{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T07:02:55Z","timestamp":1790060575051,"version":"4.0.1"},"reference-count":10,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T00:00:00Z","timestamp":1790035200000},"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. Ophthalmol."],"abstract":"<jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>The aim of this study was to determine whether routinely recorded baseline clinical factors, alone or combined with machine-learning predictive modeling, can provide individual risk stratification for myopia control by identifying children who will progress more than 0.25 diopters (D) during their first year of low-dose atropine treatment.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>From a 555-child source cohort treated initially with atropine 0.01% or 0.02%, 468 children had qualifying 9- to 15-month follow-up; 427 children started atropine monotherapy without a baseline optical adjunct. A child was classified as poorly responsive if either treated eye progressed more than 0.25 D of spherical equivalent refraction from baseline to the qualifying visit. This threshold was a practical clinical refraction boundary and was tested in sensitivity analyses using a 0.50-D threshold, annualized progression, and an annualized &amp;gt;0.50 D\/year threshold. A prevalence reference, age-plus-refraction logistic regression, elastic-net regression, gradient boosting, and an exploratory multilayer-perceptron neural network were compared by repeated cross-validation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Of 427 children, 159 (37%) were poorly responsive. Discrimination was poor and machine learning provided no improvement: the area under the curve (AUC) was 0.60 for logistic regression and 0.57 for gradient boosting [difference \u22120.03; 95% confidence interval (CI) \u22120.06 to 0.01]. Age alone performed similarly (AUC 0.60). No threshold was clinically useful; a high-sensitivity rule flagged 85% of children to identify 88% of poor responders, with positive predictive value 0.39.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Routinely recorded baseline factors did not provide clinically useful individual-level prediction of the first-year progression category. With this predictor set, observing early on-treatment progression remains the practical way to identify children who may need escalation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fopht.2026.1930814","type":"journal-article","created":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T06:17:56Z","timestamp":1790057876000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Routine baseline clinical data do not reliably predict poor first-year myopia control with low-dose atropine: a machine-learning benchmarking study"],"prefix":"10.3389","volume":"6","author":[{"given":"Karenna","family":"Mehta","sequence":"first","affiliation":[{"name":"South Bay Family Eye","place":["Long Beach, CA, United States"]},{"name":"Rice University","place":["Houston, TX, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert A.","family":"Clark","sequence":"additional","affiliation":[{"name":"South Bay Family Eye","place":["Long Beach, CA, United States"]},{"name":"Department of Ophthalmology, David Geffen School of Medicine, University of California, Los Angeles","place":["Los Angeles, CA, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,22]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2018.05.029","article-title":"Low-concentration atropine for myopia progression (LAMP) study: a randomized, double-blinded, placebo-controlled trial of 0.05%, 0.025%, and 0.01% atropine eye drops in myopia control","volume":"126","author":"Yam","year":"2019","journal-title":"Ophthalmology"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2015.07.004","article-title":"Five-year clinical trial on atropine for the treatment of myopia 2: myopia control with atropine 0.01% eyedrops","volume":"123","author":"Chia","year":"2016","journal-title":"Ophthalmology"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1002674","article-title":"Prediction of myopia development among Chinese school-aged children using refraction data from electronic medical records: a retrospective, multicentre machine learning study","volume":"15","author":"Lin","year":"2018","journal-title":"PloS Med"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00752-8","article-title":"Deep learning system to predict the 5-year risk of high myopia using fundus imaging in children","volume":"6","author":"Foo","year":"2023","journal-title":"NPJ Digit Med"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1167\/iovs.62.10.36","article-title":"Myopia progression as a function of sex, age, and ethnicity","volume":"62","author":"Jones-Jordan","year":"2021","journal-title":"Invest Ophthalmol Vis Sci"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1016\/j.xops.2026.101300","article-title":"Low-dose atropine for pediatric myopia: first-year progression as a risk-stratification and management signal","volume":"6","author":"Suh","year":"2026","journal-title":"Ophthalmol Sci"},{"key":"B7","doi-asserted-by":"crossref","DOI":"10.1145\/2939672.2939785","article-title":"XGBoost: a scalable tree boosting system","author":"Chen","year":"2016"},{"key":"B8","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":"B9","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","year":"2024","journal-title":"BMJ"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1001\/jamaophthalmol.2023.2097","article-title":"Efficacy and safety of 0.01% and 0.02% atropine for the treatment of pediatric myopia progression over 3 years: a randomized clinical trial","volume":"141","author":"Zadnik","year":"2023","journal-title":"JAMA Ophthalmol"}],"container-title":["Frontiers in Ophthalmology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fopht.2026.1930814\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T06:17:57Z","timestamp":1790057877000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fopht.2026.1930814\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,22]]},"references-count":10,"alternative-id":["10.3389\/fopht.2026.1930814"],"URL":"https:\/\/doi.org\/10.3389\/fopht.2026.1930814","relation":{},"ISSN":["2674-0826"],"issn-type":[{"value":"2674-0826","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,22]]},"article-number":"1930814"}}