EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Development of a web-based machine learning model for early prediction of delayed high-dose methotrexate clearance in pediatric osteosarcoma

Fengyi Duan, Mingqing Ji, Lichun Wu, Chang Liu

Frontiers in Pediatrics · 30.03.2026 · 14

DOI: 10.3389/fped.2026.1758691 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Pediatrics, online erschienen am 30.03.2026. Verfasst von Fengyi Duan und 3 weiteren Autor:innen. Beteiligte Einrichtung: Pediatric Oncology, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, University of Electronic…. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

Pediatric osteosarcoma treatment with high-dose (HD) methotrexate (MTX) poses risks of delayed clearance due to immature organ function. Interpretable machine learning facilitates proactive prediction, enabling improved monitoring and reduced toxicity risks.

Method

A retrospective study (2020–2024) of 181 pediatric patients with osteosarcoma treated with HD-MTX was conducted to identify key predictors using least absolute shrinkage and selection operator (LASSO) regression and Boruta analyses. Training and test datasets were proportionally split. Ten-fold cross-validation and hyperparameter tuning were performed, followed by the development of models (LASSO, ridge, and logistic regression), which were subsequently compared. Model performance was comprehensively evaluated using metrics such as the receiver operating characteristic (ROC) and F 1 scores.

Results

Of the 181 patients, 51 experienced delayed MTX elimination. Nine predictors (MTX3H, IBil3H, Urea3H, Cr, APTT, PT, MPV, EC, and FIB) were identified. LASSO regression outperformed the other models, achieving an AUC of 0.8466, with robust performance across multiple metrics, including the ROC, F 1 score, and decision curve analysis.

Conclusion

This interpretable machine learning model effectively predicts delayed MTX elimination in pediatric patients with osteosarcoma, enhancing patient monitoring, minimizing toxicity risks, and supporting evidence-based clinical decisions. The application is publicly accessible at: https://sclslc.shinyapps.io/shiny_cls2_1model_dalex/

Schlagwörter

Stichwörter der Autor:innen

delayed metabolismmachine learningmethotrexatepediatric osteosarcomaprognosis

Autor:innen und Institutionen

  • Pediatric Oncology, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, University of Electronic Science and Technology of China, Chengdu, China.
  • Laboratory Department of Clinical Laboratory, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, University of Electronic Science and Technology of China, Chengdu, C…

Zitieren

APA

Duan, F., Ji, M., Wu, L., & Liu, C. (2026). Development of a web-based machine learning model for early prediction of delayed high-dose methotrexate clearance in pediatric osteosarcoma. Frontiers in Pediatrics, 14. https://doi.org/10.3389/fped.2026.1758691

Vancouver

Duan F, Ji M, Wu L, Liu C. Development of a web-based machine learning model for early prediction of delayed high-dose methotrexate clearance in pediatric osteosarcoma. Frontiers in Pediatrics. 2026;14. doi:10.3389/fped.2026.1758691

BibTeX
@article{Duan2026,
  author = {Duan, Fengyi and Ji, Mingqing and Wu, Lichun and Liu, Chang},
  title = {Development of a web-based machine learning model for early prediction of delayed high-dose methotrexate clearance in pediatric osteosarcoma},
  journal = {Frontiers in Pediatrics},
  year = {2026},
  volume = {14},
  doi = {10.3389/fped.2026.1758691}
}
Kostenlos starten →