Advances and prospects in the application of artificial intelligence vision screening in the prevention and control of myopia

doi:10.3877/cma.j.issn.2095-2007.2023.01.012

Abstract

Abstract:

In recent years, the prevalence of myopia in children and adolescents has continued to rise in China. School-based vision screening has been the key work of myopia prevention and control. Artificial intelligence (AI) technology is bringing a great shift in healthcare. The application of AI has been expandingto ophthalmology, with the rapid progress of AI technology, including mass refraction and prediction of myopia. The current status of AI applications in screening and prediction of myopia was introduced and the current deficiencies of AI and hurdles for real-life deployment of AI and the application prospects of it were reviewed.

Key words: Artificial intelligence, Myopia, Vision screening, Prevention and control

Chenxi Zong, Lin Xiao, Hongxin Song. Advances and prospects in the application of artificial intelligence vision screening in the prevention and control of myopia[J]. Chinese Journal of Ophthalmologic Medicine(Electronic Edition), 2023, 13(01): 60-64.

/ / Recommend

Add to citation manager EndNote|Ris|BibTeX

URL: https://zhykyxzz.cma-cmc.com.cn/EN/10.3877/cma.j.issn.2095-2007.2023.01.012

https://zhykyxzz.cma-cmc.com.cn/EN/Y2023/V13/I01/60

Figures/Tables 1

References 57

[47]	Obermeyer Z, Emanuel EJ. Predicting the Future－Big Data, Machine Learning, and Clinical Medicine[J]. N Engl J Med, 2016, 375(13): 1216－1219.
[48]	Dutt S, Sivaraman A, Savoy F, et al. Insights into the growing popularity of artificial intelligence in ophthalmology[J]. Indian J Ophthalmol, 2020, 68(7): 1339－1346.
[49]	Foo LL, Ang M, Wong CW, et al. Is artificial intelligence a solution to the myopia pandemic？[J]. Br J Ophthalmol, 2021, 105(6): 741－744.
[50]	Yang X, Chen G, Qian Y, et al. Prediction of Myopia in Adolescents through Machine Learning Methods[J]. Int J Environ Res Public Health, 2020, 17(2)：463.
[51]	唐涛，范玉琢，徐琼，等. 机器学习对青少年近视眼轴增长与近视度数增加关联性的预测作用[J]. 中华实验眼科杂志，2020，38(2)：134－139.
[52]	王妍茜，王成虎，张竞月，等. 人工智能应用于眼科的积极作用及其伦理问题[J]. 国际眼科杂志，2022，22(6)：1020－1024.
[53]	Esmaeilzadeh P, Mirzaei T, Dharanikota S. Patients' Perceptions Toward Human－Artificial Intelligence Interaction in Health Care: Experimental Study[J]. J Med Internet Res, 2021, 23(11): e25856.
[54]	周楠，魏文斌. 大数据背景下的医学研究模式及其在眼科的应用[J]. 中华实验眼科杂志，2019，37(12)：1024－1028.
[55]	Ting DSW, Pasquale LR, Peng L, et al. Artificial intelligence and deep learning in ophthalmology[J]. Br J Ophthalmol, 2019, 103(2): 167－175.
[56]	林浩添，刘奕志. 我国眼科电子病历系统的专科功能要求及展望[J]. 中华眼科杂志，2014，50(6)：456－458.
[57]	Wu PC, Huang HM, Yu HJ, et al. Epidemiology of Myopia[J]. Asia Pac J Ophthalmol (Phila), 2016, 5(6): 386－393.
[1]	魏文斌，董力. 病理性近视是近视防控的重点和难点[J]. 安徽医科大学学报，2022，57(2)：169－172.
[2]	Ikuno Y. Overview of the complications of high myopia[J]. Retina, 2017, 37(12): 2347－2351.
[3]	徐捷，徐亮. 近视防控的六维度评估及防控模式[J]. 中华眼视光学与视觉科学杂志，2018，20(3)：129－132.
[4]	Flitcroft DI, He M, Jonas JB, et al. IMI－Defining and Classifying Myopia: A Proposed Set of Standards for Clinical and Epidemiologic Studies[J]. Invest Ophthalmol Vis Sci, 2019, 60(3): M20－M30.
[5]	姚瑶，陈伟伟，付晶，等. Lea Symbols电子视力表与灯箱视力表在儿童视力检查中的对比研究[J]. 中国斜视与小儿眼科杂志，2022，30(1)：11－14，37.
[6]	娄斌，陈志钧，刘虎. 新版美国眼科学会《儿童眼评估临床指南》解读[J]. 中国斜视与小儿眼科杂志，2019，27(3)：37－38，34.
[7]	王春波，梁景斌，王海涛，等. 2847名2~6岁儿童主观、客观视力筛查结果分析[J]. 中国妇幼保健，2007，22(21)：2947－2948.
[8]	Salcido AAV, Bradley J, Donahue SP. Predictive value of photoscreening and traditional screening of preschool children[J]. JAAPOS, 2005, 9(2): 114－120.
[9]	李影，廖娅，刘一如，等. Spot双目视力筛查仪和自动电脑验光仪在近视筛查中结果的比较[J]. 中华眼视光学与视觉科学杂志，2021，23(1)：54－58.
[10]	刘国仿，边德换. 手持式视力筛查仪和自动电脑验光仪在青少年屈光检查中的应用[J]. 中国医疗器械信息，2022，28(5)：114－116.
[11]	Zhang X, Wang J, Li Y, et al. Diagnostic test accuracy of Spot and Plusoptix photoscreeners in detecting amblyogenic risk factors in children: a systemic review and meta－analysis[J]. Ophthalmic Physiol Opt, 2019, 39(4): 260－271.
[12]	马瑀涵，王路，夏志伟，等. 北京市学生标化与非标化近视检出率比较[J]. 中国学校卫生，2021，42(2)：195－197，202.
[13]	唐敏华，赵根明，姜永根，等. 上海市松江区2036名儿童青少年视力健康现状及其影响因素分析[J]．中国儿童保健杂志，2022，30(3)：319－324.
[14]	郑冬冬，蒋丹丹，杨汉喜，等. 温州市一至三年级小学生近视及矫正现况[J]. 中国学校卫生，2016，37(3)：459－461.
[15]	许馨文，周巧玲，梁艳哲，等. 甘肃省儿童青少年近视筛查现况分析[J]. 中国初级卫生保健，2022，36(2)：92－94.
[16]	唐文婷，李佳倩，李世贝，等. 2018~2020年成都市新都区小学生近视流行病学研究[J]. 国际眼科杂志，2022，22(1)：148－152.
[17]	Collins ME, Guo X, Repka MX, et al. Lessons Learned From School－Based Delivery of Vision Care in Baltimore, Maryland[J]. Asia－Pac J Ophthalmol, 2022, 11(1): 6－11.
[18]	Seet B, Wong TY, Tan DT, et al. Myopia in Singapore: taking a public health approach[J]. Br J Ophthalmol, 2001, 85(5): 521－526.
[19]	Karuppiah V, Wong L, Tay V, et al. School－based programme to address childhood myopia in Singapore[J]. Singapore Med J, 2021, 62(2): 63－68.
[20]	Lin S, Ma Y, He X, et al. Using Decision Curve Analysis to Evaluate Common Strategies for Myopia Screening in School－Aged Children[J]. Ophthalmic Epidemiol, 2019, 26(4): 286－294.
[21]	赵原原，龚洁，杨莉华，等. AL/CR及裸眼视力筛查儿童青少年近视的准确性研究[J]. 现代预防医学，2019，46(6)：1028－1030.
[22]	He X, Zou H, Lu L, et al. Axial length/corneal radius ratio: association with refractive state and role on myopia detection combined with visual acuity in Chinese schoolchildren[J]. PLoS One, 2015, 10(2): e0111766.
[23]	Wang J, Xie H, Morgan I, et al. How to Conduct School Myopia Screening: Comparison Among Myopia Screening Tests and Determination of Associated Cutoffs[J]. Asia Pac J Ophthalmol (Phila), 2022, 11(1): 12－18.
[24]	刘红卫. 不同场所对小学生视力检测结果准确性的影响探究[J]. 基层医学论坛，2013，17(10)：1288－1289.
[25]	陈秀荣，王艳红，石慧，等. 儿童视力检查准确度的影响因素及护理对策[J]. 护理实践与研究，2012，9(24)：70－71.
[26]	林浩添，李龙辉，陈睛晶. 儿童眼病的人工智能研究进展[J]. 山东大学学报(医学版)，2020，58(11)：11－16.
[27]	林浩添，林铎儒. 我国未成年人视觉损害人工智能诊疗研究的现状和建议[J]. 中国临床新医学，2020，13(2)：111－114.
[28]	Mathers M, Keyes M, Wright M. A review of the evidence on the effectiveness of children's vision screening[J]. Child Care Health Dev, 2010, 36(6): 756－780.
[29]	Milante RR, Guo X, Neitzel AJ, et al. Analysis of vision screening failures in a school－based vision program (2016－19)[J]. J AAPOS, 2021, 25(1): 29.e21－29.e27.
[30]	Yang Y, Li R, Lin D, et al. Automatic identification of myopia based on ocular appearance images using deep learning[J]. Ann Transl Med, 2020, 8(11): 705.
[31]	Jiang F, Jiang Y, Zhi H, et al. Artificial intelligence in healthcare: past, present and future[J]. Stroke Vasc Neurol, 2017, 2(4): 230－243.
[32]	Amisha, Malik P, Pathania M, et al. Overview of artificial intelligence in medicine[J]. J Family Med Prim Care, 2019, 8(7): 2328－2331.
[33]	Varadarajan AV, Poplin R, Blumer K, et al. Deep Learning for Predicting Refractive Error From Retinal Fundus Images[J]. Invest Ophthalmol Vis Sci, 2018, 59(7): 2861－2868.
[34]	Lin H, Long E, Ding X, et al. Prediction of myopia development among Chinese school－aged children using refraction data from electronic medical records: A retrospective, multicentre machine learning study[J]. PLoS Med, 2018, 15(11): e1002674.
[35]	周云帆，陈娄，蒋沁. 眼健康大数据平台实践研究[J]. 医学信息学杂志，2019，40(5)：32－35.
[36]	宋倩，唐世琪. 互联网+视觉健康管理－武汉市近视眼预测预防系统在视觉健康管理中应用的探索与实践[J]. 中国临床保健杂志，2019，22(1)：142－144.
[37]	Foo LL, Ng WY, Lim GYS, et al. Artificial intelligence in myopia: current and future trends[J]. Curr Opin Ophthalmol, 2021, 32(5): 413－424.
[38]	Wu X, Liu L, Zhao L, et al. Application of artificial intelligence in anterior segment ophthalmic diseases: diversity and standardization[J]. Ann Transl Med, 2020, 8(11): 714.
[39]	田娟秀，刘国才，谷珊珊，等. 医学图像分析深度学习方法研究与挑战[J]. 自动化学报，2018，44(3)：401－424.
[40]	De Fauw J, Ledsam JR, Romera－Paredes B, et al. Clinically applicable deep learning for diagnosis and referral in retinal disease[J]. Nat Med, 2018, 24(9): 1342－1350.
[41]	Ting DSW, Cheung CY, Lim G, et al. Development and Validation of a Deep Learning System for Diabetic Retinopathy and Related Eye Diseases Using Retinal Images From Multiethnic Populations With Diabetes[J]. JAMA, 2017, 318(22): 2211－2223.
[42]	Abràmoff MD, Lavin PT, Birch M, et al. Pivotal trial of an autonomous AI－based diagnostic system for detection of diabetic retinopathy in primary care offices[J]. NPJ Digit Med, 2018, 1: 39.
[43]	Gulshan V, Peng L, Coram M, et al. Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs[J]. JAMA, 2016, 316(22): 2402－2410.
[44]	Schmidt－Erfurth U, Sadeghipour A, Gerendas BS, et al. Artificial intelligence in retina[J]. Prog Retin Eye Res, 2018, 67: 1－29.
[45]	Tan TE, Anees A, Chen C, et al. Retinal photograph－based deep learning algorithms for myopia and a blockchain platform to facilitate artificial intelligence medical research: a retrospective multicohort study[J]. Lancet Digit Health, 2021, 3(5): e317－e329.
[46]	项毅帆，陈睛晶，胡伟玲，等. 基于移动终端的视力智能检查和管理系统的研发及临床应用价值评估[J]. 中华实验眼科杂志，2021，39(9)：798－802.

序号	筛查手段	良好表现	参考文献
1	通过眼外观图像筛查近视	工作特征曲线下面积为0.9270、敏感性为81.13 %和特异性为86.42 %	[6]
2	利用眼底照相预测屈光度	平均绝对误差为0.56~0.91屈光度	[9]
3	利用眼底照相筛查高度近视	工作特征曲线下面积大于0.91，灵敏度达到95%。	[37]
4	通过验光数据预测个性化近视发展	八年内预测高度近视的工作特征曲线下面积可到达0.801~0.985	[10]
5	分析近视相关因素预测近视发展	工作特征曲线下面积为0.98，特异性度为94%和敏感性为94%	[42]

序号	筛查手段	良好表现	参考文献
1	通过眼外观图像筛查近视	工作特征曲线下面积为0.9270、敏感性为81.13 %和特异性为86.42 %	[6]
2	利用眼底照相预测屈光度	平均绝对误差为0.56~0.91屈光度	[9]
3	利用眼底照相筛查高度近视	工作特征曲线下面积大于0.91，灵敏度达到95%。	[37]
4	通过验光数据预测个性化近视发展	八年内预测高度近视的工作特征曲线下面积可到达0.801~0.985	[10]
5	分析近视相关因素预测近视发展	工作特征曲线下面积为0.98，特异性度为94%和敏感性为94%	[42]

Please choose a citation manager

Content to export