{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T23:49:47Z","timestamp":1787701787206,"version":"build-2784847793"},"reference-count":30,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T00:00:00Z","timestamp":1747872000000},"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><jats:title>Objective<\/jats:title><jats:p>To develop and validate machine learning (ML) models for predicting cycloplegic spherical equivalent refraction (SER) using non-cycloplegic parameters, addressing challenges in pediatric ophthalmic assessments.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>A prospective cohort of 2,274 Chinese children (4,548 eyes) aged 3\u223c16 years was stratified into development (<jats:italic>n<\/jats:italic> = 1819) and validation (<jats:italic>n<\/jats:italic> = 455) datasets. Six ML models (linear regression, random forest, extreme gradient boosting, multilayer perceptron, support vector machine, and light gradient boosting machine) were trained on demographics, non-cycloplegic refractive error, and ocular biometrics. Model performance was evaluated using <jats:italic>R<\/jats:italic><jats:sup><jats:italic>2<\/jats:italic><\/jats:sup>, mean error (ME), mean absolute error (MAE), and clinical accuracy (proportions within \u00b10.50 D\/\u00b11.00 D).<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>In the validation dataset, ML models predicted cycloplegic SER with high <jats:italic>R<\/jats:italic><jats:sup><jats:italic>2<\/jats:italic><\/jats:sup> (0.920\u223c0.934), low ME (\u22120.004\u223c0.015 D) and MAE (0.385\u223c0.413 D). The multilayer perceptron model achieved the highest accuracy (<jats:italic>R<\/jats:italic><jats:sup><jats:italic>2<\/jats:italic><\/jats:sup> = 0.934, MAE = 0.385 D), with 73.08% and 94.29% of predictions within \u00b10.50 D and \u00b11.00 D, respectively. Performance was optimal in children aged 7\u223c10 years (77.17\u223c79.70% within \u00b10.50 D) and those with low myopia (\u22123.00 to \u22120.50 D; 83.09\u223c83.56% within \u00b10.50 D). Non-cycloplegic measurements systematically overestimated myopia (mean difference: \u22120.39 \u00b1 0.71 D, <jats:italic>P<\/jats:italic> &amp;lt; 0.001), particularly in younger children and hyperopic eyes.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>ML models provide accurate estimates of cycloplegic SER using non-cycloplegic parameters, offering a practical alternative for pediatric refractive assessments when cycloplegia is infeasible.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fcell.2025.1608494","type":"journal-article","created":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T05:26:33Z","timestamp":1747891593000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Machine learning-driven prediction of cycloplegic refractive error in Chinese children"],"prefix":"10.3389","volume":"13","author":[{"given":"Bichi","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fuyue","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiaochu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Ruan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuanyan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maoyuan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suzhong","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruzhi","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,5,22]]},"reference":[{"key":"B1","volume-title":"Neural networks","author":"Abu-Mostafa","year":"2012"},{"key":"B2","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"B3","doi-asserted-by":"publisher","first-page":"478","DOI":"10.3390\/jcm11030478","article-title":"Accuracy of machine learning assisted detection of keratoconus: a systematic review and meta-analysis","volume":"11","author":"Cao","year":"2022","journal-title":"J. Clin. Med."},{"key":"B4","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1167\/tvst.12.1.18","article-title":"Evaluation of multiple machine learning models for predicting number of anti-VEGF injections in the comparison of AMD treatment trials (CATT)","volume":"12","author":"Chandra","year":"2023","journal-title":"Transl. Vis. Sci. Technol."},{"key":"B5","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1016\/j.oret.2023.11.010","article-title":"Predicting visual acuity responses to anti-VEGF treatment in the comparison of age-related macular degeneration treatments trials using machine learning","volume":"8","author":"Chandra","year":"2024","journal-title":"Ophthalmol. Retina"},{"key":"B6","doi-asserted-by":"crossref","DOI":"10.1145\/2939672.2939785","article-title":"XGBoost: a scalable tree boosting system","volume-title":"Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining","author":"Chen","year":"2016"},{"key":"B7","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach. Learn."},{"key":"B8","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1111\/opo.12629","article-title":"Comparison of retinoscopy results with and without 1% cyclopentolate in school-aged children","volume":"39","author":"Doherty","year":"2019","journal-title":"Ophthalmic Physiol. Opt."},{"key":"B9","doi-asserted-by":"publisher","first-page":"1096330","DOI":"10.3389\/fpubh.2023.1096330","article-title":"Prediction of spherical equivalent difference before and after cycloplegia in school-age children with machine learning algorithms","volume":"11","author":"Du","year":"2023","journal-title":"Front. Public Health"},{"key":"B10","doi-asserted-by":"publisher","first-page":"M20","DOI":"10.1167\/iovs.18-25957","article-title":"IMI - defining and classifying myopia: a proposed set of standards for clinical and epidemiologic studies","volume":"60","author":"Flitcroft","year":"2019","journal-title":"Invest Ophthalmol. Vis. Sci."},{"key":"B11","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1167\/tvst.5.1.5","article-title":"Axial length\/corneal radius of curvature ratio and myopia in 3-year-old children","volume":"5","author":"Foo","year":"2016","journal-title":"Transl. Vis. Sci. Technol."},{"key":"B12","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1016\/j.ajo.2007.03.041","article-title":"Necessity of cycloplegia for assessing refractive error in 12-year-old children: a population-based study","volume":"144","author":"Fotedar","year":"2007","journal-title":"Am. J. Ophthalmol."},{"key":"B13","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1080\/09286586.2021.1999986","article-title":"Effect of cycloplegia on refractive error measure in Chinese school students","volume":"29","author":"Gu","year":"2022","journal-title":"Ophthalmic Epidemiol."},{"key":"B14","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1136\/bjophthalmol-2021-319431","article-title":"Normative data and percentile curves for axial length and axial length\/corneal curvature in Chinese children and adolescents aged 4-18 years","volume":"107","author":"He","year":"2023","journal-title":"Br. J. Ophthalmol."},{"key":"B15","doi-asserted-by":"publisher","first-page":"e0111766","DOI":"10.1371\/journal.pone.0111766","article-title":"Axial length\/corneal radius ratio: association with refractive state and role on myopia detection combined with visual acuity in Chinese schoolchildren","volume":"10","author":"He","year":"2015","journal-title":"PLoS One"},{"key":"B16","doi-asserted-by":"publisher","first-page":"e0117482","DOI":"10.1371\/journal.pone.0117482","article-title":"Effect of cycloplegia on the refractive status of children: the Shandong children eye study","volume":"10","author":"Hu","year":"2015","journal-title":"PLoS One"},{"key":"B17","doi-asserted-by":"publisher","first-page":"4846","DOI":"10.1167\/iovs.07-0101","article-title":"Variation of the contribution from axial length and other oculometric parameters to refraction by age and ethnicity","volume":"48","author":"Ip","year":"2007","journal-title":"Invest Ophthalmol. Vis. Sci."},{"key":"B18","article-title":"LightGBM: a highly efficient gradient boosting decision tree","volume-title":"Advances in neural information processing systems","author":"Ke","year":"2017"},{"key":"B19","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1007\/s10384-006-0410-5","article-title":"Axial length measurement using partial coherence interferometry in myopic children: repeatability of the measurement and comparison with refractive components","volume":"51","author":"Kimura","year":"2007","journal-title":"Jpn. J. Ophthalmol."},{"key":"B20","volume-title":"Regression - Modelle, Methoden und Anwendungen","author":"Ludwig Fahrmeir","year":"2009"},{"key":"B21","doi-asserted-by":"publisher","first-page":"e0248494","DOI":"10.1371\/journal.pone.0248494","article-title":"Prediction of cycloplegic refraction for noninvasive screening of children for refractive error","volume":"16","author":"Magome","year":"2021","journal-title":"PLoS One"},{"key":"B22","doi-asserted-by":"publisher","first-page":"929","DOI":"10.1097\/01.OPX.0000147681.94971.28","article-title":"Accommodative lag using dynamic retinoscopy: age norms for school-age children","volume":"81","author":"McClelland","year":"2004","journal-title":"Optom. Vis. Sci."},{"key":"B23","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1111\/aos.12642","article-title":"Cycloplegic refraction is the gold standard for epidemiological studies","volume":"93","author":"Morgan","year":"2015","journal-title":"Acta Ophthalmol."},{"key":"B24","doi-asserted-by":"publisher","first-page":"e633","DOI":"10.1111\/aos.13569","article-title":"Comparison of noncycloplegic and cycloplegic autorefraction in categorizing refractive error data in children","volume":"95","author":"Sankaridurg","year":"2017","journal-title":"Acta Ophthalmol."},{"key":"B25","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1167\/tvst.11.1.15","article-title":"Prediction for cycloplegic refractive error in Chinese school students: model development and validation","volume":"11","author":"Wang","year":"2022","journal-title":"Transl. Vis. Sci. Technol."},{"key":"B26","doi-asserted-by":"publisher","first-page":"e23863","DOI":"10.2196\/23863","article-title":"Performance and limitation of machine learning algorithms for diabetic retinopathy screening: meta-analysis","volume":"23","author":"Wu","year":"2021","journal-title":"J. Med. Internet Res."},{"key":"B27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.ajo.2021.12.008","article-title":"Performances of machine learning in detecting glaucoma using fundus and retinal optical coherence tomography images: a meta-analysis","volume":"237","author":"Wu","year":"2022","journal-title":"Am. J. Ophthalmol."},{"key":"B28","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1167\/tvst.13.8.16","article-title":"Machine learning models for predicting cycloplegic refractive error and myopia status based on non-cycloplegic data in Chinese students","volume":"13","author":"Ying","year":"2024","journal-title":"Transl. Vis. Sci. Technol."},{"key":"B29","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1097\/00006324-200401000-00010","article-title":"Accuracy of noncycloplegic autorefraction in school-age children in China","volume":"81","author":"Zhao","year":"2004","journal-title":"Optom. Vis. Sci."},{"key":"B30","doi-asserted-by":"publisher","first-page":"2115","DOI":"10.4103\/ijo.Ijo_2989_22","article-title":"Prediction of spherical equivalent refraction and axial length in children based on machine learning","volume":"71","author":"Zhu","year":"2023","journal-title":"Indian J. Ophthalmol."}],"container-title":["Frontiers in Cell and Developmental Biology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcell.2025.1608494\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T05:26:36Z","timestamp":1747891596000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcell.2025.1608494\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,22]]},"references-count":30,"alternative-id":["10.3389\/fcell.2025.1608494"],"URL":"https:\/\/doi.org\/10.3389\/fcell.2025.1608494","relation":{},"ISSN":["2296-634X"],"issn-type":[{"value":"2296-634X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,22]]},"article-number":"1608494"}}