首页 / 院系成果 / 成果详情页

A deep learning system for myopia onset prediction and intervention effectiveness evaluation in children  期刊论文  

  • 编号：
    451DBC71F9811B3462D97298A608A968
  • 作者：
    Qi, Ziyi#[1,2,3]Li, Tingyao#[4,5]Chen, Jun#[1,2]Yam, Jason C.#[6]Wen, Yang(温阳)#[7]Huang, Gengyou[4,5];Zhong, Hua(钟华)[8]He, Mingguang(何明光)[9,10]Zhu, Dan(朱丹)[11]Dai, Rongping(戴荣平)[12]Qian, Bo[4,5];Wang, Jingjing[1,2,10];Qian, Chaoxu[8];Wang, Wei;Zheng, Yanfei[11];Zhang, Jian[13];Yi, Xianglong(易湘龙)[14]Wang, Zheyuan[4,5];Zhang, Bo[1];Liu, Chunyu[4,5];Cheng, Tianyu[3];Yang, Xiaokang(杨小康)[5]Li, Jun[15];Pan, YanTing[15];Ding, Xiaohu(丁小虎)[10]Xiong, Ruilin[10];Wang, Yan[11];Zhou, Yan[12];Feng, Dagan(冯大淦)[16]Liu, Sichen[1,2];Du, Linlin[1,2];Yang, Jinliuxing[1,2];Zhu, Zhuoting(朱卓婷)[17]Bi, Lei[18];Kim, Jinman[16];Tang, Fangyao[6];Zhang, Yuzhou[6];Zhang, Xiujuan[6]Zou, Haidong(邹海东)[1,2]Ang, Marcus[19,20];Tham, Clement C.[6]Cheung, Carol Y.(张艳蕾)[6]Pang, Chi Pui(彭智培)*[6]Sheng, Bin(盛斌)*[4,5]He, Xiangui(何鲜桂)*[1,2,3]Xu, Xun(许迅)*[1,2,3]
  • 语种：
    英文
  • 期刊：
    NPJ DIGITAL MEDICINE ISSN：2398-6352 2024 年 7 卷 1 期 ; AUG 7
  • 收录：
     
  • 摘要：

    The increasing prevalence of myopia worldwide presents a significant public health challenge. A key strategy to combat myopia is with early detection and prediction in children as such examination allows for effective intervention using readily accessible imaging technique. To this end, we introduced DeepMyopia, an artificial intelligence (AI)-enabled decision support system to detect and predict myopia onset and facilitate targeted interventions for children at risk using routine retinal fundus images. Based on deep learning architecture, DeepMyopia had been trained and internally validated on a large cohort of retinal fundus images (n = 1,638,315) and then externally tested on datasets from seven sites in China (n = 22,060). Our results demonstrated robustness of DeepMyopia, with AUCs of 0.908, 0.813, and 0.810 for 1-, 2-, and 3-year myopia onset prediction with the internal test set, and AUCs of 0.796, 0.808, and 0.767 with the external test set. DeepMyopia also effectively stratified children into low- and high-risk groups (p < 0.001) in both test sets. In an emulated randomized controlled trial (eRCT) on the Shanghai outdoor cohort (n = 3303) where DeepMyopia showed effectiveness in myopia prevention compared to NonCyc-based model, with an adjusted relative reduction (ARR) of -17.8%, 95% CI: -29.4%, -6.4%. DeepMyopia-assisted interventions attained quality-adjusted life years (QALYs) of 0.75 (95% CI: 0.53, 1.04) per person and avoided blindness years of 13.54 (95% CI: 9.57, 18.83) per 1 million persons compared to natural lifestyle with no active intervention. Our findings demonstrated DeepMyopia as a reliable and efficient AI-based decision support system for intervention guidance for children.

  • 推荐引用方式
    GB/T 7714：
    Qi Ziyi,Li Tingyao,Chen Jun, et al. A deep learning system for myopia onset prediction and intervention effectiveness evaluation in children [J].NPJ DIGITAL MEDICINE,2024,7(1).
  • APA：
    Qi Ziyi,Li Tingyao,Chen Jun,Yam Jason C.,&Xu Xun.(2024).A deep learning system for myopia onset prediction and intervention effectiveness evaluation in children .NPJ DIGITAL MEDICINE,7(1).
  • MLA：
    Qi Ziyi, et al. "A deep learning system for myopia onset prediction and intervention effectiveness evaluation in children" .NPJ DIGITAL MEDICINE 7,1(2024).
  • 入库时间：
    2024/10/31 9:58:17
  • 更新时间：
    2024/10/31 9:58:17
  • 条目包含文件：
    文件类型：PDF,文件大小：
    正在加载全文
浏览次数：28 下载次数：0
分享到：
浏览次数：28
下载次数：0
打印次数：0

网站总浏览量： 次   

Copyright © 昆明医科大学

技术支持：北京同舟云网络信息技术有限公司

浏览器支持: Google Chrome   火狐   360浏览器极速模式(8.0+极速模式) 
返回顶部