{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T16:12:15Z","timestamp":1782835935508,"version":"3.54.5"},"reference-count":52,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T00:00:00Z","timestamp":1769385600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Cell Dev. Biol."],"abstract":"<jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>Early identification of children at risk for accelerated axial elongation is essential for implementing timely myopia control strategies. Quantitative parameters derived from color fundus photography (CFP) may capture subtle structural and microvascular features relevant to axial length (AL) progression, yet their predictive value remains insufficiently characterized. To develop and validate a machine learning\u2013based model integrating CFP-derived quantitative biomarkers and clinical characteristics to predict 1-year AL progression in school-aged children.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This cohort study included 693 children aged 6\u201310 years from Tianjin, China. AL progression &amp;gt;0.2\u00a0mm over 1\u00a0year was defined as significant elongation. Baseline clinical variables and 144 quantitative CFP metrics were evaluated. Feature selection was performed using Least Absolute Shrinkage and Selection Operator (LASSO) regression, logistic regression screening, and expert ophthalmologic assessment. Seven machine learning algorithms were developed using fivefold cross-validation, with hyperparameters optimized by grid search. Model performance was evaluated on an independent validation set using the area under the receiver operating characteristic (ROC) curve (AUC), F1 score, and other metrics. The best-performing model was interpreted using Shapley Additive Explanations (SHAP) and Local Interpretable Model-Agnostic Explanations (lime).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Of the 693 included children, 457 (65.9%) exhibited AL progression &amp;gt;0.2\u00a0mm. LASSO regression selected 39 candidate variables, and 12 predictors were ultimately incorporated into the model construction. Among all algorithms, the Random Forest (RF) model achieved the best discrimination, with an AUC of 0.961 (95% CI: 0.933\u20130.984) and the highest F1 score. Decision curve analysis (DCA) demonstrated a favorable net benefit across clinically relevant thresholds. SHAP analysis indicated that retinal venous density, venous fractal dimension, presence of leopard-spot lesions, vascular fractal dimension, and inferior-region vascular density were among the most influential predictors of AL progression.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The RF model, which combines clinical characteristics with CFP-derived quantitative biomarkers, accurately predicts short-term AL progression in children. Retinal microvascular and fundus structural parameters significantly contributed to model performance, underscoring their potential as early indicators of myopic AL elongation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fcell.2026.1753213","type":"journal-article","created":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T07:20:37Z","timestamp":1769412037000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Quantitative color fundus photography parameters as potential biomarkers of axial length progression: evidence from a machine learning cohort study"],"prefix":"10.3389","volume":"14","author":[{"given":"Zixun","family":"Wang","sequence":"first","affiliation":[{"name":"Tianjin Key Laboratory of Retinal Functions and Diseases, Tianjin Branch of National Clinical Research Center for Ocular Disease, Eye Institute and School of Optometry, Tianjin Medical University Eye Hospital","place":["Tianjin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feifei","family":"Han","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory of Retinal Functions and Diseases, Tianjin Branch of National Clinical Research Center for Ocular Disease, Eye Institute and School of Optometry, Tianjin Medical University Eye Hospital","place":["Tianjin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoling","family":"Zhang","sequence":"additional","affiliation":[{"name":"Handan Eye Hospital (The Third Hospital of Handan)","place":["Handan, Hebei, China"]},{"name":"Tianjin Key Laboratory of Retinal Functions and Diseases, Tianjin Branch of National Clinical Research Center for Ocular Disease, Eye Institute and School of Optometry, Tianjin Medical University Eye Hospital","place":["Tianjin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingjie","family":"Ding","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory of Retinal Functions and Diseases, Tianjin Branch of National Clinical Research Center for Ocular Disease, Eye Institute and School of Optometry, Tianjin Medical University Eye Hospital","place":["Tianjin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingtao","family":"Yu","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory of Retinal Functions and Diseases, Tianjin Branch of National Clinical Research Center for Ocular Disease, Eye Institute and School of Optometry, Tianjin Medical University Eye Hospital","place":["Tianjin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xueshuo","family":"Xie","sequence":"additional","affiliation":[{"name":"Haihe Lab of ITAI, Naikai University","place":["Tianjin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiqing","family":"Li","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory of Retinal Functions and Diseases, Tianjin Branch of National Clinical Research Center for Ocular Disease, Eye Institute and School of Optometry, Tianjin Medical University Eye Hospital","place":["Tianjin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bei","family":"Du","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory of Retinal Functions and Diseases, Tianjin Branch of National Clinical Research Center for Ocular Disease, Eye Institute and School of Optometry, Tianjin Medical University Eye Hospital","place":["Tianjin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruihua","family":"Wei","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory of Retinal Functions and Diseases, Tianjin Branch of National Clinical Research Center for Ocular Disease, Eye Institute and School of Optometry, Tianjin Medical University Eye Hospital","place":["Tianjin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,1,26]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"106156","DOI":"10.1016\/j.compbiomed.2022.106156","article-title":"Explanatory classification of CXR images into COVID-19, pneumonia and tuberculosis using deep learning and XAI","volume":"150","author":"Bhandari","year":"2022","journal-title":"Comput. Biology Medicine"},{"key":"B2","doi-asserted-by":"publisher","first-page":"e489","DOI":"10.1016\/s2214-109x(20)30488-5","article-title":"The lancet global health commission on global eye health: vision beyond 2020","volume":"9","author":"Burton","year":"2021","journal-title":"Lancet. Glob. Health"},{"key":"B3","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1167\/iovs.66.13.33","article-title":"Acceleration of myopic shifts in refraction and axial elongation begins in the premyopia stage","volume":"66","author":"Cai","year":"2025","journal-title":"Investigative Ophthalmology and Visual Science"},{"key":"B4","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1177\/0272989x221143058","article-title":"Decision curve analysis for personalized treatment choice between multiple options","volume":"43","author":"Chalkou","year":"2023","journal-title":"Med. Decision Making"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1329263","DOI":"10.3389\/fbioe.2024.1329263","article-title":"Progress in clinical research and applications of retinal vessel quantification technology based on fundus imaging","volume":"12","author":"Chen","year":"2024","journal-title":"Front. Bioengineering Biotechnology"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1645015","DOI":"10.3389\/fmed.2025.1645015","article-title":"Differences in macular structure and microvasculature between high myopia and non-high myopia","volume":"12","author":"Chen","year":"2025","journal-title":"Front. Medicine"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1961","DOI":"10.1038\/s41433-019-0573-1","article-title":"Deep perifoveal vessel density as an indicator of capillary loss in high myopia","volume":"33","author":"Cheng","year":"2019","journal-title":"Eye Lond. Engl."},{"key":"B8","doi-asserted-by":"publisher","first-page":"101474","DOI":"10.1016\/j.clae.2021.101474","article-title":"Machine learning algorithm improves accuracy of ortho-K lens fitting in vision shaping treatment","volume":"45","author":"Fan","year":"2022","journal-title":"Contact Lens and Anterior Eye"},{"key":"B9","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1111\/aos.12908","article-title":"Myopia and\/or longer axial length are protective against diabetic retinopathy: a meta-analysis","volume":"94","author":"Fu","year":"2016","journal-title":"Acta Ophthalmologica"},{"key":"B10","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1111\/aos.15291","article-title":"Lower fractal dimension of retinal vessel for patients with birdshot chorioretinopathy","volume":"101","author":"Furnon","year":"2023","journal-title":"Acta Ophthalmologica"},{"key":"B11","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1167\/tvst.13.6.22","article-title":"Quantification of fundus tessellation reflects early myopic maculopathy in a large-scale population of children and adolescents","volume":"13","author":"Gong","year":"2024","journal-title":"Transl. Vision Science and Technology"},{"key":"B12","doi-asserted-by":"publisher","first-page":"2867","DOI":"10.3390\/jcm13102867","article-title":"Ocular biometry percentile curves and their relation to myopia development in Indian children","volume":"13","author":"Gopalakrishnan","year":"2024","journal-title":"J. Clinical Medicine"},{"key":"B13","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1186\/s13054-024-05138-0","article-title":"Interpretable machine learning model for new-onset atrial fibrillation prediction in critically ill patients: a multi-center study","volume":"28","author":"Guan","year":"2024","journal-title":"Crit. Care London, Engl."},{"key":"B14","doi-asserted-by":"publisher","first-page":"29381","DOI":"10.1038\/s41598-025-13414-4","article-title":"Choroidal vascular alterations in diabetic retinopathy and their association with macular microvascular parameters","volume":"15","author":"Guan","year":"2025","journal-title":"Sci. Reports"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1595","DOI":"10.1016\/j.ophtha.2009.11.003","article-title":"Long-term pattern of progression of myopic maculopathy: a natural history study","volume":"117","author":"Hayashi","year":"2010","journal-title":"Ophthalmology"},{"key":"B16","doi-asserted-by":"publisher","first-page":"100086","DOI":"10.1016\/j.apjo.2024.100086","article-title":"Deep learning-enabled vasculometry depicts phased lesion patterns in high myopia progression","volume":"13","author":"He","year":"2024","journal-title":"Asia-Pacific Journal Ophthalmology Phila. Pa."},{"key":"B17","doi-asserted-by":"publisher","first-page":"1036","DOI":"10.1016\/j.ophtha.2016.01.006","article-title":"Global prevalence of myopia and high myopia and temporal trends from 2000 through 2050","volume":"123","author":"Holden","year":"2016","journal-title":"Ophthalmology"},{"key":"B18","doi-asserted-by":"publisher","first-page":"31416","DOI":"10.1038\/s41598-025-15605-5","article-title":"Integrating biometric and multimodal imaging data for early prediction of myopia onset","volume":"15","author":"Hu","year":"2025","journal-title":"Sci. Reports"},{"key":"B19","doi-asserted-by":"publisher","first-page":"466","DOI":"10.1186\/s12886-025-04303-5","article-title":"Orthokeratology for myopia control: a three-year longitudinal study on axial length modulation influenced by baseline age and spherical equivalent","volume":"25","author":"Hu","year":"2025","journal-title":"BMC Ophthalmology"},{"key":"B20","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1186\/s12931-024-02874-3","article-title":"An explainable machine learning-based model to predict intensive care unit admission among patients with community-acquired pneumonia and connective tissue disease","volume":"25","author":"Huang","year":"2024","journal-title":"Respir. Research"},{"key":"B21","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1167\/iovs.62.4.17","article-title":"Rapid myopic progression in childhood is associated with teenage high myopia","volume":"62","author":"Lanca","year":"2021","journal-title":"Investigative Ophthalmology and Visual Science"},{"key":"B22","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1001\/jamaophthalmol.2021.5067","article-title":"Incidence and progression of myopia in early adulthood","volume":"140","author":"Lee","year":"2022","journal-title":"JAMA Ophthalmology"},{"key":"B23","doi-asserted-by":"publisher","first-page":"3847","DOI":"10.1038\/s41433-023-02629-2","article-title":"Association between choriocapillaris perfusion and axial elongation in children using defocus incorporated multiple segments (DIMS) spectacle lenses","volume":"37","author":"Li","year":"2023","journal-title":"Eye Lond. Engl."},{"key":"B24","doi-asserted-by":"publisher","first-page":"1435","DOI":"10.1111\/opo.13530","article-title":"Axial elongation as a marker to identify obvious myopic shift in non-myopic eyes of Chinese children","volume":"45","author":"Liu","year":"2025","journal-title":"Ophthalmic and Physiological Optics"},{"key":"B25","doi-asserted-by":"publisher","first-page":"35277","DOI":"10.1038\/s41598-025-18400-4","article-title":"Prevalence and associated factors of myopia and axial length-related visual impairment in children and adolescents aged 4-18 years","volume":"15","author":"Mingming","year":"2025","journal-title":"Sci. Reports"},{"key":"B26","doi-asserted-by":"publisher","first-page":"95","DOI":"10.3341\/kjo.2022.0059","article-title":"Deep learning-based prediction of axial length using ultra-widefield fundus photography","volume":"37","author":"Oh","year":"2023","journal-title":"Korean Journal Ophthalmology KJO"},{"key":"B27","doi-asserted-by":"publisher","first-page":"101484","DOI":"10.1016\/j.lanwpc.2025.101484","article-title":"Prevalence and temporal trends in myopia and high myopia children in China: a systematic review and meta-analysis with projections from 2020 to 2050","volume":"55","author":"Pan","year":"2025","journal-title":"Lancet Regional Health. West. Pac."},{"key":"B28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1615\/CritRevBiomedEng.2024055532","article-title":"Mathematical probe of nanoparticle aggregation in capillary-tissue system applying fractal model","volume":"53","author":"Prasad","year":"2025","journal-title":"Crit. Reviews Biomedical Engineering"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1276","DOI":"10.1002\/sim.7992","article-title":"Minimum sample size for developing a multivariable prediction model: PART II - binary and time-to-event outcomes","volume":"38","author":"Riley","year":"2019","journal-title":"Statistics Medicine"},{"key":"B30","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1186\/s40942-024-00570-4","article-title":"Longitudinal changes of funduscopic optic disc size, color and cup-to-disc ratio in school children","volume":"10","author":"Sameshima","year":"2024","journal-title":"Int. Journal Retina Vitreous"},{"key":"B31","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1167\/iovs.66.4.33","article-title":"Three-dimensional characteristics of choroidal vasculature associated with filling delay in central serous chorioretinopathy","volume":"66","author":"Sekiryu","year":"2025","journal-title":"Investigative Ophthalmology and Visual Science"},{"key":"B32","doi-asserted-by":"publisher","first-page":"168100","DOI":"10.1016\/j.bbadis.2025.168100","article-title":"Integrated bioinformatics and machine learning analysis identify CROT as a regulator of immunological features in idiopathic pulmonary fibrosis","volume":"1872","author":"Song","year":"2026","journal-title":"Biochimica biophysica acta. Mol. basis Dis."},{"key":"B33","doi-asserted-by":"publisher","first-page":"2121","DOI":"10.1007\/s00417-024-06403-2","article-title":"Morphological characteristics of the foveal avascular zone in pathological myopia and its relationship with macular structure and microcirculation","volume":"262","author":"Sui","year":"2024","journal-title":"Graefe's Archive Clinical Experimental Ophthalmology"},{"key":"B34","doi-asserted-by":"publisher","first-page":"2563752","DOI":"10.1080\/07853890.2025.2563752","article-title":"Tracking myopia development through axial length progression: a retrospective longitudinal study","volume":"57","author":"Tao","year":"2025","journal-title":"Ann. Medicine"},{"key":"B35","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1186\/s12916-019-1466-7","article-title":"Calibration: the achilles heel of predictive analytics","volume":"17","author":"Van Calster","year":"2019","journal-title":"BMC Medicine"},{"key":"B36","doi-asserted-by":"publisher","first-page":"532","DOI":"10.3390\/medicina61030532","article-title":"The significance of OCTA in studying vessel density and retinal thickness in individuals with myopia","volume":"61","author":"Veselinovi\u0107","year":"2025","journal-title":"Med. Kaunas. Lith."},{"key":"B37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.diabres.2015.10.020","article-title":"Myopia and diabetic retinopathy: a systematic review and meta-analysis","volume":"111","author":"Wang","year":"2016","journal-title":"Diabetes Research Clinical Practice"},{"key":"B38","doi-asserted-by":"publisher","first-page":"1296","DOI":"10.1038\/s41433-023-02885-2","article-title":"Development and validation of a deep learning model to predict axial length from ultra-wide field images","volume":"38","author":"Wang","year":"2024","journal-title":"Eye Lond. Engl."},{"key":"B39","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1167\/tvst.14.8.38","article-title":"Myopic-net: deep learning-based direct identification of myopia onset and progression","volume":"14","author":"Wang","year":"2025","journal-title":"Transl. Vision Science and Technology"},{"key":"B40","doi-asserted-by":"publisher","first-page":"104475","DOI":"10.1016\/j.pdpdt.2025.104475","article-title":"Evaluating choroidal vascular changes in young adults with high myopia utilizing swept source optical coherence tomography angiography","volume":"51","author":"Wang","year":"2025","journal-title":"Photodiagnosis Photodynamic Therapy"},{"key":"B41","doi-asserted-by":"publisher","first-page":"1260","DOI":"10.1016\/j.ophtha.2025.06.010","article-title":"Establishment of myopia occurrence prediction model in children without myopia using cycloplegic refraction and prior axial length change","volume":"132","author":"Xu","year":"2025","journal-title":"Ophthalmology"},{"key":"B42","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1167\/tvst.13.5.23","article-title":"Convolutional neural network-based prediction of axial length using color fundus photography","volume":"13","author":"Yang","year":"2024","journal-title":"Transl. Vision Science and Technology"},{"key":"B43","doi-asserted-by":"publisher","first-page":"908","DOI":"10.1111\/ceo.14585","article-title":"Comparison of the peripapillary structure-vessel density relationship before and after axial length magnification correction using different methods","volume":"53","author":"Yang","year":"2025","journal-title":"Clin. and Experimental Ophthalmology"},{"key":"B44","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1001\/jamaophthalmol.2025.1513","article-title":"Fundus refraction offset as an individualized myopia biomarker","volume":"143","author":"Yii","year":"2025","journal-title":"JAMA Ophthalmology"},{"key":"B45","doi-asserted-by":"publisher","first-page":"1146291","DOI":"10.3389\/fmed.2023.1146291","article-title":"Influencing factors associated with high myopia in Chinese college students","volume":"10","author":"Zhang","year":"2023","journal-title":"Front. Medicine"},{"key":"B46","doi-asserted-by":"publisher","first-page":"ceo.70024","DOI":"10.1111\/ceo.70024","article-title":"Myopia progression management: current trends and future directions","author":"Zhang","year":"2025","journal-title":"Clin. and Experimental Ophthalmology"},{"key":"B47","doi-asserted-by":"publisher","first-page":"43729","DOI":"10.1038\/s41598-025-27848-3","article-title":"Predicting myopia risk using a machine learning model based on fundus imageomics","volume":"15","author":"Zhang","year":"2025","journal-title":"Sci. Rep."},{"key":"B48","doi-asserted-by":"publisher","first-page":"7104","DOI":"10.1038\/s41598-022-11087-x","article-title":"Hemodynamic and morphological changes of the central retinal artery in myopic eyes","volume":"12","author":"Zhao","year":"2022","journal-title":"Sci. Reports"},{"key":"B49","doi-asserted-by":"publisher","first-page":"284","DOI":"10.1016\/j.jad.2025.02.063","article-title":"A machine-learning-derived online prediction model for depression risk in COPD patients: a retrospective cohort study from CHARLS","volume":"377","author":"Zhao","year":"2025","journal-title":"J. Affective Disorders"},{"key":"B50","doi-asserted-by":"publisher","first-page":"466","DOI":"10.1186\/s12916-022-02620-w","article-title":"Retinal age gap as a predictive biomarker of stroke risk","volume":"20","author":"Zhu","year":"2022","journal-title":"BMC Medicine"},{"key":"B51","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1186\/s12886-025-04425-w","article-title":"Three-dimensional choroidal parameter differences in myopic anisometropia","volume":"25","author":"Zhu","year":"2025","journal-title":"BMC Ophthalmology"},{"key":"B52","doi-asserted-by":"publisher","first-page":"1609639","DOI":"10.3389\/fbioe.2025.1609639","article-title":"Retinal features as predictive indicators for high myopia: insights from explainable multi-machine learning models","volume":"13","author":"Zou","year":"2025","journal-title":"Front. Bioengineering Biotechnology"}],"container-title":["Frontiers in Cell and Developmental Biology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcell.2026.1753213\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T09:12:01Z","timestamp":1771924321000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcell.2026.1753213\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,26]]},"references-count":52,"alternative-id":["10.3389\/fcell.2026.1753213"],"URL":"https:\/\/doi.org\/10.3389\/fcell.2026.1753213","relation":{},"ISSN":["2296-634X"],"issn-type":[{"value":"2296-634X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,26]]},"article-number":"1753213"}}