 individuals. The images were taken in-clinic using a smartphone under controlled lighting and at a distance of 4.2cm from the subject. These images were uploaded into the ConvNeXt deep-learning network, which detected myopia, strabismus, and ptosis with accuracies of 0.80 (95% CI, 0.78-0.81), 0.80 (95% CI, 0.79-0.82), and 0.92 (95% CI, 0.91-0.93), respectively.
These results suggest AI and smartphones can assist families in screening children for myopia, strabismus and ptosis, reducing the risk of visual function loss and severe problems due to delayed screening, said researchers. “Moreover, using such information can help achieve a more equitable allocation of limited medical resources. This is critical to the advancement of global health standards.”
