{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T18:37:26Z","timestamp":1777055846469,"version":"3.51.4"},"reference-count":28,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T00:00:00Z","timestamp":1776988800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>This study aimed to develop a machine learning-based prediction model for myopia progression using ocular biometric parameters to provide an objective assessment tool for clinical practice.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A retrospective analysis was conducted on patients treated at Shanghai Parkway Health Ophthalmology Department as the training set, and myopic individuals from the Optometry Center of Peking University People\u2019s Hospital as the validation set. Demographic and biometric data were collected, including central corneal thickness (CCT), axial length (AL), corneal curvature (K-value), anterior chamber depth (ACD), corneal diameter (WTW), and pupil size (PS). Seven machine learning models (e.g., XGBoost, random forest, support vector machine) were employed for modeling, with performance optimized via 5-fold cross-validation. Model accuracy was evaluated using mean squared error (MSE) and the coefficient of determination (R\u00b2), and variable importance was analyzed.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>No statistically significant differences were observed in baseline characteristics between the training and validation sets (all P\u2009&gt;\u20090.05). The XGBoost model demonstrated the best performance, achieving R\u00b2\u2009=\u20090.913 (MSE\u2009=\u20090.005) on the training set and R\u00b2\u2009=\u20090.766 (MSE\u2009=\u20090.016) on the test set. Variable importance analysis revealed pupil size (score 100) and corneal thickness (40.88) as the key predictors of axial elongation rate, followed by age of onset (17.96).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The machine learning-based prediction model effectively utilizes ocular biometric data to assess myopia progression risk, with pupil size and corneal thickness identified as core predictive factors. This model provides a quantitative tool for early clinical intervention. Future studies should expand the sample size and incorporate additional biomarkers to optimize performance.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0348085","type":"journal-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T17:43:35Z","timestamp":1777052615000},"page":"e0348085","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine learning identifies pupil size and corneal thickness as key predictors of axial elongation rate"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1744-5167","authenticated-orcid":true,"given":"Peng","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sitong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingli","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1157-7520","authenticated-orcid":true,"given":"Yan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2026,4,24]]},"reference":[{"issue":"1","key":"pone.0348085.ref001","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1038\/s41572-020-00231-4","article-title":"Myopia","volume":"6","author":"PN Baird","year":"2020","journal-title":"Nat Rev Dis Primers"},{"issue":"4","key":"pone.0348085.ref002","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1080\/2576117X.2024.2387379","article-title":"Growing Pains: The Incidence and Prevalence of Myopia from 1950 to 2050","volume":"74","author":"K Arnoldi","year":"2024","journal-title":"J Binocul Vis Ocul Motil"},{"issue":"8","key":"pone.0348085.ref003","doi-asserted-by":"crossref","first-page":"4514","DOI":"10.1167\/iovs.14-13935","article-title":"Central and Peripheral Corneal Power Change in Myopic Orthokeratology and Its Relationship With 2-Year Axial Length Change","volume":"56","author":"Y Zhong","year":"2015","journal-title":"Invest Ophthalmol Vis Sci"},{"issue":"6","key":"pone.0348085.ref004","doi-asserted-by":"crossref","first-page":"100123","DOI":"10.1016\/j.apjo.2024.100123","article-title":"Axial elongation in nonpathologic high myopia: Ocular structural changes and glaucoma diagnostic challenges","volume":"13","author":"K Kong","year":"2024","journal-title":"Asia Pac J Ophthalmol (Phila)"},{"issue":"6","key":"pone.0348085.ref005","doi-asserted-by":"crossref","first-page":"100114","DOI":"10.1016\/j.apjo.2024.100114","article-title":"Clinical and anatomical features of myopia","volume":"13","author":"JB Jonas","year":"2024","journal-title":"Asia Pac J Ophthalmol (Phila)"},{"issue":"5","key":"pone.0348085.ref006","article-title":"Analysis of axial shortening induced by orthokeratology lenses and its mechanical mechanisms","volume":"20","author":"Z-Y Meng","year":"2025","journal-title":"PLoS One"},{"key":"pone.0348085.ref007","doi-asserted-by":"crossref","first-page":"3815863","DOI":"10.1155\/2023\/3815863","article-title":"Thin Central Corneal Thickness May Be a Risk Factor for Myopia Progression in Children","volume":"2023","author":"P Zhou","year":"2023","journal-title":"J Ophthalmol"},{"issue":"4","key":"pone.0348085.ref008","doi-asserted-by":"crossref","first-page":"958","DOI":"10.1038\/s41591-024-02902-1","article-title":"Causal machine learning for predicting treatment outcomes","volume":"30","author":"S Feuerriegel","year":"2024","journal-title":"Nat Med"},{"key":"pone.0348085.ref009","first-page":"134","article-title":"A study of the predictive effects of machine learning for the relationship between axial length elongation and the progression of myopia in school-aged children","volume-title":"Chin J Exp Ophthalmol","author":"T Tang","year":"2020"},{"key":"pone.0348085.ref010","article-title":"Machine Learning Approaches in High Myopia: Systematic Review and Meta-Analysis","volume":"27","author":"H Zuo","year":"2025","journal-title":"J Med Internet Res"},{"issue":"7","key":"pone.0348085.ref011","doi-asserted-by":"crossref","first-page":"1333","DOI":"10.1038\/s41433-023-02899-w","article-title":"The long and short of it: a comprehensive assessment of axial length estimation in myopic eyes from ocular and demographic variables","volume":"38","author":"G Lingham","year":"2024","journal-title":"Eye (Lond)"},{"issue":"12","key":"pone.0348085.ref012","doi-asserted-by":"crossref","first-page":"2082","DOI":"10.18240\/ijo.2023.12.22","article-title":"Observation of peripheral refraction in myopic anisometropia in young adults","volume":"16","author":"Y-Q Du","year":"2023","journal-title":"Int J Ophthalmol"},{"key":"pone.0348085.ref013","doi-asserted-by":"crossref","first-page":"104505","DOI":"10.1016\/j.pdpdt.2025.104505","article-title":"Correlation of retinal curvature with ocular biometry in patients with myopia","volume":"52","author":"G-R Xu","year":"2025","journal-title":"Photodiagnosis Photodyn Ther"},{"issue":"5","key":"pone.0348085.ref014","doi-asserted-by":"crossref","first-page":"1548","DOI":"10.12998\/wjcc.v10.i5.1548","article-title":"Correlation of myopia onset and progression with corneal biomechanical parameters in children","volume":"10","author":"L-L Lu","year":"2022","journal-title":"World J Clin Cases"},{"key":"pone.0348085.ref015","doi-asserted-by":"crossref","first-page":"1573329","DOI":"10.3389\/fmed.2025.1573329","article-title":"A scoping review of advancements in machine learning for glaucoma: current trends and future direction","volume":"12","author":"J Zhang","year":"2025","journal-title":"Front Med (Lausanne)"},{"issue":"8","key":"pone.0348085.ref016","doi-asserted-by":"crossref","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":"B Ying","year":"2024","journal-title":"Transl Vis Sci Technol"},{"key":"pone.0348085.ref017","doi-asserted-by":"crossref","first-page":"1482788","DOI":"10.3389\/fmed.2024.1482788","article-title":"Machine-learning models to predict myopia in children and adolescents","volume":"11","author":"J Mu","year":"2024","journal-title":"Front Med (Lausanne)"},{"issue":"5","key":"pone.0348085.ref018","doi-asserted-by":"crossref","DOI":"10.1002\/hsr2.70874","article-title":"Prediction of myopia among undergraduate students using ensemble machine learning techniques","volume":"8","author":"IK Sifat","year":"2025","journal-title":"Health Sci Rep"},{"key":"pone.0348085.ref019","article-title":"Evaluating efficacy of 0.125% atropine using a myopia progression machine learning model","author":"CY Han","year":"2025","journal-title":"Jpn J Ophthalmol"},{"key":"pone.0348085.ref020","doi-asserted-by":"crossref","first-page":"1057863","DOI":"10.3389\/fped.2022.1057863","article-title":"Machine learning for predicting the treatment effect of orthokeratology in children","volume":"10","author":"J Fang","year":"2023","journal-title":"Front Pediatr"},{"issue":"6","key":"pone.0348085.ref021","doi-asserted-by":"crossref","first-page":"1462","DOI":"10.1111\/opo.13212","article-title":"Machine learning models for orthokeratology lens fitting and axial length prediction","volume":"43","author":"S Xu","year":"2023","journal-title":"Ophthalmic Physiol Opt"},{"issue":"1","key":"pone.0348085.ref022","article-title":"Accurate prediction of myopic progression and high myopia by machine learning","volume":"7","author":"J Li","year":"2024","journal-title":"Precis Clin Med"},{"issue":"2","key":"pone.0348085.ref023","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1007\/s40123-021-00450-2","article-title":"Machine Learning to Determine Risk Factors for Myopia Progression in Primary School Children: The Anyang Childhood Eye Study","volume":"11","author":"S-M Li","year":"2022","journal-title":"Ophthalmol Ther"},{"issue":"7","key":"pone.0348085.ref024","doi-asserted-by":"crossref","first-page":"2009","DOI":"10.1007\/s40123-024-00972-5","article-title":"Association Between Myopia and Pupil Diameter in Preschoolers: Evidence from a Machine Learning Approach Based on a Real-World Large-Scale Dataset","volume":"13","author":"S Xu","year":"2024","journal-title":"Ophthalmol Ther"},{"issue":"1","key":"pone.0348085.ref025","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1111\/opo.12427","article-title":"Iris colour in relation to myopia among Chinese school-aged children","volume":"38","author":"C-W Pan","year":"2018","journal-title":"Ophthalmic Physiol Opt"},{"issue":"11","key":"pone.0348085.ref026","doi-asserted-by":"crossref","first-page":"1636","DOI":"10.1097\/OPX.0b013e31826c1831","article-title":"Impact of pupil diameter on axial growth in orthokeratology","volume":"89","author":"Z Chen","year":"2012","journal-title":"Optom Vis Sci"},{"issue":"11","key":"pone.0348085.ref027","first-page":"1535","article-title":"Effect of low-dose atropine on myopia progression, pupil diameter and accommodative amplitude: low-dose atropine and myopia progression","volume":"104","author":"A Fu","year":"2020","journal-title":"Br J Ophthalmol"},{"issue":"2","key":"pone.0348085.ref028","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1007\/s00417-019-04573-y","article-title":"Studies on retinal mechanisms possibly related to myopia inhibition by atropine in the chicken","volume":"258","author":"U Mathis","year":"2020","journal-title":"Graefes Arch Clin Exp Ophthalmol"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0348085","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T17:43:41Z","timestamp":1777052621000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0348085"}},"subtitle":[],"editor":[{"given":"Shiva Ram","family":"Male","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2026,4,24]]},"references-count":28,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,4,24]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0348085","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,24]]}}}