EUVIMEDEUVIMED entdecken
Multizentrische Studie

Development of a Machine Learning-based Model for Methimazole Dosage Adjustment in Youth With Hyperthyroidism

Joon Young Kim iD, Kanghyuck Lee iD, Eunsik Choi iD, Jun Suk Oh iD, Eun Byoul Lee iD, Hyun Wook Chae iD, Taehoon Ko iD, Kyungchul Song iD

The Journal of Clinical Endocrinology & Metabolism · 2026

DOI: 10.1210/clinem/dgaf542 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift The Journal of Clinical Endocrinology & Metabolism, 2026. Verfasst von Joon Young Kim und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pediatrics, Yonsei University College of Medicine, Gangnam Severance Hospital, Seoul 06273, Republic of Korea. Hauptthemen laut MEDLINE: Methimazole, Hyperthyroidism, Machine Learning, Antithyroid Agents. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: Korea Health Technology, Korea Health Industry Development Institute, Ministry of Health & Welfare.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Context

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.

Objective

This study aimed to develop and validate machine learning-based models for predicting optimal MMI dosage in pediatric hyperthyroidism.

Design

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.

Setting

Data were collected from a primary center for model training, with 2 separate centers providing data for external validation. Patients or Other Participants 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 ≤18 years with hyperthyroidism.

Interventions

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. Main Outcome Measures 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.

Results

The XGBoost model demonstrated the best performance in both internal validation (MAE 1.72 mg) and external validation (MAE 1.08 mg). SHAP analysis identified previous MMI dose, T3, and free T4 levels as key predictors.

Conclusion

This study introduces the first data-driven tool to guide MMI dosing in pediatric hyperthyroidism, which can improve clinical efficiency.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

MethimazoleHyperthyroidismMachine LearningAntithyroid AgentsHumansFemaleMaleChildAdolescentRetrospective StudiesChild, PreschoolNeural Networks, Computer

Stichwörter der Autor:innen

drug dosage calculationshyperthyroidismmachine learningmethimazolepediatrics

Substanzen

MethimazoleAntithyroid Agents

Autor:innen und Institutionen

  • Department of Pediatrics, Yonsei University College of Medicine, Gangnam Severance Hospital, Seoul 06273, Republic of Korea.
  • Department of Medical Informatics, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of Korea.
  • College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of Korea.
  • Department of Pediatrics, Konyang University College of Medicine, Daejeon 35365, Republic of Korea.
  • Department of Pediatrics, Yonsei University College of Medicine, Yongin Severance Hospital, Gyeonggi-do 16995, Republic of Korea.
  • Department of Biomedicine & Health Sciences, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of Korea.

ORCID-Profile: Joon Young Kim, Kanghyuck Lee, Eunsik Choi, Jun Suk Oh, Eun Byoul Lee, Hyun Wook Chae, Taehoon Ko, Kyungchul Song

Förderung

  • Korea Health Technology
  • Korea Health Industry Development Institute
  • Ministry of Health & Welfare
  • Basic Medical Science Facilitation Program
  • Catholic Medical Center
  • Catholic University of Korea
  • Catholic Education Foundation

Zitieren

APA

Kim, J. Y., Lee, K., Choi, E., Oh, J. S., Lee, E. B., Chae, H. W., Ko, T., & Song, K. (2026). Development of a Machine Learning-based Model for Methimazole Dosage Adjustment in Youth With Hyperthyroidism. The Journal of Clinical Endocrinology & Metabolism. https://doi.org/10.1210/clinem/dgaf542

Vancouver

Kim JY, Lee K, Choi E, Oh JS, Lee EB, Chae HW, et al. Development of a Machine Learning-based Model for Methimazole Dosage Adjustment in Youth With Hyperthyroidism. The Journal of Clinical Endocrinology & Metabolism. 2026. doi:10.1210/clinem/dgaf542

BibTeX
@article{Kim2026,
  author = {Kim, Joon Young and Lee, Kanghyuck and Choi, Eunsik and Oh, Jun Suk and Lee, Eun Byoul and Chae, Hyun Wook and Ko, Taehoon and Song, Kyungchul},
  title = {Development of a Machine Learning-based Model for Methimazole Dosage Adjustment in Youth With Hyperthyroidism},
  journal = {The Journal of Clinical Endocrinology & Metabolism},
  year = {2026},
  doi = {10.1210/clinem/dgaf542}
}
Kostenlos starten →