Refractive error is among the leading causes of visual impairment globally. The diagnosis and management of refractive error has traditionally relied on comprehensive eye examinations by eye care professionals, but access to these specialized services has remained limited in many areas of the world. Given this, artificial intelligence (AI) has shown immense potential in transforming the diagnosis and management of refractive error. We review AI applications across various aspects of refractive error care – from axial length prediction using fundus images to risk stratification for myopia progression. AI algorithms can be trained to analyze clinical data to detect refractive error as well as predict associated risks of myopia progression. For treatments such as implantable collamer and orthokeratology lenses, AI models facilitate vault size prediction and optimal lens fitting with high accuracy. Furthermore, AI has demonstrated promise in optimizing surgical planning and outcomes for refractive procedures. Emerging digital technologies such as telehealth, smartphone applications, and virtual reality integrated with AI present novel avenues for refractive error screening. We discuss key challenges, including limited validation datasets, lack of data standardization, image quality issues, population heterogeneity, practical deployment, and ethical considerations regarding patient privacy that need to be addressed before widespread clinical implementation.
FlaxmanSRBourneRRAResnikoffS, et al.Global causes of blindness and distance vision impairment 1990–2020: a systematic review and meta-analysis. Lancet Glob Health2017; 5: e1221–e1234. 20171011. DOI: https://doi.org/10.1016/s2214-109x(17)30393-5.
2.
HoldenBAFrickeTRWilsonDA, et al.Global prevalence of myopia and high myopia and temporal trends from 2000 through 2050. Ophthalmology2016; 123: 1036–1042. DOI: https://doi.org/10.1016/j.ophtha.2016.01.006
3.
FlitcroftDI. The complex interactions of retinal, optical and environmental factors in myopia aetiology. Prog Retin Eye Res2012; 31: 622–660. 20120704. DOI: https://doi.org/10.1016/j.preteyeres.2012.06.004.
VaradarajanAVPoplinRBlumerK, et al.Deep learning for predicting refractive error from retinal Fundus images. Invest Ophthalmol Visual Sci2018; 59: 2861–2868. DOI: https://doi.org/10.1167/iovs.18-23887
6.
YangDLiMLiW, et al.Prediction of refractive error based on ultrawide field images with deep learning models in myopia patients. Front Med (Lausanne)2022; 9. DOI: https://doi.org/10.3389/fmed.2022.834281.
7.
TanT-ETingDSWLiuY, et al.Artificial intelligence using a deep learning system with transfer learning to predict refractive error and myopic macular degeneration from color fundus photographs. Invest Ophthalmol Visual Sci2019; 60: 1478–1478.
8.
ManivannanNLeahyCCovitaA, et al.Predicting axial length and refractive error by leveraging focus settings from widefield fundus images. Invest Ophthalmol Visual Sci2020; 61: B0063–PB0063.
9.
ZouHShiSYangX, et al.Identification of ocular refraction based on deep learning algorithm as a novel retinoscopy method. Biomed Eng Online2022; 21(1): 87. DOI: https://doi.org/10.1186/s12938-022-01057-9
10.
XuDDingSZhengT, et al.Deep learning for predicting refractive error from multiple photorefraction images. Biomed Eng Online2022; 21(1): 55. DOI: https://doi.org/10.1186/s12938-022-01025-3
11.
ChunJKimYShinKY, et al.Deep learning–based prediction of refractive error using photorefraction images captured by a smartphone: model development and validation study. JMIR Med Inform2020; 8: e16225. DOI: https://doi.org/10.2196/16225
12.
LindeGChalakkalRZhouL, et al.Automatic Refractive Error Estimation Using Deep Learning-Based Analysis of Red Reflex Images. Diagnostics2023; 13(17). DOI: https://doi.org/10.3390/diagnostics13172810
13.
YooTKRyuIHKimJK, et al.Deep learning for predicting uncorrected refractive error using posterior segment optical coherence tomography images. Eye2022; 36: 1959–1965. DOI: https://doi.org/10.1038/s41433-021-01795-5
14.
JainRYooTKRyuIH, et al.Deep transfer learning for ethnically distinct populations: prediction of refractive error using optical coherence tomography. Ophthalmol Ther2024; 13: 305–319. DOI: https://doi.org/10.1007/s40123-023-00842-6
15.
DongLHuXYYanYN, et al.Deep Learning-Based Estimation of Axial Length and Subfoveal Choroidal Thickness From Color Fundus Photographs. Front Cell Dev Biol2021; 9. DOI: https://doi.org/10.3389/fcell.2021.653692.
16.
OhRLeeEKBaeK, et al.Deep learning-based prediction of axial length using ultra-widefield Fundus photography. Korean J Ophthalmol2023; 37: 95–104. DOI: https://doi.org/10.3341/kjo.2022.0059
17.
LinghamGLoughmanJPanahDS, et al.The long and short of it: a comprehensive assessment of axial length estimation in myopic eyes from ocular and demographic variables. Eye2024. DOI: https://doi.org/10.1038/s41433-023-02899-w
LinHLongEDingX, et al.Prediction of myopia development among Chinese school-aged children using refraction data from electronic medical records: a retrospective, multicentre machine learning study. PLoS Med2018; 15: e1002674. DOI: https://doi.org/10.1371/journal.pmed.1002674
RampatRDeshmukhRChenX, et al.Artificial Intelligence in Cornea, Refractive Surgery, and Cataract: Basic Principles, Clinical Applications, and Future Directions. The Asia-Pacific J of Ophthalmol2021; 10(3).
23.
LopesBTRamosICSalomãoMQ, et al.Enhanced tomographic assessment to detect corneal ectasia based on artificial intelligence. Am J Ophthalmol2018; 195: 223–232. DOI: https://doi.org/10.1016/j.ajo.2018.08.005
24.
XieYZhaoLYangX, et al.Screening candidates for refractive surgery with corneal tomographic–based deep learning. JAMA Ophthalmol2020; 138: 519–526. DOI: https://doi.org/10.1001/jamaophthalmol.2020.0507
25.
AmbrósioRJr., MachadoAPLeãoE, et al. Optimized artificial intelligence for enhanced ectasia detection using scheimpflug-based corneal tomography and biomechanical data. Am J Ophthalmol2023; 251: 126–142. DOI: https://doi.org/10.1016/j.ajo.2022.12.016.
26.
AmbrósioRLopesBTFaria-CorreiaF, et al.Integration of scheimpflug-based corneal tomography and biomechanical assessments for enhancing ectasia detection. J Refract Surg2017; 33: 434–443. DOI: doi:10.3928/1081597X-20170426-02.
27.
FrancisMShettyRPadmanabhanP, et al.New simulation software to predict postoperative corneal stiffness before laser vision correction. J of Cataract & Refractive Surg2023; 49(6).
28.
CuiTWangYJiS, et al.Applying machine learning techniques in nomogram prediction and analysis for SMILE treatment. Am J Ophthalmol2020; 210: 71–77. DOI: https://doi.org/10.1016/j.ajo.2019.10.015
29.
ParkSKimHKimL, et al.Artificial intelligence-based nomogram for small-incision lenticule extraction. Biomed Eng Online2021; 20(1): 38. DOI: https://doi.org/10.1186/s12938-021-00867-7
30.
WangHZhengSTangS, et al.Investigation of Accuracy and Influence Factors of Predicting Lenticule Thickness in Small Incision Lenticule Extraction by Machine Learning Models. J Pers Med2023; 13(2). DOI: https://doi.org/10.3390/jpm13020256
31.
KimJRyuIHKimJK, et al.Machine learning predicting myopic regression after corneal refractive surgery using preoperative data and fundus photography. Graefe's Arch Clin Exp Ophthalmol2022; 260: 3701–3710. DOI: https://doi.org/10.1007/s00417-022-05738-y
32.
KoprowskiRLanzaMIrregolareC. Corneal power evaluation after myopic corneal refractive surgery using artificial neural networks. Biomed Eng Online2016; 15(1): 121. DOI: https://doi.org/10.1186/s12938-016-0243-5
33.
HiraokaT. Myopia Control With Orthokeratology: A Review. Eye Contact Lens2022; 48(3).
34.
MoshirfarMWebsterCRRonquilloYC. Phakic intraocular lenses: an update and review for the treatment of myopia and myopic astigmatism in the United States. Curr Opin Ophthalmol2022; 33(5).
35.
ChamberlainPPeixoto-de-MatosSCLoganNS, et al.A 3-year Randomized Clinical Trial of MiSight Lenses for Myopia Control. Optom Vis Sci2019; 96(8).
36.
KamiyaKIgarashiAHayashiK, et al. A multicenter prospective cohort study on refractive surgery in 15 011 eyes. Am J Ophthalmol2017; 175: 159–168. DOI: https://doi.org/10.1016/j.ajo.2016.12.009.
37.
KamiyaKRyuIHYooTK, et al.Prediction of phakic intraocular Lens vault using machine learning of anterior segment optical coherence tomography metrics. Am J Ophthalmol2021; 226: 90–99. DOI: https://doi.org/10.1016/j.ajo.2021.02.006
38.
KangEMRyuIHLeeG, et al.Development of a web-based ensemble machine learning application to select the optimal size of posterior chamber phakic intraocular Lens. Transl Vis Sci Technol2021; 10: 5–5. DOI: https://doi.org/10.1167/tvst.10.6.5
39.
XuKLiuXLeiY, et al.Use of neural networks to predict vault values after implantable collamer lens surgery. Graefe's Arch Clin Exp Ophthalmol2021; 259: 3795–3803. DOI: https://doi.org/10.1007/s00417-021-05294-x
40.
YangSLinWWeijunJ, et al.Big-data and artificial-intelligence-assisted vault prediction and EVO-ICL size selection for myopia correction. Br J Ophthalmol2023; 107(2): 201. DOI: https://doi.org/10.1136/bjophthalmol-2021-319618
41.
AssafJFReinsteinDZZakkaC, et al.Deep learning–based estimation of implantable collamer Lens vault using optical coherence tomography. Am J Ophthalmol2023; 253: 29–36. DOI: https://doi.org/10.1016/j.ajo.2023.04.008
42.
XuSYangXZhangS, et al. Machine learning models for orthokeratology lens fitting and axial length prediction. Ophthal Phys Opt2023; n/a. DOI: https://doi.org/10.1111/opo.13212.
43.
FanYYuZTangT, et al.Machine learning algorithm improves accuracy of ortho-K lens fitting in vision shaping treatment. Contact Lens and Anterior Eye2022; 45(3). DOI: https://doi.org/10.1016/j.clae.2021.101474
44.
TangYChenZWangW, et al.A deep learning–based framework for accurate evaluation of corneal treatment zone after orthokeratology. Transl Vis Sci Technol2021; 10: 21–21. DOI: https://doi.org/10.1167/tvst.10.14.21
45.
LiYZhaoHFanY, et al.A machine learning-based algorithm for estimating the original corneal curvature based on corneal topography after orthokeratology. Contact Lens and Anterior Eye2023; 46: 101862. DOI: https://doi.org/10.1016/j.clae.2023.101862
46.
ZhangMGuoYZhouC, et al.Deep neural network with self-attention based automated determination system for treatment zone and peripheral steepened zone in Orthokeratology for adolescent myopia. Contact Lens and Anterior Eye2024; 47(1). DOI: https://doi.org/10.1016/j.clae.2023.102081
47.
KooSKimWKParkYK, et al.Development of a machine-learning–based tool for overnight orthokeratology Lens fitting. Transl Vis Sci Technol2024; 13: 17–17. DOI: https://doi.org/10.1167/tvst.13.2.17
48.
FangJZhengYMouH, et al.Machine learning for predicting the treatment effect of orthokeratology in children. Front Pediatr2023; 10. DOI: https://doi.org/10.3389/fped.2022.1057863.
LimZWPushpanathanKYewSME, et al.Benchmarking large language models’ performances for myopia care: a comparative analysis of ChatGPT-3.5. ChatGPT 4(0, and Google Bard. eBioMedicine2023; 95. DOI: https://doi.org/10.1016/j.ebiom.2023.104770.
52.
ĆirkovićAKatzT. Exploring the potential of ChatGPT-4 in predicting refractive surgery categorizations: comparative study. JMIR Form Res2023; 7: e51798: 20231228. DOI: https://doi.org/10.2196/51798
53.
LiJ-POLiuHTingDSJ, et al. Digital technology, tele-medicine and artificial intelligence in ophthalmology: a global perspective. Prog Retinal Eye Res2021; 82: 100900. DOI: https://doi.org/10.1016/j.preteyeres.2020.100900.
54.
ZhangCZhaoJZhuZ, et al.Applications of Artificial Intelligence in Myopia: Current and Future Directions. Front Med (Lausanne)2022; 9, Review. DOI: https://doi.org/10.3389/fmed.2022.840498.
LiYYipMYTTingDSW, et al.Artificial intelligence and digital solutions for myopia. Taiwan J Ophthalmol2023; 13: 142–150. 20230516. DOI: https://doi.org/10.4103/tjo.TJO-D-23-00032.
62.
KubotaRJoshiNRFitzgeraldTJ, et al.Biometric and refractive changes following the monocular application of peripheral myopic defocus using a novel augmented-reality optical system in adults. Sci Rep2022; 12: 11875. DOI: https://doi.org/10.1038/s41598-022-15456-4
ZhaoFChenLMaH, et al. Virtual reality: a possible approach to myopia prevention and control?Med Hypotheses2018; 121: 1–3. DOI: https://doi.org/10.1016/j.mehy.2018.09.021.
65.
MasalkhiMWaisbergEOngJ, et al.Apple vision pro for ophthalmology and medicine. Ann Biomed Eng2023: 1–4.
WenLCaoYChengQ, et al.Objectively measured near work, outdoor exposure and myopia in children. Br J Ophthalmol2020; 104: 1542–1547. 20200219. DOI: https://doi.org/10.1136/bjophthalmol-2019-315258.
68.
WenLChengQLanW, et al.An objective comparison of light intensity and near-visual tasks between rural and urban school children in China by a wearable device clouclip. Transl Vis Sci Technol2019; 8: 15. 20191115. DOI: https://doi.org/10.1167/tvst.8.6.15
69.
CaoYLanWWenL, et al. An effectiveness study of a wearable device (clouclip) intervention in unhealthy visual behaviors among school-age children: a pilot study. Medicine (Baltimore)2020; 99: e17992. DOI: https://doi.org/10.1097/md.0000000000017992.
70.
YouAKimJKRyuIH, et al.Application of generative adversarial networks (GAN) for ophthalmology image domains: a survey. Eye and Vision2022; 9: 6. DOI: https://doi.org/10.1186/s40662-022-00277-3
71.
ImanMArabniaHRRasheedK. A Review of Deep Transfer Learning and Recent Advancements. Technologies2023; 11(2): 40.
72.
HassijaVChamolaVMahapatraA, et al.Interpreting Black-Box Models: A Review on Explainable Artificial Intelligence. Cognit Comput2023. DOI: https://doi.org/10.1007/s12559-023-10179-8
73.
LinardatosPPapastefanopoulosVKotsiantisS. Explainable AI: A Review of Machine Learning Interpretability Methods. Entropy2021; 23(1). DOI: https://doi.org/10.3390/e23010018
74.
OngJTavakkoliAZamanN, et al. Terrestrial health applications of visual assessment technology and machine learning in spaceflight associated neuro-ocular syndrome. npj Microgravity2022; 8(1). DOI: https://doi.org/10.1038/s41526-022-00222-7.
75.
LinHLiRLiuZ, et al.Diagnostic efficacy and therapeutic decision-making capacity of an artificial intelligence platform for childhood cataracts in eye clinics: a multicentre randomized controlled trial. eClinicalMedicine2019; 9: 52–59. DOI: https://doi.org/10.1016/j.eclinm.2019.03.001
76.
NoriegaAMeiznerDCamachoD, et al.Screening diabetic retinopathy using an automated retinal image analysis system in independent and assistive use cases in Mexico: randomized controlled trial. JMIR Form Res2021; 5: e25290. DOI: https://doi.org/10.2196/25290
77.
WolfRMChannaRLiuTYA, et al.Autonomous artificial intelligence increases screening and follow-up for diabetic retinopathy in youth: the ACCESS randomized control trial. Nat Commun2024; 15: 421. DOI: https://doi.org/10.1038/s41467-023-44676-z
78.
AbràmoffMDLavinPTBirchM, et al.Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices. npj Digital Medicine2018; 1: 39. DOI: https://doi.org/10.1038/s41746-018-0040-6
79.
LiBChenHYuW, et al.The performance of a deep learning system in assisting junior ophthalmologists in diagnosing 13 major fundus diseases: a prospective multi-center clinical trial. npj Digital Medicine2024; 7: 8. DOI: https://doi.org/10.1038/s41746-023-00991-9
80.
MathengeWWhitestoneNNkurikiyeJ, et al.Impact of Artificial Intelligence Assessment of Diabetic Retinopathy on Referral Service Uptake in a Low-Resource Setting: The RAIDERS Randomized Trial. Ophthalmology Science2022; 2(4). DOI: https://doi.org/10.1016/j.xops.2022.100168
81.
EvansNGWennerDMCohenIG, et al. Emerging ethical considerations for the use of artificial intelligence in ophthalmology. Ophthalmol Sci2022; 2: 100141. 20220307. DOI: https://doi.org/10.1016/j.xops.2022.100141.
82.
TanT-EAneesAChenC, et al.Retinal photograph-based deep learning algorithms for myopia and a blockchain platform to facilitate artificial intelligence medical research: a retrospective multicohort study. The Lancet Digital Health2021; 3: e317–e329. DOI: https://doi.org/10.1016/S2589-7500(21)00055-8
83.
WangYWeiRYangD, et al.Development and validation of a deep learning model to predict axial length from ultra-wide field images. Eye2023. DOI: https://doi.org/10.1038/s41433-023-02885-2
84.
RampatRDebellemanièreGMaletJ, et al.Using artificial intelligence and novel polynomials to predict subjective refraction. Sci Rep2020; 10: 8565. DOI: https://doi.org/10.1038/s41598-020-65417-y
85.
WeiRLiJYangW, et al. Association of tessellation density with progression of axial length and refraction in children: an AI-assisted 4-year study. RETINA2024; 10. DOI: https://doi.org/10.1097/iae.0000000000003991.
86.
FooLLLimGYSLancaC, et al. Deep learning system to predict the 5-year risk of high myopia using fundus imaging in children. npj Digital Medicine2023; 6: 10. DOI: https://doi.org/10.1038/s41746-023-00752-8.
87.
TongH-JHuangZ-MLiY-L, et al. Machine learning to analyze the factors influencing myopia in students of different school periods. Front Public Health2023; 11. DOI: https://doi.org/10.3389/fpubh.2023.1169128.
88.
ZhangRDongLYangQ, et al. Screening for novel risk factors related to high myopia using machine learning. BMC Ophthalmol2022; 22: 405. DOI: https://doi.org/10.1186/s12886-022-02627-0.
89.
SanthiagoMRAraujoDCStivalLR, et al. Ectasia risk model: a novel method without cut-off point based on artificial intelligence improves detection of higher-risk eyes. J Refract Surg2022; 38: 716–724. DOI: doi:10.3928/1081597X-20221018-01.
90.
YooTKRyuIHChoiH, et al. Explainable machine learning approach as a tool to understand factors used to select the refractive surgery technique on the expert level. Transl Vis Sci Technol2020; 9: 8–8. DOI: https://doi.org/10.1167/tvst.9.2.8.
91.
YooTKRyuIHLeeG, et al. Adopting machine learning to automatically identify candidate patients for corneal refractive surgery. npj Digital Medicine2019; 2: 59. DOI: https://doi.org/10.1038/s41746-019-0135-8.
92.
AchironAGurZAvivU, et al. Predicting refractive surgery outcome: machine learning approach with big data. J Refract Surg2017; 33: 592–597. DOI: doi:10.3928/1081597X-20170616-03.
93.
NikdelMGhadimiHTavakoliM, et al. Assessment of the responses of the artificial intelligence-based chatbot ChatGPT-4 to frequently asked questions about amblyopia and childhood myopia. J Pediatr Ophthalmol Strabismus2023: 1–4. 20231025. DOI: https://doi.org/10.3928/01913913-20231005-02.
94.
BiswasSLoganNSDaviesLN, et al. Assessing the utility of ChatGPT as an artificial intelligence-based large language model for information to answer questions on myopia. Ophthalmic Physiol Opt2023; 43: 1562–1570. 20230721. DOI: https://doi.org/10.1111/opo.13207.
