{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T04:47:57Z","timestamp":1782362877303,"version":"3.54.5"},"reference-count":49,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T00:00:00Z","timestamp":1782345600000},"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. Med."],"abstract":"<jats:p>The rapid increase in childhood myopia highlights the need for accurate, non-invasive tools for early risk stratification in large-scale screening; however, static cross-sectional data often fail to capture dynamic refractive trajectories. In this study, we developed and validated an Expert-Guided Stacking (EGS) predictive framework using longitudinal school screening data (Autumn 2023\u2013Autumn 2025) from Binchuan County, China. For each student, predictors were constructed only from screening records preceding the outcome-defining follow-up record, thereby preserving the original temporal prediction boundary. We first evaluated performance across six conventional classifiers (LR, RF, XGBoost, SVM, NB, and AdaBoost), then proposed a hybrid EGS model that integrates a multi-model ensemble architecture with a clinical risk-heuristic override module. This framework was specifically designed to reduce false negatives and improve prediction of future high-myopia risk by leveraging historical longitudinal refractive trajectories. Model development used student-level partitioning, with 5-fold cross-validation for tuning and held-out test-set evaluation for final performance assessment. Although AdaBoost attained a high overall discrimination (AUC = 0.9992), the proposed EGS framework achieved clinically favorable utility with high Recall (0.9533) and Precision (0.9211), enabling reliable future-risk identification while avoiding the false-positive burden of less precise high-recall models. SHAP analysis verified the critical contribution of longitudinal trajectory features to model interpretability and transparency. Our findings demonstrate that this knowledge-augmented ML approach delivers a robust, scalable solution for school-based myopia surveillance, with a priority on high-risk recall to support timely clinical intervention and personalized vision care.<\/jats:p>","DOI":"10.3389\/fmed.2026.1843421","type":"journal-article","created":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T04:21:48Z","timestamp":1782361308000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["EGS-Net: a knowledge-augmented machine learning framework for predicting future high-myopia risk from longitudinal school-screening trajectories"],"prefix":"10.3389","volume":"13","author":[{"given":"Zhan","family":"Tang","sequence":"first","affiliation":[{"name":"School of Physics, Zhejiang University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Na","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Software, Yunnan University","place":["Kunming, Yunnan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoyu","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Software, Yunnan University","place":["Kunming, Yunnan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinhao","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Software, Yunnan University","place":["Kunming, Yunnan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Dai","sequence":"additional","affiliation":[{"name":"School of Software, Yunnan University","place":["Kunming, Yunnan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Information Engineering and Automation, Kunming University of Science and Technology","place":["Kunming, Yunnan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Runze","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Software, Yunnan University","place":["Kunming, Yunnan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,25]]},"reference":[{"key":"B1","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":"B2","doi-asserted-by":"publisher","first-page":"1739","DOI":"10.1016\/S0140-6736(12)60272-4","article-title":"Myopia","volume":"379","author":"Morgan","year":"2012","journal-title":"Lancet"},{"key":"B3","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1038\/519276a","article-title":"The myopia boom","volume":"519","author":"Dolgin","year":"2015","journal-title":"Nature"},{"key":"B4","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1167\/iovs.61.4.49","article-title":"The complications of myopia: a review and meta-analysis","volume":"61","author":"Haarman","year":"2020","journal-title":"Invest Ophthalmol Visual Sci"},{"key":"B5","doi-asserted-by":"publisher","first-page":"e0140419","DOI":"10.1371\/journal.pone.0140419","article-title":"The association between near work activities and myopia in children\u2013a systematic review and meta-analysis","volume":"10","author":"Huang","year":"2015","journal-title":"PLoS ONE"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1142","DOI":"10.1001\/jama.2015.10803","article-title":"Effect of time spent outdoors at school on the development of myopia among children in china: a randomized clinical trial","volume":"314","author":"He","year":"2015","journal-title":"JAMA"},{"key":"B7","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1001\/jamaophthalmol.2020.6239","article-title":"Progression of myopia in school-aged children after COVID-19 home confinement","volume":"139","author":"Wang","year":"2021","journal-title":"JAMA Ophthalmol"},{"key":"B8","doi-asserted-by":"publisher","first-page":"M20","DOI":"10.1167\/iovs.18-25957","article-title":"IMI\u2013defining and classifying myopia: a proposed set of standards for clinical and epidemiologic studies","volume":"60","author":"Flitcroft","year":"2019","journal-title":"Invest Ophthalmol Visual Sci"},{"key":"B9","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":"B10","doi-asserted-by":"publisher","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":"Li","year":"2022","journal-title":"Ophthalmol Ther"},{"key":"B11","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1186\/s12967-024-05075-0","article-title":"Development and validation of predictive models for myopia onset and progression using extensive 15-year refractive data in children and adolescents","volume":"22","author":"Zhao","year":"2024","journal-title":"J Transl Med"},{"key":"B12","doi-asserted-by":"publisher","first-page":"pbae005","DOI":"10.1093\/pcmedi\/pbae005","article-title":"Accurate prediction of myopic progression and high myopia by machine learning","volume":"7","author":"Li","year":"2024","journal-title":"Precis Clin Med"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1646277","DOI":"10.3389\/fmed.2025.1646277","article-title":"Prediction of myopia onset and shift in premyopic school-aged children: a machine learning-based algorithm","volume":"12","author":"Gao","year":"2025","journal-title":"Front Med"},{"key":"B14","doi-asserted-by":"publisher","first-page":"e2553543","DOI":"10.1001\/jamanetworkopen.2025.53543","article-title":"Deep learning prediction of childhood myopia progression using fundus image and refraction data","volume":"9","author":"Kang","year":"2025","journal-title":"JAMA Netw Open"},{"key":"B15","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1111\/opo.13259","article-title":"Myopia progression patterns among paediatric patients in a clinical setting","volume":"44","author":"Moore","year":"2024","journal-title":"Ophthal Physiol Optics"},{"key":"B16","doi-asserted-by":"publisher","first-page":"e57644","DOI":"10.2196\/57644","article-title":"Machine learning approaches in high myopia: systematic review and meta-analysis","volume":"27","author":"Zuo","year":"2025","journal-title":"J Med Internet Res"},{"key":"B17","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1038\/s41746-025-02308-4","article-title":"AI-guided personalized predictions on myopia progression and interventions","volume":"9","author":"Liu","year":"2026","journal-title":"NPJ Dig Med"},{"key":"B18","first-page":"4765","article-title":"A unified approach to interpreting model predictions","author":"Lundberg","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B19","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat Mach Intell"},{"key":"B20","doi-asserted-by":"publisher","first-page":"16","DOI":"10.3390\/medicina61010016","article-title":"The potential of SHAP and machine learning for personalized explanations of influencing factors in myopic treatment for children","volume":"61","author":"Chen","year":"2024","journal-title":"Medicina"},{"key":"B21","doi-asserted-by":"publisher","first-page":"19811","DOI":"10.1038\/s41598-025-05021-0","article-title":"Interpretable machine learning models for predicting childhood myopia from school-based screening data","volume":"15","author":"Feng","year":"2025","journal-title":"Sci Rep"},{"key":"B22","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1167\/iovs.66.7.4","article-title":"Perspectives on genetic and environmental factors in myopia, its prediction, and the future direction of research","volume":"66","author":"Williams","year":"2025","journal-title":"Invest Ophthalmol Visual Sci"},{"key":"B23","doi-asserted-by":"publisher","first-page":"5","DOI":"10.4103\/IJO.IJO_2632_25","article-title":"Artificial intelligence for myopia: current update and concern","volume":"74","author":"Saxena","year":"2026","journal-title":"Indian J Ophthalmol"},{"key":"B24","year":"2021","journal-title":"Guidelines for Appropriate Technology of Myopia Prevention and Control in Children and Adolescents (Updated Edition)"},{"key":"B25","doi-asserted-by":"publisher","first-page":"M184","DOI":"10.1167\/iovs.18-25977","article-title":"IMI\u2013clinical management guidelines report","volume":"60","author":"Gifford","year":"2019","journal-title":"Invest Ophthalmol Visual Sci"},{"key":"B26","doi-asserted-by":"publisher","first-page":"388","DOI":"10.1111\/opo.12305","article-title":"Age of onset of myopia predicts risk of high myopia in later childhood in myopic Singapore children","volume":"36","author":"Chua","year":"2016","journal-title":"Ophth Physiol Optics"},{"key":"B27","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1016\/j.patrec.2005.10.010","article-title":"An introduction to ROC analysis","volume":"27","author":"Fawcett","year":"2006","journal-title":"Pattern Recognit Lett"},{"key":"B28","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1016\/j.ipm.2009.03.002","article-title":"A systematic analysis of performance measures for classification tasks","volume":"12","author":"Sokolova","year":"2009","journal-title":"Inf Retr Boston"},{"key":"B29","doi-asserted-by":"crossref","DOI":"10.1201\/b13880","volume-title":"Generalized Estimating Equations","author":"Hardin","year":"2012"},{"key":"B30","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1155\/2014\/303728","article-title":"Generalized estimating equations in longitudinal data analysis: a review and recent developments","volume":"1","author":"Liang","year":"2014","journal-title":"Ann Rev Stat Applic"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v045.i03","article-title":"Mice: multivariate imputation by chained equations in R","volume":"45","author":"van Buuren","year":"2011","journal-title":"J Stat Softw"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1201\/9780429492259","author":"van","year":"2018","journal-title":"Flexible Imputation of Missing Data"},{"key":"B33","first-page":"1137","article-title":"A study of cross-validation and bootstrap for accuracy estimation and model selection","author":"Kohavi","year":"1995","journal-title":"International joint conference on artificial intelligence (IJCAI)"},{"key":"B34","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"Bergstra","year":"2012","journal-title":"J Mach Learn Res"},{"key":"B35","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1097\/IJG.0000000000002579","article-title":"SMOTE-enhanced explainable artificial intelligence model for predicting visual field progression in myopic normal tension glaucoma","volume":"34","author":"Kim","year":"2025","journal-title":"J Glaucoma"},{"key":"B36","doi-asserted-by":"crossref","DOI":"10.1002\/9781118548387","volume-title":"Applied Logistic Regression","author":"Hosmer","year":"2013"},{"key":"B37","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":"B38","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1145\/2939672.2939785","article-title":"XGBoost: a scalable tree boosting system","author":"Chen","year":"2016","journal-title":"Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining"},{"key":"B39","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511801389","volume-title":"An Introduction to Support Vector Machines and Other Kernel-based Learning Methods","author":"Cristianini","year":"2000"},{"key":"B40","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1006\/jcss.1997.1504","article-title":"A decision-theoretic generalization of on-line learning and an application to boosting","volume":"55","author":"Freund","year":"1997","journal-title":"J Comput Syst Sci"},{"key":"B41","volume-title":"Pattern Classification","author":"Duda","year":"2000"},{"key":"B42","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1186\/s12938-025-01416-2","article-title":"Deep learning for predicting myopia severity classification method","volume":"24","author":"Xing","year":"2025","journal-title":"Biomed Eng Online"},{"key":"B43","doi-asserted-by":"publisher","first-page":"e048008","DOI":"10.1136\/bmjopen-2020-048008","article-title":"Protocol for development of a reporting guideline (TRIPOD-AI) and risk of bias tool (PROBAST-AI) for diagnostic and prognostic prediction model studies based on artificial intelligence","volume":"11","author":"Collins","year":"2021","journal-title":"BMJ Open"},{"key":"B44","first-page":"g7594","article-title":"updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"384","author":"Collins","year":"2024","journal-title":"BMJ"},{"key":"B45","doi-asserted-by":"publisher","first-page":"1745","DOI":"10.3390\/molecules30081745","article-title":"Ensemble machine learning for the prediction and understanding of the refractive index in chalcogenide glasses","volume":"30","author":"Belciu","year":"2025","journal-title":"Molecules"},{"key":"B46","doi-asserted-by":"publisher","first-page":"e001932","DOI":"10.1136\/bmjophth-2024-001932","article-title":"Prediction of long-term uncorrected distance visual acuity in surgically SMILE corrected myopic eyes using machine learning","volume":"10","author":"Yang","year":"2025","journal-title":"BMJ Open Ophthalmol"},{"key":"B47","doi-asserted-by":"publisher","first-page":"e71425","DOI":"10.1002\/hsr2.71425","article-title":"Prediction of myopia among undergraduate students by using ensemble machine learning techniques","volume":"8","author":"Qureshi","year":"2025","journal-title":"Health Sci Rep"},{"key":"B48","author":"Maruf Yasin","year":"2025","journal-title":"Data-driven study of behavioral predictors of myopia: a machine learning based early screening approach"},{"key":"B49","doi-asserted-by":"publisher","first-page":"5430","DOI":"10.1038\/s41598-023-32367-0","article-title":"Myopia prediction for children and adolescents via time-aware deep learning","volume":"13","author":"Huang","year":"2023","journal-title":"Sci Rep"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1843421\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T04:21:50Z","timestamp":1782361310000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1843421\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,25]]},"references-count":49,"alternative-id":["10.3389\/fmed.2026.1843421"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1843421","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,25]]},"article-number":"1843421"}}