Early detection of visual impairment in young children using a smartphone-based deep learning system

Wenben Chen, Ruiyang Li, Qinji Yu, Andi Xu, Yile Feng, Ruixin Wang, Lanqin Zhao, Zhenzhe Lin, Yahan Yang, Duoru Lin, Xiaohang Wu, Jingjing Chen, Zhenzhen Liu, Yuxuan Wu, Kang Dang, Kexin Qiu, Zilong Wang, Ziheng Zhou, Dong Liu, Qianni WuMingyuan Li, Yifan Xiang, Xiaoyan Li, Zhuoling Lin, Danqi Zeng, Yunjian Huang, Silang Mo, Xiucheng Huang, Shulin Sun, Jianmin Hu, Jun Zhao, Meirong Wei, Shoulong Hu, Liang Chen, Bingfa Dai, Huasheng Yang, Danping Huang, Xiaoming Lin, Lingyi Liang, Xiaoyan Ding, Yangfan Yang, Pengsen Wu, Feihui Zheng, Nick Stanojcic, Ji Peng Olivia Li, Carol Y. Cheung, Erping Long, Chuan Chen, Yi Zhu, Patrick Yu-Wai-Man, Ruixuan Wang, Wei shi Zheng, Xiaowei Ding*, Haotian Lin*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

13 Citations (Scopus)


Early detection of visual impairment is crucial but is frequently missed in young children, who are capable of only limited cooperation with standard vision tests. Although certain features of visually impaired children, such as facial appearance and ocular movements, can assist ophthalmic practice, applying these features to real-world screening remains challenging. Here, we present a mobile health (mHealth) system, the smartphone-based Apollo Infant Sight (AIS), which identifies visually impaired children with any of 16 ophthalmic disorders by recording and analyzing their gazing behaviors and facial features under visual stimuli. Videos from 3,652 children (≤48 months in age; 54.5% boys) were prospectively collected to develop and validate this system. For detecting visual impairment, AIS achieved an area under the receiver operating curve (AUC) of 0.940 in an internal validation set and an AUC of 0.843 in an external validation set collected in multiple ophthalmology clinics across China. In a further test of AIS for at-home implementation by untrained parents or caregivers using their smartphones, the system was able to adapt to different testing conditions and achieved an AUC of 0.859. This mHealth system has the potential to be used by healthcare professionals, parents and caregivers for identifying young children with visual impairment across a wide range of ophthalmic disorders.

Original languageEnglish
Pages (from-to)493-503
Number of pages11
JournalNature Medicine
Issue number2
Publication statusPublished - Feb 2023
Externally publishedYes


Dive into the research topics of 'Early detection of visual impairment in young children using a smartphone-based deep learning system'. Together they form a unique fingerprint.

Cite this