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

Chen, Wenben1; Li, Ruiyang1; Yu, Qinji2; Xu, Andi1; Feng, Yile3; Wang, Ruixin1; Zhao, Lanqin1; Lin, Zhenzhe1; Yang, Yahan1; Lin, Duoru1; Wu, Xiaohang1; Chen, Jingjing1; Liu, Zhenzhen1; Wu, Yuxuan1; Dang, Kang3; Qiu, Kexin3; Wang, Zilong3; Zhou, Ziheng3; Liu, Dong1; Wu, Qianni1; Li, Mingyuan1; Xiang, Yifan1; Li, Xiaoyan1; Lin, Zhuoling1; Zeng, Danqi1; Huang, Yunjian1; Mo, Silang4; Huang, Xiucheng4; Sun, Shulin5; Hu, Jianmin6; Zhao, Jun7,8; Wei, Meirong9; Hu, Shoulong10,11; Chen, Liang12; Dai, Bingfa6; Yang, Huasheng1; Huang, Danping1; Lin, Xiaoming1; Liang, Lingyi1; Ding, Xiaoyan1; Yang, Yangfan1; Wu, Pengsen1; Zheng, Feihui13; Stanojcic, Nick14; Li, Ji-Peng Olivia15; Cheung, Carol Y.16; Long, Erping1; Chen, Chuan17; Zhu, Yi18; Yu-Wai-Man, Patrick19,20; Wang, Ruixuan; Zheng, Wei-shi; Ding, Xiaowei2,3; Lin, Haotian1

2023

10.1038/s41591-022-02180-9

NATURE MEDICINE   影响因子和分区

1078-8956

1546-170X

["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.","A smartphone-based system, designed to induce a steady gaze in children using cartoon-like video stimuli, can identify visually impaired children across a wide range of ophthalmic disorders, based on analysis of gazing behaviors and facial features."]

SCI

英语

NI论文

其他

National Natural Science Foundation of China["82171035","91846109"] ; Science and Technology Planning Projects of Guangdong Province[2021B1111610006] ; Key-Area Research and Development of Guangdong Province[2020B1111190001] ; Guangzhou Basic and Applied Basic Research Project[2022020328] ; China Postdoctoral Science Foundation[2022M713589] ; Fundamental Research Funds of the State Key Laboratory of Ophthalmology[2022QN10] ; Hainan Province Clinical Medical Center[NIHR301696] ; Moorfields Eye Charity[GR001376] ; NIHR Cambridge Biomedical Research Centre[BRC-1215-20014]

Biochemistry & Molecular Biology ; Cell Biology ; Research & Experimental Medicine

Biochemistry & Molecular Biology ; Cell Biology ; Medicine, Research & Experimental

WOS:000920964700001

NATURE PORTFOLIO

MOLECULAR BIOLOGY & GENETICS

Web of Science

1.Sun Yat Sen Univ, Zhongshan Ophthalm Ctr, Guangdong Prov Clin Res Ctr Ocular Dis, State Key Lab Ophthalmol,Guangdong Prov Key Lab Op, Guangzhou, Peoples R China
2.Shanghai Jiao Tong Univ, Inst Image Commun & Network Engn, Shanghai, Peoples R China
3.VoxelCloud, Shanghai, Peoples R China
4.Sun Yat Sen Univ, Sch Med, Shenzhen, Peoples R China
5.Peking Univ Third Hosp, Hlth Sci Ctr, Dept Urol, Beijing, Peoples R China
6.Fujian Med Univ, Affiliated Hosp 2, Dept Ophthalmol, Quanzhou, Peoples R China
7.Jinan Univ, Shenzhen Peoples Hosp, Clin Med Coll 2, Shenzhen, Peoples R China
8.Southern Univ Sci & Technol, Affiliated Hosp 1, Shenzhen, Peoples R China
9.Guangxi Univ Sci & Technol, Liuzhou Matern & Child Healthcare Hosp, Affiliated Women & Childrens Hosp, Liuzhou, Peoples R China
10.Capital Med Univ, Beijing Childrens Hosp, Natl Ctr Childrens Hlth, Dept Ophthalmol, Beijing, Peoples R China
11.Zhengzhou Childrens Hosp, Dept Ophthalmol, Dept Clin Neurosci, Mitochondrial Biol Unit, Cambridge, Peoples R China
12.Sun Yat Sen Univ, Sch Comp Sci & Engn, Shenzhen Eye Inst, Guangzhou, Peoples R China
13.Sun Yat Sen Univ, Hainan Eye Hosp, Natl Ctr Childrens Hlth, Dept Ophthalmol, Haikou, Peoples R China
14.Sun Yat Sen Univ, Dept Ophthalmol, Key Lab Ophthalmol, London, England
15.Sun Yat Sen Univ, Ctr Precis Med, Zhongshan Sch Med, London, England
16.Chinese Univ Hong Kong, Fac Med, Dept Ophthalmol & Visual Sci, Hong Kong, Peoples R China
17.Univ Miami, Sylvester Comprehens Canc Ctr, Miller Sch Med, Miami, FL USA
18.Univ Miami, Dept Mol & Cellular Pharmacol, Miller Sch Med, Miami, FL USA
19.UCL, Univ Coll London Inst Ophthalmol, London, England
20.Cambridge Univ Hosp, Addenbrookes Hosp, Cambridge Eye Unit, Cambridge, England

Chen, Wenben,Li, Ruiyang,Yu, Qinji,et al. Early detection of visual impairment in young children using a smartphone-based deep learning system[J]. NATURE MEDICINE,2023.

Chen, Wenben.,Li, Ruiyang.,Yu, Qinji.,Xu, Andi.,Feng, Yile.,...&Lin, Haotian.(2023).Early detection of visual impairment in young children using a smartphone-based deep learning system.NATURE MEDICINE.

Chen, Wenben,et al."Early detection of visual impairment in young children using a smartphone-based deep learning system".NATURE MEDICINE (2023).