This paper is in the following e-collection/theme issue:

Digital Health Reviews (1339) Clinical Information and Decision Making (1450) Artificial Intelligence (1446) Machine Learning (1516) Ophthalmology (50)

Published on in Vol 27 (2025)

Preprints (earlier versions) of this paper are available at https://preprints.jmir.org/preprint/57644, first published .
Machine Learning Approaches in High Myopia: Systematic Review and Meta-Analysis

Machine Learning Approaches in High Myopia: Systematic Review and Meta-Analysis

Machine Learning Approaches in High Myopia: Systematic Review and Meta-Analysis

Authors of this article:

Huiyi Zuo1 Author Orcid Image ;   Baoyu Huang1 Author Orcid Image ;   Jian He1 Author Orcid Image ;   Liying Fang1 Author Orcid Image ;   Minli Huang1 Author Orcid Image
Article Authors Cited by Tweetations Metrics

    Review

    Ophthalmology Department, First Affiliated Hospital of GuangXi Medical University, Nanning, China

    Corresponding Author:

    Minli Huang, MD

    Ophthalmology Department

    First Affiliated Hospital of GuangXi Medical University

    No 6 Shuangyong Road, Nanning, Guangxi

    Nanning, 530000

    China

    Phone: 86 0771 5356507

    Email: 420306@sr.gxmu.edu.cn


    Background: In recent years, with the rapid development of machine learning (ML), it has gained widespread attention from researchers in clinical practice. ML models appear to demonstrate promising accuracy in the diagnosis of complex diseases, as well as in predicting disease progression and prognosis. Some studies have applied it to ophthalmology, primarily for the diagnosis of pathologic myopia and high myopia-associated glaucoma, as well as for predicting the progression of high myopia. ML-based detection still requires evidence-based validation to prove its accuracy and feasibility.

    Objective: This study aims to discern the performance of ML methods in detecting high myopia and pathologic myopia in clinical practice, thereby providing evidence-based support for the future development and refinement of intelligent diagnostic or predictive tools.

    Methods: PubMed, Cochrane, Embase, and Web of Science were thoroughly retrieved up to September 3, 2023. The prediction model risk of bias assessment tool was leveraged to appraise the risk of bias in the eligible studies. The meta-analysis was implemented using a bivariate mixed-effects model. In the validation set, subgroup analyses were conducted based on the ML target events (diagnosis and prediction of high myopia and diagnosis of pathological myopia and high myopia-associated glaucoma) and modeling methods.

    Results: This study ultimately included 45 studies, of which 32 were used for quantitative meta-analysis. The meta-analysis results unveiled that for the diagnosis of pathologic myopia, the summary receiver operating characteristic (SROC), sensitivity, and specificity of ML were 0.97 (95% CI 0.95-0.98), 0.91 (95% CI 0.89-0.92), and 0.95 (95% CI 0.94-0.97), respectively. Specifically, deep learning (DL) showed an SROC of 0.97 (95% CI 0.95-0.98), sensitivity of 0.92 (95% CI 0.90-0.93), and specificity of 0.96 (95% CI 0.95-0.97), while conventional ML (non-DL) showed an SROC of 0.86 (95% CI 0.75-0.92), sensitivity of 0.77 (95% CI 0.69-0.84), and specificity of 0.85 (95% CI 0.75-0.92). For the diagnosis and prediction of high myopia, the SROC, sensitivity, and specificity of ML were 0.98 (95% CI 0.96-0.99), 0.94 (95% CI 0.90-0.96), and 0.94 (95% CI 0.88-0.97), respectively. For the diagnosis of high myopia-associated glaucoma, the SROC, sensitivity, and specificity of ML were 0.96 (95% CI 0.94-0.97), 0.92 (95% CI 0.85-0.96), and 0.88 (95% CI 0.67-0.96), respectively.

    Conclusions: ML demonstrated highly promising accuracy in diagnosing high myopia and pathologic myopia. Moreover, based on the limited evidence available, we also found that ML appeared to have favorable accuracy in predicting the risk of developing high myopia in the future. DL can be used as a potential method for intelligent image processing and intelligent recognition, and intelligent examination tools can be developed in subsequent research to provide help for areas where medical resources are scarce.

    Trial Registration: PROSPERO CRD42023470820; https://tinyurl.com/2xexp738

    J Med Internet Res 2025;27:e57644

    doi:10.2196/57644

    Keywords

    high myopia; pathological myopia; high myopia-associated glaucoma; machine learning; deep learning 


    Myopia is currently widely regarded as a significant public health issue, leading to substantial vision loss and serving as a risk factor for a range of other serious ocular diseases. It is estimated that by 2050, 4.758 billion people (49.8% of the world population) and 938 million people (9.8% of the world population) will suffer from myopia and high myopia, respectively [1]. A recent meta-analysis study proposed that the global economic burden due to productivity losses from uncorrected myopia and myopic macular degeneration is estimated to reach US $250 billion [2]. Therefore, the prevention of high myopia as well as the diagnosis and treatment of pathological myopia remain a formidable societal challenge.

    High myopia is defined as the spherical equivalent ≤–6.0 diopter [3] when the accommodation of the eye is relaxed. However, increased severity of myopia and elongation of the eye’s axial length could alter the posterior segment structures, causing posterior scleral staphyloma, myopic macular degeneration, and optic neuropathy related to high myopia, potentially leading to the loss of best-corrected visual acuity [3]. High myopia-related fundus lesions stand as an important contributing factor to blindness across the world as well as in China [4]. The detection of high myopia hinges primarily on artificial auxiliary techniques, like refraction detection, fundus examination, measurement of axial length, and fundus photography. Nevertheless, manual examination and analysis by ophthalmologists are still essential, necessitating a significant investment of time and effort [5]. Additionally, in regions with limited medical resources, the shortage of ophthalmologists and medical equipment impedes the early and accurate identification of high-risk patients with high myopia, resulting in missed opportunities for optimal treatment. Therefore, forecasting the risk of high myopia and precisely diagnosing pathological myopia are currently major research focus.

    With the rapid advances in computing technology and the ongoing refinement of statistical theory, machine learning (ML) has gradually been promoted and applied in clinical practice. For instance, ML can not only improve image quality, reduce misregistration, and simulate attenuation correction imaging in core cardiology [6], but also be used for cancer screening (detection of lesions), characterization and grading of tumors, and prognosis prediction, thus facilitating clinical decision-making [7]. Since fundus images are noncontact, noninvasive, low-cost, easily accessible, and easy to process, ML has been extensively used to diagnose common retinal diseases, including diabetic retinopathy [8-10], macular degeneration [10], and glaucoma [11-13]. ML has been applied to various image-processing tasks. Novel techniques for analyzing fundus images of high myopia and pathological myopia are continuously emerging [14,15]. However, the accuracy of these ML detections has not been systematically studied. Consequently, the present study was executed to comprehensively describe the accuracy of ML in detecting different degrees of lesions in high myopia, furnishing an evidence-based reference for subsequent lesion management.


    Study Registration

    This study was implemented as per the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 guidelines and prospectively registered with PROSPERO (ID: CRD42023470820). The PRISMA checklist is available in Multimedia Appendix 1.

    Inclusion and Exclusion Criteria

    We established detailed inclusion and exclusion criteria for this systematic review. To enhance visualization, these criteria are presented in tabular form (Textbox 1).

    Textbox 1. Inclusion and exclusion criteria.

    Inclusion criteria

    • Study type: (1) case-control, cohort, nested case-control, and case-cohort studies and (2) studies reported in English.
    • Machine learning (ML): studies that fully constructed ML models for the prediction or diagnosis of high myopia, the diagnosis of pathological myopia, or the diagnosis of high myopia-associated glaucoma.
    • Outcome measures: at least one of the following outcome indicators were reported: receiver operating characteristic (ROC), c-index, sensitivity, specificity, accuracy, recovery rate, accuracy rate, confusion matrix, F1-score, and calibration curve.
    • Datasets: (1) some studies lacked independent validation sets, and only k-fold cross-validation was leveraged to verify the effect of the constructed mode; and (2) in some publicly available datasets, particularly those involving medical imaging, different studies have reported the efficiency of varying ML methods.

    Exclusion criteria

    • Study type: (1) meta, review, guide, expert opinion; and (2) studies with too few samples (less than 20 cases).
    • ML: literature that only executed the risk factor analysis but did not develop a complete ML mode.
    • Outcome measures: none of the following outcomes were reported: ROC, c-index, sensitivity, specificity, accuracy, recovery rate, accuracy rate, confusion matrix, F1-score, and calibration curve.

    Data Sources and Search Strategy

    PubMed, Cochrane, Embase, and Web of Science were thoroughly retrieved up to September 3, 2023, using the form of MeSH (Medical Subjects Headings) + free term, without any restrictions on region or publication period. The specific search strategy is depicted in Multimedia Appendix 2.

    Study Selection and Data Extraction

    Duplicates were excluded from the retrieved literature, and titles and abstracts were reviewed to delete obviously irrelevant studies. The full texts of the remaining studies were then downloaded and thoroughly read to determine the final included studies in the systematic review. A standard electronic data extraction spreadsheet was prepared prior to extracting data. The extracted data encompassed the title, first author, type of study, year of publication, author’s country, patient source, target event, number of cases of the target event, the total number of cases, number of training set cases, the total number of training set cases, method of validation set generation, number of events in the validation set, total number of cases in the validation set, type of models, and modeling variables.

    Two researchers (HZ and LF) independently screened the literature and extracted data. Upon completion, their findings were cross-checked. A third reviewer (JH) was consulted for resolution in case of any dissents.

    Risk of Bias in Studies

    The risk of bias in the eligible studies was appraised by two independent reviewers (HZ and LF) using the prediction model risk of bias assessment tool [16]. This tool is comprised of a large number of questions in four domains (participants, predictors, outcomes, and analysis), which reflect overall bias risk and applicability. The 4 domains involve 2, 3, 6, and 9 specific questions, respectively, and each question may be answered by yes or probably yes, no or probably not, or no information. Following the quality evaluation, a cross-check was carried out. In the event of any disputes, a third researcher (JH) was consulted for resolution.

    Synthesis Methods

    In some of the original studies included in our research, there was not only 1 validation set. Therefore, the number of models included in the meta-analysis does not equal the number of studies. The meta-analysis of sensitivity and specificity was executed using a bivariate mixed-effects model [17]. Sensitivity and specificity were meta-analyzed as per the diagnostic 2×2 table. However, most included studies did not provide the diagnostic 2×2 table. In such cases, the following two approaches were used to calculate the diagnostic 2×2 table: (1) it was computed based on sensitivity, specificity, and precision, combined with the number of cases; and (2) sensitivity and specificity were extracted based on the optimal Youden index, and then combined with the number of cases for calculation. The meta-analysis was implemented using R (version 4.2.0; R Foundation for Statistical Computing).


    Study Selection

    A total of 4214 records were retrieved from the databases, of which 582 were duplicates. After reading the titles and abstracts, 3561 studies unrelated to ML in high myopia were excluded, leaving 71 studies. Of these, 13 only conducted image segmentation without constructing ML models, 5 did not provide full extractable outcome indicators, and 8 analyzed risk factors. Ultimately, 45 studies were incorporated into this review. The literature screening process is depicted in Figure 1.

    ‎
    Figure 1. Flowchart of literature screening.

    Study Characteristics

    The included studies were published from 2010 to 2023. Four of the studies [18-21] were about the prediction of high myopia, and the predicted variables were mainly derived from life characteristics, environmental and genetic factors, and routinely interpretable ocular clinical characteristics. Five of the studies [22-26] were about the diagnosis of high myopia, of which 1 study [22] also involved the diagnosis of pathological lesions of high myopia. Six studies focused on the diagnosis of high myopia-associated glaucoma [27-32]. Out of the included studies, 31 studies focused on the diagnosis of pathological myopia, primarily using optical coherence tomography and fundus imaging to construct artificial intelligence models. Of these, 26 studies [4,15,22,33-55] were based on DL (deep learning), while 5 studies [56-60] required manually coded ML for construction. Additionally, it was noted that in the 45 original studies, all 45 studies included binary classification tasks, with 9 studies [4,33,34,38,39,49,50,52,61] additionally incorporating multiclassification tasks. Regarding validation methods, 31 studies provided an external validation set, and 23 used a combination of internal and external validation sets. In terms of the generation method of validation set, 6 studies [23,24,34,40,47,59] used k-fold cross-validation, 29 [15,19-22,25-29,35-38,41,42,45,48-58,61] used random sampling, and 6 [4,18,32,33,44,60] applied a combination of k-fold cross-validation and random sampling. The detailed characteristics of the eligible studies are shown in Tables 1 and 2.

    Table 1. Fundamental features of included studies.
    First authorYear of publicationCountry of authorsStudy typePatient sourceTarget eventsTotal number of cases
    Tang et al [33]2022China, United StatesRetrospective studyMulticenterDiagnosis of pathologic myopia1395 fundus photographs, 895 patients
    Li et al [56]2023ChinaNested case-control studySingle centerDiagnosis and prediction of pathological myopia20,870 patients
    Du et al [57]2021ChinaRetrospective studySingle centerDiagnosis of pathologic myopia313 patients with high myopia and 457 eyes
    Foo et al [18]2023SingaporeProspective studyMulticenterPrediction of high myopia965 children with 1878 eyes and 7456 fundus photographs
    Kim et al [58]2021KoreaRetrospective studyMulticenterDiagnosis of pathologic myopia860 eyes
    Zhang et al [59]2013SingaporeRetrospective studyRegistry databaseDiagnosis of pathologic myopia2258 patients
    Zhu et al [34]2023ChinaRetrospective studySingle centerDiagnosis of pathologic myopia6078 photographs
    Wu et al [35]2022ChinaRetrospective studySingle centerDiagnosis of pathologic myopia1853 photographs
    Ye et al [36]2021ChinaRetrospective studySingle centerDiagnosis of pathologic myopia1041 patients with pathologic myopia and with 2342 eligible OCTa macular images
    Wang et al [37]2023ChinaRetrospective studySingle centerDiagnosis of pathologic myopia7606 patients with 10,347 fundus photographs
    Wang et al [19]2022ChinaProspective, longitudinal, observational studyWenzhou large-scale surveyPrediction of myopia and high myopia15,765 patients
    Wan et al [4]2021ChinaRetrospective studySingle centerDiagnosis of pathologic myopia858 photographs
    Wan et al [38]2023ChinaRetrospective studySingle centerDiagnosis of pathologic myopia1750 photographs
    Tan et al [22]2021SingaporeRetrospective multicohort studyMulticenter + registry databaseDiagnosis of high myopia + pathological myopia125,421 patients with 251,349 photographs
    Sun et al [39]2023ChinaRetrospective multicohort studyMulticenter + registry databaseDiagnosis of pathologic myopia1514 fundus photographs
    Sogawa et al [40]2020JapanRetrospective studySingle centerDiagnosis of pathologic myopia910 patients with 910 images
    Du et al [41]2022JapanRetrospective studySingle centerDiagnosis of pathologic myopia1327 patients with 2400 high myopia eyes and 9176 OCT images
    Hou et al [60]2023ChinaProspective cohort studySingle centerDiagnosis of pathologic myopia576 patients
    Li et al [52]2022ChinaRetrospective cohort studyMulticenterPathologic myopia29,230 patients with 57,148 fundus photographs
    Li et al [27]2021ChinaCase-control studyMulticenterDiagnosis of glaucoma in high myopia2731 participants with 2731 eyes
    Chen et al [20]2019ChinaProspective studySingle centerPrediction of high myopia1063 patients
    Choi et al [23]2021KoreaRetrospective studySingle centerPrediction of high myopia492 patients with 690 eyes
    Cui et al [42]2021China, TaiwanRetrospective studyRegistry databaseDiagnosis of pathologic myopia800 images
    Guan et al [24]2023ChinaRetrospective studyMulticenterPrediction of high myopia1,285,609 participants
    He et al [61]2022ChinaRetrospective studyMulticenterDiagnosis of pathologic myopia2866 patients with 3945 OCT images
    Hemelings et al [15]2021BelgiumRetrospective studyRegistry databaseDiagnosis of pathologic myopia1200 photographs
    Rauf et al [44]2021PakistanRetrospective studyRegistry databaseDiagnosis of pathologic myopia840 photographs
    Park et al [45]2022KoreaRetrospective studySingle centerDiagnosis of pathologic myopia367 eyes
    Lu et al [46]2021ChinaRetrospective studySingle centerDiagnosis of pathologic myopia and diagnosis of pathologic myopia
    • 17,330 photographs
    • 17,330 photographs
    Lu et al [47]2021ChinaRetrospective studyMulticenterDiagnosis of pathologic myopia32,419 patients with 37,659 images
    Liu et al [54]2010SingaporeRetrospective studySingle centerPathologic myopia80 photographs
    Li et al [48]2022China, United StatesRetrospective studySingle centerDiagnosis of pathologic myopia1139 patients with 5917 images
    Lee et al [28]2023KoreaRetrospective studySingle centerDiagnosis of glaucoma in high myopia260 eyes and 260 images
    Kim et al [29]2023KoreaRetrospective studySingle centerDiagnosis of glaucoma in high myopia2607 eyes
    Jeong et al [30]2023KoreaRetrospective cross-sectional studySingle centerDiagnosis of glaucoma in high myopia274 patients
    Huang et al [21]2022ChinaCase-control studySingle centerPrediction of high myopia1298 patients
    Huang et al [49]2023China, United KingdomRetrospective studySingle centerDiagnosis of pathologic myopia1131 patients with 3441 images
    Du et al [50]2021JapanRetrospective studySingle centerdiagnosis of pathologic myopia4432 eyes and 7020 images
    Crincoli et al [51]2023ItalyCase-control studyMulticenterdiagnosis of pathologic myopia84 patients with 84 eyes and 252 photographs
    Asaoka et al [31]2014JapanCase-control studyMulticenterDiagnosis of glaucoma in high myopia242 patients and 242 eyes
    Bowd et al [32]2023United States, GermanyRetrospective studySingle centerDiagnosis of glaucoma in high myopia593 eyes
    Zhao et al [25]2022ChinaRetrospective studySingle centerPrediction of high myopia546 patients
    Liu et al [53]2010SingaporeRetrospective studySingle centerDiagnosis of pathologic myopia80 photographs
    Dai et al [26]2020ChinaRetrospective studySingle centerPrediction of high myopia319 patients with 932 images
    Baid et al [55]2019IndiaRetrospective studyRegistry databaseDiagnosis of pathologic myopia481 photographs

    aOCT: optical coherence tomography.

    Table 2. Fundamental features of included studies.
    Total number of cases in training setGeneration of validation setTotal number of cases in validation setTotal number of cases in test setModel typeModeling variables
    727 fundus photographs5-fold cross-validation + random sampling238 fundus photographs238 fundus photographsDLaFundus photographs
    2069 patientsRandom sampling1382 patientsUnclearACPb, MLcClinical features
    319 eyesRandom sampling138 eyesUnclearML-based
    radiomics analysis method    		Fundus photographs
    769 children with 1502 eyes and 5945 photographsInternal validation (5-fold cross-validation + random sampling) + multicenter external validation196 children with 376 eyes and 1511 fundus photographs99 children with 189 eyes and 821 photographsDLFundus photographs + clinical features
    602 eyesRandom sampling258 eyesunclearSVMd, MLFundus photographs
    2258 patientsStratified 20-fold cross-validationunclearunclearSVM, MLSNPe + clinical features + fundus photographs
    4252 photographsStratified 20-fold cross-validationunclear1826 photographsDLFundus photographs
    1483 photographsRandom samplingunclear370 photographsDLFundus photographs
    1874 photographsInternal validation (random sampling) + external validation（multicenter）468 photographs450 photographsDLFundus photographs
    5003 patients with 7389 photographsRandom sampling775 patients with 821 photographs1828 patients with 2137 photographsDLFundus photographs
    11,350 patientsInternal validation (random sampling) + external validation(prospective)4415 patients6168 patients (prognostic cohort)LRf, GBDTg, NNhClinical features
    758 photographs5-fold cross-validation + random sampling100 photographsUnclearDLFundus photographs
    1402 photographsRandom sampling174 photographs174 photographsDLFundus photographs
    226,686 photographsInternal validation (random sampling) + external validation（multicenter）11,303 photographs213,475 photographsDLFundus photographs
    400 fundus photographsMulticenter400 fundus photographs714 fundus photographsDLFundus photographs
    Unclear5-fold cross-validationUnclearUnclearDLFundus photographs
    7865 photographsrandom sampling1311 photographsUnclearDLFundus photographs
    516 patients10-fold cross-validation + random sampling60 patientsUnclearXGBoosti, SVM, LRClinical features + metabolic characteristics
    29,213 photographsInternal validation (random sampling) + external validation（multicenter）7302 photographs16,554 photographsDCNNj, DLFundus photographs
    2223 participants with 2223 eyesRandom sampling508 participants with 508 eyesUnclearFCNkOCTl images + clinical features
    638 patientsRandom sampling425 patientsUnclearLRGenetic factors + clinical features
    434 patients with 600 eyes and 1200 images5-fold cross-validationUnclear58 patients with 90 eyes and 180 imagesCNNm, DLOCT images
    400 imagesRandom sampling200 images200 imagesDLFundus photographs
    1600 participantsInternal validation (5-fold cross-validation)Unclear400 patientsRFn, LR, SVMClinical features
    2380 imagesRandom sampling680 photographs340 photographsDLOCT images
    400 photographsRandom sampling400 photographs400 photographsDLFundus photographs
    400 photographs10-fold cross-validation + random sampling40 photographs400 photographsDLFundus photographs
    293 eyesrandom sampling37 eyes37 eyesDL3D OCT images
    11,502 photographsUnclear3284 photographs1642 photographsDLFundus photographs
    2457 photographsUnclear707 photographs372 photographsDLFundus photographs
    32,010 imagesInternal validation (5-fold cross-validation) + external validation (multicenter)Unclear732 patients with 1000 imagesDLFundus photographs
    40 photographsRandom samplingUnclear40 photographsSVM, DLFundus photographs
    838 patients with 4338 imagesInternal validation (random sampling) + external validation (prospective)210 patients with 1167 photographs91 patients with 174 eyes and 412 photographsDLOCT macular images
    165 imagesRandom sampling46 photographs49 photographsDLOCTAo and OCT images
    1416 eyesInternal validation (random sampling) + external validation471 eyes720 eyesDLOCT images
    UnclearUnclearUnclearUnclearDecision treeOCT images
    325 patientsRandom sampling973 patientsUnclearDLGenetic + clinical features
    2264 imagesInternal validation (random sampling) + external validation (prospective)501 photographs604 photographsDLOCT images
    4140 photographsRandom sampling1036 photographs1844 photographsDLFundus photographs
    176 photographsRandom sampling25 photographs51 photographsDLOCT images
    UnclearUnclearUnclearUnclearRFHRT parameters
    347 eyes5-fold cross-validation + random sampling87 eyes159 eyesCNNOCT images
    928 fundus photographsRandom sampling232 photographsUnclearDLFundus photographs
    40 photographsRandom samplingUnclear40 photographsSVM or DLFundus photographs
    792 photographsRandom samplingUnclear140 photographsDLFundus photographs
    374 photographsRandom sampling80 photographs27 photographsCNNFundus photographs

    aDL: deep learning.

    bACP: algorithm of conditional probability.

    cML: machine learning.

    dSVM: support vector machine.

    eSNP: single nucleic polymorphism.

    fLR: logistic regression.

    gGBDT: gradient boosted decision tree.

    hNN: neural network.

    iXGBoost: extreme gradient boosting

    jDCNN: deep convolutional neural networks

    kFCN: fully connected network

    lOCT: optical coherence tomography.

    mCNN: convolutional neural networks

    nRF: random forest

    oOCTA: optical coherence tomography angiography.

    Risk of Bias in Studies

    This review incorporated 67 models. There were 36 retrospective studies [4,15,22-26,28-30,32-42,44-50,52-55,57-59,61] that constructed 39 models, indicating a high bias in the choosing of study participants. Five case-control studies [21,27,31,51,56] constructed 13 models, also showing high bias in the selection of study participants. Since the predictors were evaluated in the context of a known outcome in the case-control studies, there was a high bias in the assessment of predictive factors. Twelve studies [19,20,23,24,27,30,31,56-60] constructed 22 models based on manually coded ML, with a high bias in predictive factors. In terms of statistical analysis, 2 studies [21,45] with 5 models did not meet the requirement of having an event per variable>20%, indicating a high risk of bias. In the statistical analysis, 32 models in 34 studies [4,15,18,21-23,25,26,28,29,32-42,44-55,61] could not estimate event per variable due to the use of the DL method. Additionally, 10 studies [19,20,24,27,30,31,56,58-60] with 29 models in ML did not report on the complexity of the data, rendering it difficult to determine their bias risk. Five studies [20,27,30,31,60] with 11 models were identified as having a high risk of bias in statistical analysis because they did not perform cross-validation to adjust the stability of models with different parameters. In summary, in terms of research participants, 14 models had a low risk of bias; 52 models had a high risk of bias, and 1 model had an unclear risk of bias. In terms of predictors, 37 models had a low risk of bias and 30 models had a high risk of bias. In terms of outcomes, all 67 models had a low risk of bias. In terms of statistical analysis, 3 models had a low risk of bias, 16 models had a high risk of bias, and 48 models had an unclear risk of bias.

    Meta-Analysis of ML for Binary Classification Tasks

    Pathological Myopia

    Twenty studies [26,34-37,39,41,45,47-54,56,58,60,61] reported ML for diagnosing pathological myopia. Modeling algorithms included algorithms of conditional probability, support vector machines (SVMs), logistic regression (LR), extreme gradient boosting, convolutional neural networks (CNNs), and deep convolutional neural networks (DCNNs). The overall sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR), and summary receiver operating characteristic (SROC) were 0.91 (95% CI 0.89-0.92), 0.95 (95% CI 0.94-0.97), 19.7 (95% CI 13.8-28.2), 0.10 (95% CI 0.08-0.12), 201 (95% CI 122-331), and 0.97 (95% CI 0.95-0.98), respectively. The Deek funnel plot indicated no substantial evidence of publication bias in the included ML models. Assuming that the prior probability of pathological myopia was 20% if the result of ML was pathological myopia, then the probability of true pathological myopia would be 83%. If the result of ML was nonpathological myopia, then the probability of true pathological myopia would be 2% (ie, the probability of true nonpathological myopia was 98%; Figure 2 and Figures S1-S3 in Multimedia Appendix 3).

    ‎
    Figure 2. Forest plot for the meta-analysis of sensitivity and specificity of machine learning in detecting pathological myopia [26,34-37,39,41,45,47-54,56,58,60,61]. Note: the pooled sensitivity and specificity of 44 models from 20 machine learning studies on the diagnosis of pathological myopia were 0.91 (95% CI 0.89-0.92) and 0.95 (95% CI 0.94-0.97), respectively.

    Five studies [53,54,56,58,60] reported conventional ML (non-DL) for diagnosing pathological myopia. Modeling algorithms included algorithms of conditional probability, SVM, extreme gradient boosting, and LR. The overall sensitivity, specificity, PLR, NLR, DOR, and SROC curve were 0.77 (95% CI 0.69-0.84), 0.85 (95% CI 0.75-0.92), 5.2 (95% CI 2.8-9.8), 0.27 (95% CI 0.18-0.39), 20 (95% CI 7-51), and 0.86 (95% CI 0.75-0.92), respectively. The Deek funnel plot indicated the presence of publication bias in the conventional ML (non-DL) models. Assuming that the prior probability of pathological myopia for conventional ML (non-DL) was 20% if the result of conventional ML (non-DL) was pathological myopia, then the probability of true pathological myopia would be 57%. If the result of conventional ML (non-DL) was nonpathological myopia, then the probability of true pathological myopia would be 6% (ie, the probability of true nonpathological myopia was 94%; Figure 3 and Figures S4-S6 in Multimedia Appendix 3).

    ‎
    Figure 3. Forest plot for the meta-analysis of sensitivity and specificity of conventional machine learning (non-deep learning) in detecting pathological myopia [53,54,56,58,60]. Note: the pooled sensitivity and specificity of 6 models from 5 conventional machine learning (non-deep learning) studies on the diagnosis of pathological myopia were 0.77 (95% CI 0.69-0.84) and 0.85 (95% CI 0.75-0.92), respectively.

    Fifteen studies [26,34-37,39,41,45,47-52,61] mentioned DL for diagnosing pathological myopia. Modeling algorithms included CNN and DCNN. The overall sensitivity, specificity, PLR, NLR, DOR, and SROC were 0.92 (95% CI 0.90-0.93), 0.96 (95% CI 0.95-0.97), 23.7 (95% CI 16.5-34.0), 0.09 (95% CI 0.07-0.11), 271 (95% CI 168-437), and 0.97 (95% CI 0.95-0.98), respectively. The Deek funnel plot revealed no remarkable publication bias in the DL models. Assuming that the prior probability of pathological myopia for DL was 20% if the result of DL was pathological myopia, then the probability of true pathological myopia would be 86%. If the result of DL was nonpathological myopia, then the probability of true pathological myopia would be 2% (ie, the probability of true nonpathological myopia was 98%; Figure 4 and Figures S7-S9 in Multimedia Appendix 3).

    ‎
    Figure 4. Forest plot for the meta-analysis of sensitivity and specificity of deep learning in detecting pathological myopia [26,34-37,39,41,45,47-52,61]. Note: the pooled sensitivity and specificity of 38 models from 15 deep learning studies on the diagnosis of pathological myopia were 0.92 (95% CI 0.90-0.93) and 0.96 (95% CI 0.95-0.97), respectively.
    High Myopia

    Six studies [4,18,20,23-25] discussed ML for diagnosing and forecasting high myopia. Modeling algorithms included DCNN, CNN, LR, SVM, random forest (RF), and linear mixed models. The sensitivity, specificity, PLR, NLR, DOR, and SROC were 0.94 (95% CI 0.90-0.96), 0.94 (95% CI 0.88-0.97), 16.2 (95% CI 7.7-33.8), 0.06 (95% CI 0.04-0.11), 255 (95% CI 79-822), and 0.98 (95% CI 0.96-0.99), respectively. The Deek funnel plot indicated no substantial evidence of publication bias in the included ML models. Assuming that the prior probability of high myopia for ML was 20% if the result of ML was high myopia, then the probability of true high myopia would be 80%. If the result of ML was non-high myopia, then the probability of true high myopia would be 2% (ie, the probability of true non-high myopia was 98%; Figure 5 and Figures S10-S12 in Multimedia Appendix 3).

    Three studies [4,23,25] focused on diagnosing high myopia, while 3 studies [18,20,24] focused on predicting high myopia. Due to the limited number of studies included, we did not perform a meta-analysis for the diagnostic and prediction tasks. In the validation sets of the diagnostic tasks, sensitivity ranged from 0.91 to 1.00 and specificity ranged from 0.85 to 1.00, while in the validation sets of the prediction tasks, these values were 0.85-0.94 and 0.86-0.94, respectively. We found that both diagnostic and prediction tasks demonstrated highly favorable performance.

    ‎
    Figure 5. Forest plot for the meta-analysis of sensitivity and specificity of machine learning in detecting high myopia [4,18,20,23-25]. Note: the pooled sensitivity and specificity of 9 models from 6 machine learning studies on the diagnosis and prediction of high myopia were 0.94 (95% CI 0.90-0.96) and 0.94 (95% CI 0.88-0.97), respectively.
    High Myopia–Associated Glaucoma

    Six studies [27-32] mentioned ML for diagnosing high myopia-associated glaucoma. Modeling algorithms included Lagrange multiplier, fully connected network, radial basis function network, decision tree, RF, and CNN. The sensitivity, specificity, PLR, NLR, DOR, and SROC curve were 0.92 (95% CI 0.85-0.96), 0.88 (95% CI 0.67-0.96), 7.6 (95% CI 2.4-23.8), 0.09 (95% CI 0.04-0.20), 84 (95% CI 13-555), and 0.96 (95% CI 0.94-0.97), respectively. The Deek funnel plot indicated no substantial evidence of publication bias in the included ML models. Assuming that the prior probability of high myopia–associated glaucoma was 20% if the result of ML was high myopia-associated glaucoma, then the probability of true high myopia–associated glaucoma would be 65%. If the result of ML was non-high myopia–associated glaucoma, then the probability of true high myopia–associated glaucoma would be 2% (ie, the probability of true non-high myopia–associated glaucoma was 98%; Figure 6 and Figures S13-S15 in Multimedia Appendix 3).

    ‎
    Figure 6. Forest plot for the meta-analysis of sensitivity and specificity of machine learning in detecting high myopia-associated glaucoma [27-32]. Note: the pooled sensitivity and specificity of 9 models from 6 machine learning studies on the diagnosis of high myopia-associated glaucoma were 0.92 (95% CI 0.85-0.96) and 0.88 (95% CI 0.67-0.96), respectively.

    Review of ML for Multiclassification Tasks

    Out of the included studies, 9 [4,33,34,38,39,49,50,52,61] used ML for multiclassification tasks. Due to significant variations in the diagnostic differences across these multiclassification tasks, a quantitative analysis was not feasible. Five studies [33,34,38,39,50] focused on fundus images–based DL to detect different types of myopic atrophy maculopathy in high myopia, with an accuracy ranging from 88% to 97%. Two studies [49,61] used optical coherence tomography (OCT) image–based DL to detect different types of myopic traction maculopathy in high myopia, with an accuracy ranging from 91% to 96%. One study [4] used fundus image–based DL to differentiate between normal, low-risk high myopia, and high-risk high myopia, with an accuracy of 99%. One study [52] applied fundus image–based DL to distinguish between normal, fundus tessellation, and pathologic myopia, with an accuracy of 94%, as illustrated in Table 3.

    Table 3. Results of machine learning for multiclassification tasks.
    First authorYearDiagnostic purposeTypes of artificial intelligenceModeling variablesGeneration of validation setAccuracy rate, %
    Tang et al [33]2022Classification of atrophic macular lesions in myopicCNNsa; DLbFundus photographs5-fold cross-validation + random sampling94
    Zhu et al [34]2023Classification of atrophic macular lesions in myopicNeural network; DLFundus photographsStratified 20-fold cross-validation90
    Wan et al [4]2021Normal, low, and high risk of high myopiaDCNNsc; DLFundus photographs5-fold cross-validation + random sampling99
    Wan et al [38]2023Classification of atrophic macular lesions in myopicDLFundus photographsRandom sampling95-97
    Sun et al [39]2023Classification of atrophic macular lesions in myopicDLFundus photographsExternal validation (multicenter)89.2
    Li et al [52]2022Differential diagnosis of normal, leopard print fundus, and pathological myopiaDCNN; DLFundus photographsInternal validation (random sampling) + external validation (multicenter)94
    He et al [61]2022Differential diagnosis of tractive macular degeneration and neovascular macular degeneration in high myopia, and othersDLOCTd imagesRandom sampling91-96
    Huang et al [49]2023Classification of tractive macular degeneration in high myopiaDLOCT imagesInternal validation (random sampling) + external validation (prospective)96
    Du et al [50]2021Classification of atrophic macular lesions in myopicDLFundus photographsRandom sampling88

    aCNN: convolutional neural network.

    bDL: deep learning.

    cDCNN: deep convolutional neural network.

    dOCT: Optical Coherence Tomography.


    Summary of the Main Findings

    This study comprehensively described the accuracy of ML in detecting high myopia, high myopia-associated glaucoma, and pathologic myopia. ML demonstrated exceptionally favorable performance in detecting high myopia, while DL was highly accurate in diagnosing pathologic myopia.

    Comparison With Previous Reviews

    Previous studies have also explored the detection accuracy of ML in this field. A systematic review has reported that fundus image– or OCT image–based DL can effectively diagnose and classify myopic maculopathy. Additionally, ML examination of the optic disc area can detect myopic maculopathy that may not be easily identified during clinical examination [14]. A recent meta-analysis based on only 11 studies evaluated the performance of DL in identifying pathological myopia based on fundus images. The SROC, specificity, and sensitivity were found to be 0.9905, 0.959 (95% CI 0.955-0.962), and 0.965 (95% CI 0.963-0.966), respectively [62]. In the previous meta-analysis, the 11 original studies all constructed fundus images-based DL models, and studies on conventional ML (non-DL) were not incorporated. The number of studies included in our review was further expanded, with a total of 20 studies on the performance of ML in diagnosing pathological myopia. Moreover, subgroup analysis was executed between conventional ML (non-DL) and DL. Our finding also indicated that DL demonstrated exceptionally favorable efficiency in detecting pathological myopia.

    As the understanding of the etiology of myopia deepens, growing evidence reveals risk factors for the onset or progression of myopia, including age, sex, parental myopia, susceptibility genes, and outdoor activities. For high myopia, early prediction appears to be more beneficial. Among the included studies, one incorporated 135 myopia-related single nucleotide polymorphisms to forecast the progression and onset of high myopia. ML for the prediction of high myopia was mainly based on genetic factors, environmental factors, and ocular clinical characteristics. ML showed an SROC of 0.96, sensitivity of 0.91, and specificity of 0.87, respectively [20], suggesting that ML methods can effectively identify high-risk individuals with high myopia, thus effectively preventing this condition, especially in minors.

    Glaucoma is a significant contributor to irreversible vision impairment and blindness all over the world. A 10-year study in Chinese individuals over the age of 40 years found that every 1 mm increase in axial length increased the risk of open-angle glaucoma by 1.72 times. In comparison to emmetropic and hyperopic eyes, highly myopic eyes had a 7.3 times higher risk of developing open-angle glaucoma [63]. Due to the changes in retinal structure caused by myopia, diagnosing glaucoma in myopic patients, especially those with high myopia, is challenging. Six studies were included to evaluate the diagnosis of high myopia glaucoma. Of them, 3 studies [28,29,32] used fundus OCT image-based DL techniques, while the remaining 3 [27,30,31] used non-DL ML (Lagrange multiplier, fully connected network, radial basis function network, decision tree, RF) approaches using OCT parameters, Heidelberg Retina Tomograph parameters, and ocular biometric parameters of patients. The findings indicated that ML yielded highly promising results in the detection of high myopia glaucoma.

    It was also noted that different ML methods, conventional ML and DL, showed significant differences in their ability to identify positive or outcome events. Conventional ML is often used to construct models with interpretable clinical features. Lately, various image-based ML methods have emerged. However, a significant challenge in this context is the requirement for manual annotation to facilitate ML. From this standpoint, manual annotation poses a formidable barrier to effectively mitigating the risk of bias. DL, on the other hand, enables intelligent processing of medical images and has been widely applied in various fields, including detecting diabetic retinopathy [8-10], retinopathy of prematurity [64,65], age-related macular degeneration [10], and glaucoma [11-13]. With the rapid development of ML, imaging data are increasingly becoming a valuable source for medical analysis. Multiple studies have demonstrated that images from various sources, including fundus images [66], external eye appearance [67], and refractive images [68], can effectively estimate a patient’s spherical refractive error, indicating the potential of imaging data in predicting the risk of myopia. This study also finds that image-based DL is more accurate than conventional ML, providing a theoretical basis for the creation of future intelligent tools.

    Additionally, the dataset used in ML demands considerable attention. Many studies are hampered by a limited number of cases, raising concerns about the robustness of the findings. Additionally, validation methods often depend heavily on internal validation, which may not fully capture the model’s generalizability. Hence, incorporating comprehensive patient data is essential for building a robust large-scale database, which will enable the development of ML models that are applicable to a broader population. Among the studies included, 7 [15,22,39,42,44,55,59] established ML models based on publicly available large databases.

    Limitations

    Although our review includes a larger number of studies than previous meta-analyses and provides an evidence-based basis for subsequent studies, this study has limitations. First, there were few studies on the prediction of high myopia, which limits the interpretation of our results, and clinically interpretable variables for predicting high myopia were not explained. Second, we did not conduct a subgroup analysis on the type of ML (conventional ML vs DL) owing to the insufficient number of included studies based on high myopia glaucoma and high myopia. Third, the majority of the models included in this study were assessed as having a high risk of bias, which may impact the interpretation of our results. Most included studies adopted a retrospective design, which might lead to selection bias.

    Conclusions

    In conclusion, this study comprehensively reviews and meta-analyzes the performance of ML in the diagnosis and prediction of high myopia, high myopia-associated glaucoma, and pathological myopia, providing valuable guidance and references for future research. Challenges exist within the emerging field of myopia prediction. With the development of new analytical methods and the accumulation of real medical datasets, future research holds the promise of improving the prediction of myopia onset and progression. This advancement brings us closer to the ultimate goal of identifying high-risk individuals promptly and implementing targeted interventions in clinical practice.

    Acknowledgments

    This work was supported by the Joint Project on Regional High-Incidence Diseases Research of Guangxi Natural Science Foundation under grant (2024GXNSFAA010322); Science and Technology Plan of Qingxiu District, Nanning City (2020016); Medical and Health Appropriate Technology Development and Promotion Application Project of Guangxi Zhuang Autonomous Region (S2018093); and Self-Funded Research Project of Health Commission of Guangxi Zhuang Autonomous Region (Z20210589).

    Data Availability

    All data generated or analyzed during this study are included in this published article. Further inquiries can be directed to the corresponding author.

    Conflicts of Interest

    None declared.

    Multimedia Appendix 1

    PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) checklist.

    DOCX File , 32 KB
    Multimedia Appendix 2

    Literature search strategy.

    DOCX File , 17 KB
    Multimedia Appendix 3

    Additional figures.

    DOCX File , 7517 KB
    1. Holden BA, Fricke TR, Wilson DA, Jong M, Naidoo KS, Sankaridurg P, et al. Global prevalence of myopia and high myopia and temporal trends from 2000 through 2050. Ophthalmology. 2016;123(5):1036-1042. [FREE Full text] [CrossRef] [Medline]
    2. Naidoo KS, Fricke TR, Frick KD, Jong M, Naduvilath TJ, Resnikoff S, et al. Potential lost productivity resulting from the global burden of myopia: systematic review, meta-analysis, and modeling. Ophthalmology. 2019;126(3):338-346. [FREE Full text] [CrossRef] [Medline]
    3. Flitcroft DI, He M, Jonas JB, Jong M, Naidoo K, Ohno-Matsui K, et al. IMI—defining and classifying myopia: a proposed set of standards for clinical and epidemiologic studies. Invest Ophthalmol Vis Sci. 2019;60(3):M20-M30. [FREE Full text] [CrossRef] [Medline]
    4. Wan C, Li H, Cao GF, Jiang Q, Yang WH. An artificial intelligent risk classification method of high myopia based on fundus images. J Clin Med. 2021;10(19):4488. [FREE Full text] [CrossRef] [Medline]
    5. Ikuno Y. Overview of the complications of high myopia. Retina. 2017;37(12):2347-2351. [CrossRef] [Medline]
    6. Miller RJH. Artificial intelligence in nuclear cardiology. Cardiol Clin. 2023;41(2):151-161. [CrossRef] [Medline]
    7. Majumder A, Sen D. Artificial intelligence in cancer diagnostics and therapy: current perspectives. Indian J Cancer. 2021;58(4):481-492. [FREE Full text] [CrossRef] [Medline]
    8. Ting DSW, Cheung CY, Lim G, Tan GSW, Quang ND, Gan A, 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. JAMA. 2017;318(22):2211-2223. [FREE Full text] [CrossRef] [Medline]
    9. Voets M, Møllersen K, Bongo LA. Reproduction study using public data of: development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. PLoS One. 2019;14(6):e0217541. [FREE Full text] [CrossRef] [Medline]
    10. González-Gonzalo C, Sánchez-Gutiérrez V, Hernández-Martínez P, Contreras I, Lechanteur YT, Domanian A, et al. Evaluation of a deep learning system for the joint automated detection of diabetic retinopathy and age-related macular degeneration. Acta Ophthalmol. 2020;98(4):368-377. [FREE Full text] [CrossRef] [Medline]
    11. Liu H, Li L, Wormstone IM, Qiao C, Zhang C, Liu P, et al. Development and validation of a deep learning system to detect glaucomatous optic neuropathy using fundus photographs. JAMA Ophthalmol. 2019;137(12):1353-1360. [FREE Full text] [CrossRef] [Medline]
    12. Hood DC, De Moraes CG. Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs. Ophthalmology. 2018;125(8):1207-1208. [CrossRef] [Medline]
    13. Mirzania D, Thompson AC, Muir KW. Applications of deep learning in detection of glaucoma: a systematic review. Eur J Ophthalmol. 2021;31(4):1618-1642. [CrossRef] [Medline]
    14. Li Y, Foo LL, Wong CW, Li J, Hoang QV, Schmetterer L, et al. Pathologic myopia: advances in imaging and the potential role of artificial intelligence. Br J Ophthalmol. 2023;107(5):600-606. [CrossRef] [Medline]
    15. Hemelings R, Elen B, Blaschko MB, Jacob J, Stalmans I, De Boever P. Pathological myopia classification with simultaneous lesion segmentation using deep learning. Comput Methods Programs Biomed. 2021;199:105920. [CrossRef] [Medline]
    16. Wolff RF, Moons KGM, Riley RD, Whiting PF, Westwood M, Collins GS, et al. PROBAST: a tool to assess the risk of bias and applicability of prediction model studies. Ann Intern Med. 2019;170(1):51-58. [FREE Full text] [CrossRef] [Medline]
    17. Hsiao V, Massoud E, Jensen C, Zhang Y, Hanlon BM, Hitchcock M, et al. Diagnostic accuracy of fine-needle biopsy in the detection of thyroid malignancy: a systematic review and meta-analysis. JAMA Surg. 2022;157(12):1105-1113. [FREE Full text] [CrossRef] [Medline]
    18. Foo LL, Lim GYS, Lanca C, Wong CW, Hoang QV, Zhang XJ, et al. Deep learning system to predict the 5-year risk of high myopia using fundus imaging in children. NPJ Digit Med. 2023;6(1):10. [FREE Full text] [CrossRef] [Medline]
    19. Wang H, Li L, Wang W, Wang H, Zhuang Y, Lu X, et al. Simulations to assess the performance of multifactor risk scores for predicting myopia prevalence in children and adolescents in China. Front Genet. 2022;13:861164. [FREE Full text] [CrossRef] [Medline]
    20. Chen Y, Han X, Guo X, Li Y, Lee J, He M. Contribution of genome-wide significant single nucleotide polymorphisms in myopia prediction: findings from a 10-year cohort of Chinese twin children. Ophthalmology. 2019;126(12):1607-1614. [FREE Full text] [CrossRef] [Medline]
    21. Huang Z, Xu X, Cheng W. Deep learning-based health management model application in extreme myopia eye vision monitoring and risk prediction. J Oncol. 2022;2022:4537021. [CrossRef] [Medline]
    22. Tan TE, Anees A, Chen C, Li S, Xu X, Li Z, et al. Retinal photograph-based deep learning algorithms for myopia and a blockchain platform to facilitate artificial intelligence medical research: a retrospective multicohort study. Lancet Digit Health. 2021;3(5):e317-e329. [FREE Full text] [CrossRef] [Medline]
    23. Choi KJ, Choi JE, Roh HC, Eun JS, Kim JM, Shin YK, et al. Deep learning models for screening of high myopia using optical coherence tomography. Sci Rep. 2021;11(1):21663. [CrossRef] [Medline]
    24. Guan J, Zhu Y, Hu Q, Ma S, Mu J, Li Z, et al. Prevalence patterns and onset prediction of high myopia for children and adolescents in southern China via real-world screening data: retrospective school–based study. J Med Internet Res. 2023;25:e39507. [FREE Full text] [CrossRef] [Medline]
    25. Zhao H, Ma Z, Guan Y, Li J, Wei Y. High myopia detection method on fundus images based on curriculum learning. IEEE; 2022. Presented at: 2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC); June 27, 2022; Los Alamitos, CA. [CrossRef]
    26. Dai S, Chen L, Lei T, Zhou C, Wen Y. Automatic detection of pathological myopia and high myopia on fundus images. IEEE; 2020. Presented at: 2020 IEEE International Conference on Multimedia and Expo (ICME); July 6-10, 2020:6-10; London, United Kingdom. URL: https://ieeexplore.ieee.org/document/9102787 [CrossRef]
    27. Li L, Zhu H, Zhang Z, Zhao L, Xu L, Jonas RA, et al. Neural network–based retinal nerve fiber layer profile compensation for glaucoma diagnosis in myopia: model development and validation. JMIR Med Inform. 2021;9(5):e22664. [FREE Full text] [CrossRef] [Medline]
    28. Lee YJ, Sun S, Kim YK, Jeoung JW, Park KH. Diagnostic ability of macular microvasculature with swept-source OCT angiography for highly myopic glaucoma using deep learning. Sci Rep. 2023;13(1):5209. [FREE Full text] [CrossRef] [Medline]
    29. Kim JA, Yoon H, Lee D, Kim M, Choi J, Lee EJ, et al. Development of a deep learning system to detect glaucoma using macular vertical optical coherence tomography scans of myopic eyes. Sci Rep. 2023;13(1):8040. [FREE Full text] [CrossRef] [Medline]
    30. Jeong Y, Kim YK, Jeoung JW, Park KH. Comparison of optical coherence tomography structural parameters for diagnosis of glaucoma in high myopia. JAMA Ophthalmol. 2023;141(7):631-639. [FREE Full text] [CrossRef] [Medline]
    31. Asaoka R, Iwase A, Tsutsumi T, Saito H, Otani S, Miyata K, et al. Combining multiple HRT parameters using the 'Random Forests' method improves the diagnostic accuracy of glaucoma in emmetropic and highly myopic eyes. Invest Ophthalmol Vis Sci. 2014;55(4):2482-2490. [CrossRef] [Medline]
    32. Bowd C, Belghith A, Rezapour J, Christopher M, Jonas JB, Hyman L, et al. Multimodal deep learning classifier for primary open angle glaucoma diagnosis using wide-field optic nerve head cube scans in eyes with and without high myopia. J Glaucoma. 2023;32(10):841-847. [CrossRef] [Medline]
    33. Tang J, Yuan M, Tian K, Wang Y, Wang D, Yang J, et al. An artificial-intelligence-based automated grading and lesions segmentation system for myopic maculopathy based on color fundus photographs. Transl Vis Sci Technol. 2022;11(6):16. [FREE Full text] [CrossRef] [Medline]
    34. Zhu SJ, Zhan HD, Wu MN, Zheng B, Liu BQ, Zhang SC, et al. Research on classification method of high myopic maculopathy based on retinal fundus images and optimized ALFA-Mix active learning algorithm. Int J Ophthalmol. 2023;16(7):995-1004. [FREE Full text] [CrossRef] [Medline]
    35. Wu Z, Cai W, Xie H, Chen S, Wang Y, Lei B, et al. Predicting optical coherence tomography–derived high myopia grades from fundus photographs using deep learning. Front Med. 2022;9:842680. [CrossRef] [Medline]
    36. Ye X, Wang J, Chen Y, Lv Z, He S, Mao J, et al. Automatic screening and identifying myopic maculopathy on optical coherence tomography images using deep learning. Transl Vis Sci Technol. 2021;10(13):10. [FREE Full text] [CrossRef] [Medline]
    37. Wang R, He J, Chen Q, Ye L, Sun D, Yin L, et al. Efficacy of a deep learning system for screening myopic maculopathy based on color fundus photographs. Ophthalmol Ther. 2023;12(1):469-484. [FREE Full text] [CrossRef] [Medline]
    38. Wan C, Fang J, Hua X, Chen L, Zhang S, Yang W. Automated detection of myopic maculopathy using five-category models based on vision outlooker for visual recognition. Front Comput Neurosci. 2023;17:1169464. [FREE Full text] [CrossRef] [Medline]
    39. Sun Y, Li Y, Zhang F, Zhao H, Liu H, Wang N, et al. A deep network using coarse clinical prior for myopic maculopathy grading. Comput Biol Med. 2023;154:106556. [CrossRef] [Medline]
    40. Sogawa T, Tabuchi H, Nagasato D, Masumoto H, Ikuno Y, Ohsugi H, et al. Accuracy of a deep convolutional neural network in the detection of myopic macular diseases using swept-source optical coherence tomography. PLoS One. 2020;15(4):e0227240. [FREE Full text] [CrossRef] [Medline]
    41. Du R, Xie S, Fang Y, Hagino S, Yamamoto S, Moriyama M, et al. Validation of soft labels in developing deep learning algorithms for detecting lesions of myopic maculopathy from optical coherence tomographic images. Asia Pac J Ophthalmol. 2022;11(3):227-236. [FREE Full text] [CrossRef] [Medline]
    42. Cui J, Zhang X, Xiong F, Chen CL. Pathological myopia image recognition strategy based on data augmentation and model fusion. J Healthc Eng. 2021;2021:5549779. [FREE Full text] [CrossRef] [Medline]
    43. Burlui D, Badralexe L, Bobocescu E, Brătucu E, Popescu-Băran D, Dragoncea C. [Intestinal carcinoid]. Rev Chir Oncol Radiol O R L Oftalmol Stomatol Chir. 1981;30(6):463-467. [Medline]
    44. Rauf N, Gilani SO, Waris A. Automatic detection of pathological myopia using machine learning. Sci Rep. 2021;11(1):16570. [FREE Full text] [CrossRef] [Medline]
    45. Park SJ, Ko T, Park CK, Kim YC, Choi IY. Deep learning model based on 3D optical coherence tomography images for the automated detection of pathologic myopia. Diagnostics. 2022;12(3):742. [FREE Full text] [CrossRef] [Medline]
    46. Lu L, Zhou E, Yu W, Chen B, Ren P, Lu Q, et al. Development of deep learning-based detecting systems for pathologic myopia using retinal fundus images. Commun Biol. 2021;4(1):1225. [FREE Full text] [CrossRef] [Medline]
    47. Lu L, Ren P, Tang X, Yang M, Yuan M, Yu W, et al. AI-model for identifying pathologic myopia based on deep learning algorithms of myopic maculopathy classification and "Plus" lesion detection in fundus images. Front Cell Dev Biol. 2021;9:719262. [FREE Full text] [CrossRef] [Medline]
    48. Li Y, Feng W, Zhao X, Liu B, Zhang Y, Chi W, et al. Development and validation of a deep learning system to screen vision-threatening conditions in high myopia using optical coherence tomography images. Br J Ophthalmol. 2022;106(5):633-639. [FREE Full text] [CrossRef] [Medline]
    49. Huang X, He S, Wang J, Yang S, Wang Y, Ye X. Lesion detection with fine-grained image categorization for myopic traction maculopathy (MTM) using optical coherence tomography. Med Phys. 2023;50(9):5398-5409. [CrossRef] [Medline]
    50. Du R, Xie S, Fang Y, Igarashi-Yokoi T, Moriyama M, Ogata S, et al. Deep learning approach for automated detection of myopic maculopathy and pathologic myopia in fundus images. Ophthalmol Retina. 2021;5(12):1235-1244. [CrossRef] [Medline]
    51. Crincoli E, Servillo A, Catania F, Sacconi R, Mularoni C, Battista M, et al. Artificial intelligence's role in differentiating the origin for subretinal bleeding in pathologic myopia. Retina. 2023;43(11):1881-1889. [CrossRef] [Medline]
    52. Li J, Wang L, Gao Y, Liang Q, Chen L, Sun X, et al. Automated detection of myopic maculopathy from color fundus photographs using deep convolutional neural networks. Eye Vis. 2022;9(1):13. [FREE Full text] [CrossRef] [Medline]
    53. Liu J, Wong DWK, Zhang Z, Lu S, Li H, Saw SM, et al. Automatic classification of pathological myopia in retinal fundus images using PAMELA. 2010. Presented at: SPIE Medical Imaging 2010; February 13-18, 2010; San Diego, CA. URL: https://doi.org/10.1117/12.844122 [CrossRef]
    54. Liu J, Wong DWK, Lim JH, Tan NM, Zhang Z, Li H, et al. Detection of pathological myopia by PAMELA with texture‐based features through an SVM approach. J Healthc Eng. 2010;1(1):1-11. [FREE Full text] [CrossRef]
    55. Baid U, Baheti B, Dutande P, Talbar S. Detection of pathological myopia and optic disc segmentation with deep convolutional neural networks. IEEE; 2019. Presented at: TENCON 2019—2019 IEEE Region 10 Conference (TENCON); October 17-20, 2019; Kochi, India. URL: https://ieeexplore.ieee.org/document/8929252 [CrossRef]
    56. Li S, Li M, Wu J, Li Y, Han J, Cao W, et al. Development and validation of a routine blood parameters–based model for screening the occurrence of retinal detachment in high myopia in the context of PPPM. EPMA J. 2023;14(2):219-233. [FREE Full text] [CrossRef] [Medline]
    57. Du Y, Chen Q, Fan Y, Zhu J, He J, Zou H, et al. Automatic identification of myopic maculopathy related imaging features in optic disc region via machine learning methods. J Transl Med. 2021;19(1):167. [FREE Full text] [CrossRef] [Medline]
    58. Kim YC, Chang DJ, Park SJ, Choi IY, Gong YS, Kim HA, et al. Machine learning prediction of pathologic myopia using tomographic elevation of the posterior sclera. Sci Rep. 2021;11(1):6950. [FREE Full text] [CrossRef] [Medline]
    59. Zhang Z, Xu Y, Liu J, Wong DWK, Kwoh CK, Saw SM, et al. Automatic diagnosis of pathological myopia from heterogeneous biomedical data. PLoS One. 2013;8(6):e65736. [FREE Full text] [CrossRef] [Medline]
    60. Hou XW, Yang JLX, Li DL, Tao YJ, Ke CF, Zhang B, et al. Machine learning–based integration of metabolomics characterisation predicts progression of ,mopic retinopathy in children and adolescents. Metabolites. 2023;13(2):301. [FREE Full text] [CrossRef] [Medline]
    61. He X, Ren P, Lu L, Tang X, Wang J, Yang Z, et al. Development of a deep learning algorithm for myopic maculopathy classification based on OCT images using transfer learning. Front Public Health. 2022;10:1005700. [FREE Full text] [CrossRef] [Medline]
    62. Prashar J, Tay N. Performance of artificial intelligence for the detection of pathological myopia from colour fundus images: a systematic review and meta-analysis. Eye. 2024;38(2):303-314. [FREE Full text] [CrossRef] [Medline]
    63. Wang YX, Yang H, Wei CC, Xu L, Wei WB, Jonas JB. High myopia as risk factor for the 10-year incidence of open-angle glaucoma in the Beijing eye study. Br J Ophthalmol. 2023;107(7):935-940. [FREE Full text] [CrossRef] [Medline]
    64. Brown JM, Campbell JP, Beers A, Chang K, Ostmo S, Chan RVP, et al. Automated diagnosis of plus disease in retinopathy of prematurity using deep convolutional neural networks. JAMA Ophthalmol. 2018;136(7):803-810. [FREE Full text] [CrossRef] [Medline]
    65. Mao J, Luo Y, Liu L, Lao J, Shao Y, Zhang M, et al. Automated diagnosis and quantitative analysis of plus disease in retinopathy of prematurity based on deep convolutional neural networks. Acta Ophthalmol. 2020;98(3):e339-e345. [FREE Full text] [CrossRef] [Medline]
    66. Han Y, Li W, Liu M, Wu Z, Zhang F, Liu X, et al. Application of an anomaly detection model to screen for ocular diseases using color retinal fundus images: design and evaluation study. J Med Internet Res. 2021;23(7):e27822. [FREE Full text] [CrossRef] [Medline]
    67. Yang Y, Li R, Lin D, Zhang X, Li W, Wang J, et al. Automatic identification of myopia based on ocular appearance images using deep learning. Ann Transl Med. 2020;8(11):705. [FREE Full text] [CrossRef] [Medline]
    68. Chun J, Kim Y, Shin KY, Han SH, Oh SY, Chung TY, et al. Deep learning-based prediction of refractive error using photorefraction images captured by a smartphone: model development and validation study. JMIR Med Inform. 2020;8(5):e16225. [FREE Full text] [CrossRef] [Medline]

    ‎
    CNN: convolutional neural network
    DCNN: deep convolutional neural network
    DL: deep learning
    DOR: diagnostic odds ratio
    LR: logistic regression
    MeSH: Medical Subjects Headings
    ML: machine learning
    NLR: negative likelihood ratio
    OCT: optical coherence tomography
    PLR: positive likelihood ratio
    PRISMA: Preferred Reporting Items for Systematic Reviews and Meta-Analyses
    RF: random forest
    SROC: summary receiver operating characteristic
    SVM: support vector machine

    Edited by A Mavragani; submitted 22.02.24; peer-reviewed by TE Komolafe, S Hansun; comments to author 20.05.24; revised version received 02.07.24; accepted 06.11.24; published 03.01.25.

    Copyright

    ©Huiyi Zuo, Baoyu Huang, Jian He, Liying Fang, Minli Huang. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 03.01.2025.

    This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in the Journal of Medical Internet Research (ISSN 1438-8871), is properly cited. The complete bibliographic information, a link to the original publication on https://www.jmir.org/, as well as this copyright and license information must be included.