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

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

doi:10.1038/s41591-022-02180-9

Cited by 29 publications

(16 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Numerous diseases have the potential to be screened by deep learning using photography or video on smartphones as a diagnostic tool, including melanoma, scoliosis, certain ocular disorders and related systematic diseases 25 – 27 . A previous study showed the potential of cataract screening through anterior segment pictures captured by smartphones 13 . A deep learning screening model for infant vision impairment has recently been developed, allowing parents to detect children’s vision disorders by recording their gazing behaviors through smartphones at home with high accuracy 13 .…”

Section: Discussionmentioning

confidence: 99%

Cost-effectiveness and cost-utility of a digital technology-driven hierarchical healthcare screening pattern in China

Wu,

et al. 2024

Nat Commun

Self Cite

View full text Add to dashboard Cite

Utilization of digital technologies for cataract screening in primary care is a potential solution for addressing the dilemma between the growing aging population and unequally distributed resources. Here, we propose a digital technology-driven hierarchical screening (DH screening) pattern implemented in China to promote the equity and accessibility of healthcare. It consists of home-based mobile artificial intelligence (AI) screening, community-based AI diagnosis, and referral to hospitals. We utilize decision-analytic Markov models to evaluate the cost-effectiveness and cost-utility of different cataract screening strategies (no screening, telescreening, AI screening and DH screening). A simulated cohort of 100,000 individuals from age 50 is built through a total of 30 1-year Markov cycles. The primary outcomes are incremental cost-effectiveness ratio and incremental cost-utility ratio. The results show that DH screening dominates no screening, telescreening and AI screening in urban and rural China. Annual DH screening emerges as the most economically effective strategy with 341 (338 to 344) and 1326 (1312 to 1340) years of blindness avoided compared with telescreening, and 37 (35 to 39) and 140 (131 to 148) years compared with AI screening in urban and rural settings, respectively. The findings remain robust across all sensitivity analyses conducted. Here, we report that DH screening is cost-effective in urban and rural China, and the annual screening proves to be the most cost-effective option, providing an economic rationale for policymakers promoting public eye health in low- and middle-income countries.

show abstract

Section: Discussionmentioning

confidence: 99%

Cost-effectiveness and cost-utility of a digital technology-driven hierarchical healthcare screening pattern in China

Wu,

et al. 2024

Nat Commun

Self Cite

View full text Add to dashboard Cite

show abstract

“…We have created a mHealth system called the Apollo Infant Sight (AIS), which includes an app collecting data and a deep learning (DL) system analyzing the collected data. 9 The DL model was trained with 25 972 800 frames of video from 3652 children to detect visual impairment caused by 16 common eye diseases in children aged ≤48 months. The app guides healthcare professionals, volunteers, parents and caregivers to record videos of children's gaze patterns while watching a cartoon video to ensure steady gaze.…”

Section: Apollo Infant Sightmentioning

confidence: 99%

“…We have created a mHealth system called the Apollo Infant Sight (AIS), which includes an app collecting data and a deep learning (DL) system analyzing the collected data 9 . The DL model was trained with 25 972 800 frames of video from 3652 children to detect visual impairment caused by 16 common eye diseases in children aged ≤48 months.…”

Section: Apollo Infant Sightmentioning

confidence: 99%

mHealth technology identifies visual impairment in young children

Chen

Lin

et al. 2023

Clinical & Translational Med

Self Cite

View full text Add to dashboard Cite

“…Ophthalmic conditions, including glaucoma, cataract, diabetic retinopathy, and ocular neoplasms, are widely spread across the globe and have the potential to cause impaired vision and complete blindness, significantly compromising an individual's quality of life (Burton et al 2021). Timely identification and prompt intervention play a pivotal role in mitigating the consequences of ocular disorders, as early detection and treatment are imperative in averting adverse outcomes associated with these conditions (Chen et al 2023). While mutations in specific genes, such as RB1, ABCA4 (D'angelo et al 2017; Khan et al 2018), myocilin, and CYP1B1 (Rezaei Kanavi et al 2022) have been linked to the development and progression of some ocular diseases, recent studies have highlighted the potential role of epigenetics, including non‐coding RNAs (ncRNAs), in these conditions (Wang 2023).…”

Section: Introductionmentioning

confidence: 99%

Potential roles of lncRNA MALAT1-miRNA interactions in ocular diseases

Nasrolahi,

Khojasteh Pour,

Mousavi Salehi

et al. 2023

J. Cell Commun. Signal.

View full text Add to dashboard Cite

Long non-coding RNAs (lncRNAs) are non-protein coding transcripts that are longer than 200 nucleotides in length. LncRNAs are implicated in gene expression at the transcriptional, translational, and epigenetic levels, and thereby impact different cellular processes including cell proliferation, migration, apoptosis, angiogenesis, and immune response. In recent years, numerous studies have demonstrated the significant contribution of lncRNAs to the pathogenesis and progression of various diseases, such as stroke, heart disease, and cancer. Further investigations have shown that lncRNAs have altered expression patterns in ocular tissues and cell lines during pathological conditions. The pathogenesis of various ocular diseases, including glaucoma, cataract, corneal diseases, proliferative vitreoretinopathy, diabetic retinopathy, and retinoblastoma, is influenced by the involvement of specific lncRNAs which play a critical role in the development and progression of these diseases. Metastasis-associated lung adenocarcinoma transcript 1 (MALAT1) is a well-researched lncRNA in the context of ocular diseases, which has been shown to exert its biological effects through several signaling pathways and downstream targets. The present review provides a comprehensive summary of the molecular mechanisms underlying the biological functions and roles of MALAT1 in ocular diseases.

show abstract

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

Cited by 29 publications

References 44 publications

Cost-effectiveness and cost-utility of a digital technology-driven hierarchical healthcare screening pattern in China

Cost-effectiveness and cost-utility of a digital technology-driven hierarchical healthcare screening pattern in China

mHealth technology identifies visual impairment in young children

Potential roles of lncRNA MALAT1-miRNA interactions in ocular diseases

Contact Info

Product

Resources

About