{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T22:53:41Z","timestamp":1791759221620,"version":"4.3.4"},"reference-count":43,"publisher":"The Endocrine Society","issue":"4","license":[{"start":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T00:00:00Z","timestamp":1759795200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"name":"Korea Health Technology"},{"DOI":"10.13039\/501100003710","name":"Korea Health Industry Development Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003710","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ministry of Health & Welfare","award":["RS-2023-KH134423"],"award-info":[{"award-number":["RS-2023-KH134423"]}]},{"name":"Ministry of Health & Welfare","award":["RS-2023-KH134396"],"award-info":[{"award-number":["RS-2023-KH134396"]}]},{"name":"Basic Medical Science Facilitation Program"},{"DOI":"10.13039\/100017317","name":"Catholic Medical Center","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017317","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002648","name":"Catholic University of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002648","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Catholic Education Foundation"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,17]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Context<\/jats:title>\n                    <jats:p>Accurate methimazole (MMI) dose adjustment in pediatric hyperthyroidism is crucial, but individualized titration relies on clinician experience due to a lack of validated predictive tools.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aimed to develop and validate machine learning-based models for predicting optimal MMI dosage in pediatric hyperthyroidism.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Design<\/jats:title>\n                    <jats:p>This was a retrospective, multicenter, model-development study. Machine learning models, including linear regression, decision tree, support vector regression, Extreme Gradient Boosting (XGBoost), and feed-forward neural networks, were trained and validated.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Setting<\/jats:title>\n                    <jats:p>Data were collected from a primary center for model training, with 2 separate centers providing data for external validation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Patients or Other Participants<\/jats:title>\n                    <jats:p>Data were derived from 1512 visits for the training set and 666 and 31 visits for 2 external validation cohorts, respectively. All data were from youth aged \u226418 years with hyperthyroidism.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Interventions<\/jats:title>\n                    <jats:p>The models were trained to predict the optimal daily dosage of MMI based on variables including age, sex, anthropometric measures, prior MMI dosage, treatment duration, and current and previous results of thyroid function tests.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Main Outcome Measures<\/jats:title>\n                    <jats:p>Model performance was evaluated by the mean absolute error (MAE) between the predicted and actual MMI dosages. Feature importance was determined using Shapley additive explanations (SHAP) analysis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The XGBoost model demonstrated the best performance in both internal validation (MAE 1.72\u2005mg) and external validation (MAE 1.08\u2005mg). SHAP analysis identified previous MMI dose, T3, and free T4 levels as key predictors.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study introduces the first data-driven tool to guide MMI dosing in pediatric hyperthyroidism, which can improve clinical efficiency.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1210\/clinem\/dgaf542","type":"journal-article","created":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T11:33:41Z","timestamp":1759750421000},"page":"e1136-e1145","source":"Crossref","is-referenced-by-count":2,"title":["Development of a Machine Learning-based Model for Methimazole Dosage Adjustment in Youth With Hyperthyroidism"],"prefix":"10.1210","volume":"111","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9595-3610","authenticated-orcid":false,"given":"Joon Young","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Pediatrics, Yonsei University College of Medicine, Gangnam Severance Hospital , Seoul 06273 ,","place":["Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4257-4776","authenticated-orcid":false,"given":"Kanghyuck","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Medical Informatics, College of Medicine, The Catholic University of Korea , Seoul 06591 ,","place":["Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8504-4636","authenticated-orcid":false,"given":"Eunsik","family":"Choi","sequence":"additional","affiliation":[{"name":"College of Medicine, The Catholic University of Korea , Seoul 06591 ,","place":["Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5765-2347","authenticated-orcid":false,"given":"Jun Suk","family":"Oh","sequence":"additional","affiliation":[{"name":"Department of Pediatrics, Konyang University College of Medicine , Daejeon 35365 ,","place":["Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4981-2446","authenticated-orcid":false,"given":"Eun Byoul","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Pediatrics, Yonsei University College of Medicine, Yongin Severance Hospital , Gyeonggi-do 16995 ,","place":["Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5016-8539","authenticated-orcid":false,"given":"Hyun Wook","family":"Chae","sequence":"additional","affiliation":[{"name":"Department of Pediatrics, Yonsei University College of Medicine, Gangnam Severance Hospital , Seoul 06273 ,","place":["Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4045-0036","authenticated-orcid":false,"given":"Taehoon","family":"Ko","sequence":"additional","affiliation":[{"name":"Department of Medical Informatics, College of Medicine, The Catholic University of Korea , Seoul 06591 ,","place":["Republic of Korea"]},{"name":"Department of Biomedicine & Health Sciences, College of Medicine, The Catholic University of Korea , Seoul 06591 ,","place":["Republic of Korea"]},{"name":"CMC Institute for Basic Medical Science, The Catholic Medical Center of the Catholic University of Korea , Seoul 06591 ,","place":["Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8497-5934","authenticated-orcid":false,"given":"Kyungchul","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Pediatrics, Yonsei University College of Medicine, Gangnam Severance Hospital , Seoul 06273 ,","place":["Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"80","published-online":{"date-parts":[[2025,10,7]]},"reference":[{"issue":"15","key":"2026031619574766100_dgaf542-B1","doi-asserted-by":"crossref","first-page":"1472","DOI":"10.1001\/jama.2023.19052","article-title":"Hyperthyroidism: a review","volume":"330","author":"Lee","year":"2023","journal-title":"JAMA"},{"issue":"6","key":"2026031619574766100_dgaf542-B2","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1542\/pir.36.6.239","article-title":"Hyperthyroidism in children","volume":"36","author":"Srinivasan","year":"2015","journal-title":"Pediatr Rev"},{"issue":"11","key":"2026031619574766100_dgaf542-B3","doi-asserted-by":"crossref","first-page":"R279","DOI":"10.1530\/EC-21-0191","article-title":"Hyperthyroidism in adolescents","volume":"10","author":"Niedziela","year":"2021","journal-title":"Endocr Connect"},{"issue":"5","key":"2026031619574766100_dgaf542-B4","first-page":"363","article-title":"Hyperthyroidism: diagnosis and treatment","volume":"93","author":"Kravets","year":"2016","journal-title":"Am Fam Physician"},{"issue":"2","key":"2026031619574766100_dgaf542-B5","doi-asserted-by":"crossref","first-page":"260","DOI":"10.3803\/EnM.2018.33.2.260","article-title":"Prevalence and annual incidence of thyroid disease in Korea from 2006 to 2015: a nationwide population-based cohort study","volume":"33","author":"Kwon","year":"2018","journal-title":"Endocrinology and Metabolism"},{"issue":"2","key":"2026031619574766100_dgaf542-B6","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1159\/000430985","article-title":"Increasing incidence of juvenile thyrotoxicosis in Denmark: a nationwide study, 1998-2012","volume":"84","author":"Havgaard Kj\u00e6r","year":"2015","journal-title":"Horm Res Paediatr"},{"issue":"3","key":"2026031619574766100_dgaf542-B7","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1159\/000500265","article-title":"The incidence of childhood thyrotoxicosis is increasing in both girls and boys in Sweden","volume":"91","author":"Rodanaki","year":"2019","journal-title":"Horm Res Paediatr"},{"issue":"4","key":"2026031619574766100_dgaf542-B8","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1046\/j.1365-2265.2001.01252.x","article-title":"Increasing incidence of childhood graves\u2019 disease in Hong Kong: a follow-up study","volume":"54","author":"Wong","year":"2001","journal-title":"Clin Endocrinol (Oxf)"},{"issue":"4","key":"2026031619574766100_dgaf542-B9","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1530\/EJE-11-0299","article-title":"A critical review and meta-analysis of the association between overt hyperthyroidism and mortality","volume":"165","author":"Brandt","year":"2011","journal-title":"Eur J Endocrinol"},{"issue":"3","key":"2026031619574766100_dgaf542-B10","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1177\/0885066613498053","article-title":"Thyroid storm: an updated review","volume":"30","author":"Chiha","year":"2015","journal-title":"J Intensive Care Med"},{"issue":"1","key":"2026031619574766100_dgaf542-B11","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1097\/MED.0000000000000521","article-title":"Update on pediatric hyperthyroidism","volume":"27","author":"Kaplowitz","year":"2020","journal-title":"Curr Opin Endocrinol Diabetes Obes"},{"issue":"1","key":"2026031619574766100_dgaf542-B12","doi-asserted-by":"crossref","first-page":"e210073","DOI":"10.1530\/ETJ-21-0073","article-title":"2022 European thyroid association guideline for the management of pediatric graves\u2019 disease","volume":"11","author":"Mooij","year":"2022","journal-title":"Eur Thyroid J"},{"issue":"1","key":"2026031619574766100_dgaf542-B13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1687-9856-2010-176970","article-title":"Adverse events associated with methimazole therapy of graves\u2019 disease in children","volume":"2010","author":"Rivkees","year":"2010","journal-title":"Int J Pediatr Endocrinol"},{"issue":"155","key":"2026031619574766100_dgaf542-B14","doi-asserted-by":"crossref","first-page":"20190083","DOI":"10.1098\/rsif.2019.0083","article-title":"Hyperthyroidism in the personalized medicine era: the rise of mathematical optimization","volume":"16","author":"Meng","year":"2019","journal-title":"J R Soc Interface"},{"issue":"3","key":"2026031619574766100_dgaf542-B15","doi-asserted-by":"crossref","first-page":"506","DOI":"10.1097\/SLA.0000000000002922","article-title":"Hyperthyroidism is underdiagnosed and undertreated in 3336 patients: an opportunity for improvement and intervention","volume":"268","author":"Asban","year":"2018","journal-title":"Ann Surg"},{"issue":"1","key":"2026031619574766100_dgaf542-B16","first-page":"e21339","article-title":"A case report on methimazole-induced severe hypothyroidism","volume":"14","author":"Alaie","year":"2022","journal-title":"Cureus"},{"issue":"9","key":"2026031619574766100_dgaf542-B17","doi-asserted-by":"crossref","first-page":"3671","DOI":"10.1210\/jc.2013-1954","article-title":"Comparative effectiveness of therapies for graves\u2019 hyperthyroidism: a systematic review and network meta-analysis","volume":"98","author":"Sundaresh","year":"2013","journal-title":"J Clin Endocrinol Metab"},{"issue":"2","key":"2026031619574766100_dgaf542-B18","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1089\/105072501300042947","article-title":"Surgical treatment of hyperthyroidism: a ten-year experience","volume":"11","author":"Werga-Kjellman","year":"2001","journal-title":"Thyroid"},{"issue":"3","key":"2026031619574766100_dgaf542-B19","doi-asserted-by":"crossref","first-page":"122","DOI":"10.6065\/apem.2014.19.3.122","article-title":"The treatment of graves\u2019 disease in children and adolescents","volume":"19","author":"Lee","year":"2014","journal-title":"Ann Pediatr Endocrinol Metab"},{"issue":"7","key":"2026031619574766100_dgaf542-B20","doi-asserted-by":"crossref","first-page":"1676","DOI":"10.1111\/jth.15318","article-title":"Comparison of multivariate linear regression and a machine learning algorithm developed for prediction of precision warfarin dosing in a Korean population","volume":"19","author":"Nguyen","year":"2021","journal-title":"J Thromb Haemost"},{"key":"2026031619574766100_dgaf542-B21","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1016\/j.jss.2019.06.025","article-title":"Optimizing levothyroxine dose adjustment after thyroidectomy with a decision tree","volume":"244","author":"Chen","year":"2019","journal-title":"J Surg Res"},{"issue":"6","key":"2026031619574766100_dgaf542-B22","doi-asserted-by":"crossref","first-page":"761","DOI":"10.1080\/17512433.2021.1911642","article-title":"Prediction of vancomycin dose on high-dimensional data using machine learning techniques","volume":"14","author":"Huang","year":"2021","journal-title":"Expert Rev Clin Pharmacol"},{"issue":"1","key":"2026031619574766100_dgaf542-B23","doi-asserted-by":"crossref","first-page":"42192","DOI":"10.1038\/srep42192","article-title":"Application of machine-learning models to predict tacrolimus stable dose in renal transplant recipients","volume":"7","author":"Tang","year":"2017","journal-title":"Sci Rep"},{"issue":"4","key":"2026031619574766100_dgaf542-B24","doi-asserted-by":"crossref","first-page":"1105","DOI":"10.1210\/clinem\/dgae642","article-title":"Data-driven strategies for carbimazole titration: exploring machine learning solutions in hyperthyroidism control","volume":"110","author":"Reich","year":"2025","journal-title":"J Clin Endocrinol Metab"},{"issue":"5","key":"2026031619574766100_dgaf542-B25","doi-asserted-by":"crossref","first-page":"135","DOI":"10.3345\/kjp.2018.61.5.135","article-title":"The 2017 Korean national growth charts for children and adolescents: development, improvement, and prospects","volume":"61","author":"Kim","year":"2018","journal-title":"Korean J Pediatr"},{"key":"2026031619574766100_dgaf542-B26","author":"cobas\u00ae"},{"issue":"1","key":"2026031619574766100_dgaf542-B27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12976-017-0073-6","article-title":"A patient-specific treatment model for graves\u2019 hyperthyroidism","volume":"15","author":"Pandiyan","year":"2018","journal-title":"Theor Biol Med Model"},{"issue":"4","key":"2026031619574766100_dgaf542-B28","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1055\/a-1336-3502","article-title":"Development and prospective validation of the levothyroxine dose prediction model in primary hypothyroidism","volume":"53","author":"Singh","year":"2021","journal-title":"Horm Metab Res"},{"issue":"1","key":"2026031619574766100_dgaf542-B29","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1111\/j.1365-2265.2008.03291.x","article-title":"Prediction of cure and risk of hypothyroidism in patients receiving 131I for hyperthyroidism","volume":"70","author":"Boelaert","year":"2009","journal-title":"Clin Endocrinol (Oxf)"},{"key":"2026031619574766100_dgaf542-B30","first-page":"785","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":"2026031619574766100_dgaf542-B31","doi-asserted-by":"crossref","unstructured":"Kim JY, Lee K, Choi E, et al \u00a0Supplementary data \u201cDevelopment of a Machine Learning-based Model for Methimazole Dosage Adjustment in Youth With Hyperthyroidism\u201d. Figshare. 2025. 10.6084\/m9.figshare.30264484.v1","DOI":"10.1210\/clinem\/dgaf542"},{"key":"2026031619574766100_dgaf542-B32","first-page":"1","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"issue":"2","key":"2026031619574766100_dgaf542-B33","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1097\/FTD.0000000000001078","article-title":"Artificial intelligence and machine learning approaches to facilitate therapeutic drug management and model-informed precision dosing","volume":"45","author":"Poweleit","year":"2023","journal-title":"Ther Drug Monit"},{"key":"2026031619574766100_dgaf542-B34","first-page":"1211","article-title":"Designing disease prediction model using machine learning approach","author":"Dahiwade","year":"2019","journal-title":"2019 3rd International Conference on Computing Methodologies and Communication (ICCMC)"},{"issue":"10","key":"2026031619574766100_dgaf542-B35","doi-asserted-by":"crossref","first-page":"1343","DOI":"10.1089\/thy.2016.0229","article-title":"2016 American thyroid association guidelines for diagnosis and management of hyperthyroidism and other causes of thyrotoxicosis","volume":"26","author":"Ross","year":"2016","journal-title":"Thyroid"},{"issue":"4","key":"2026031619574766100_dgaf542-B36","doi-asserted-by":"crossref","first-page":"389","DOI":"10.3390\/pharmaceutics2040389","article-title":"Pediatric dosing and body size in biotherapeutics","volume":"2","author":"Shi","year":"2010","journal-title":"Pharmaceutics"},{"issue":"3","key":"2026031619574766100_dgaf542-B37","doi-asserted-by":"crossref","first-page":"716","DOI":"10.1002\/cpt.3250","article-title":"Assessment of dosing strategies for pediatric drug products","volume":"116","author":"Taylor","year":"2024","journal-title":"Clinical Pharmacology & Therapeutics"},{"issue":"4","key":"2026031619574766100_dgaf542-B38","doi-asserted-by":"crossref","first-page":"597","DOI":"10.1111\/j.1365-2125.2009.03591.x","article-title":"What is the right dose for children?","volume":"70","author":"Cella","year":"2010","journal-title":"Br J Clin Pharmacol"},{"issue":"3","key":"2026031619574766100_dgaf542-B39","first-page":"1038","article-title":"Age and gender predict the outcome of treatment for graves\u2019 hyperthyroidism*","volume":"85","author":"Allahabadia","year":"2000","journal-title":"J Clin Endocrinol Metab"},{"issue":"1","key":"2026031619574766100_dgaf542-B40","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12911-020-1063-x","article-title":"An evaluation of time series summary statistics as features for clinical prediction tasks","volume":"20","author":"Guo","year":"2020","journal-title":"BMC Med Inform Decis Mak"},{"key":"2026031619574766100_dgaf542-B41","first-page":"1571","article-title":"Leveraging clinical time-series data for prediction: a cautionary tale","volume":"2017","author":"Sherman","year":"2018","journal-title":"AMIA Annu Symp Proc"},{"key":"2026031619574766100_dgaf542-B42","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.jclinepi.2019.02.004","article-title":"A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models","volume":"110","author":"Christodoulou","year":"2019","journal-title":"J Clin Epidemiol"},{"key":"2026031619574766100_dgaf542-B43","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.jclinepi.2020.03.002","article-title":"Logistic regression was as good as machine learning for predicting major chronic diseases","volume":"122","author":"Nusinovici","year":"2020","journal-title":"J Clin Epidemiol"}],"container-title":["The Journal of Clinical Endocrinology &amp; Metabolism"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jcem\/advance-article-pdf\/doi\/10.1210\/clinem\/dgaf542\/64540825\/dgaf542.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jcem\/article-pdf\/111\/4\/e1136\/64540825\/dgaf542.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jcem\/article-pdf\/111\/4\/e1136\/64540825\/dgaf542.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T23:58:01Z","timestamp":1773705481000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jcem\/article\/111\/4\/e1136\/8277117"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,7]]},"references-count":43,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,10,7]]},"published-print":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1210\/clinem\/dgaf542","relation":{},"ISSN":["0021-972X","1945-7197"],"issn-type":[{"value":"0021-972X","type":"print"},{"value":"1945-7197","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,4]]},"published":{"date-parts":[[2025,10,7]]}}}