EUVIMEDEUVIMED entdecken
Crossref

Metabolomic Profiling and Machine Learning‐Based Prediction of High‐Dose Methotrexate‐Induced Liver Injury in Pediatric Acute Lymphoblastic Leukemia

Kai Guo, Lei Wang, Xiaoran Feng iD, Junfang Yang, Xian Zhang, Ying Zhao, Yating Ma, Jiujiang He, Min Zhang, Wenjing Lang, Jin Zhang, Yaru Zhao und 9 weitere

Pediatric Blood & Cancer · 2026-09 · 73 (9)

DOI: 10.1002/1545-5017.70424 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Pediatric Blood & Cancer, online erschienen am 23.07.2026. Verfasst von Kai Guo und 20 weiteren Autor:innen. Beteiligte Einrichtung: National Center for Clinical Laboratories, Institute of Geriatric Medicine, Chinese Academy of Medical Sciences, Beijing Hospital/National Center of …. Hauptthemen laut MEDLINE: Chemical and Drug Induced Liver Injury, Methotrexate, Precursor Cell Lymphoblastic Leukemia-Lymphoma, Metabolomics. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 51 Literaturangaben. Gefördert von: National Special Project for Science and Technology Basic Work of the Ministry of Science and Technology of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

High‐dose methotrexate (HD‐MTX) is essential for pediatric acute lymphoblastic leukemia (ALL) but frequently causes hepatotoxicity. To address the critical lack of early prediction tools, this study investigated untargeted metabolomic profiles to identify predictive biomarkers and establish robust machine learning (ML) models for early clinical risk assessment and therapeutic optimization.

Methods

This study included 106 pediatric patients with ALL undergoing HD‐MTX therapy. Of these, 56 developed moderate‐to‐severe liver injury. Untargeted plasma metabolomics was performed before and after treatment. Metabolic alterations were identified using multivariate analyses, with pathway annotation performed via KEGG enrichment. Key discriminatory metabolites were further screened via LASSO regression to identify potential biomarkers. Three ML algorithms (Random Forest, Support Vector Machine, and Bayesian logistic regression) were developed for risk prediction, integrating SHAP analysis for model interpretability and feature contribution evaluation.

Results

Patients with liver injury showed distinct metabolic signatures compared with controls. Prior to HD‐MTX treatment, 13 metabolites—such as prominently elevated glycocholic acid—were identified as potential predictors of liver injury, with overarching pathway alterations primarily involving arginine biosynthesis and glutathione metabolism, among others. Post‐treatment, 11 distinct metabolites—including arachidic acid—further distinguished the injury group, reflecting complex regulatory mechanisms and multi‐pathway shifts. Crucially, all three ML models developed using pre‐ or post‐treatment metabolic biomarkers exhibited high predictive and discriminative accuracy for hepatotoxicity (AUC > 0.900).

Conclusions

These findings characterize the metabolic alterations underlying HD‐MTX‐induced liver injury, provide a metabolomics‐based framework for early risk assessment, and facilitate the development of precision therapeutic strategies in pediatric ALL.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Chemical and Drug Induced Liver InjuryMethotrexatePrecursor Cell Lymphoblastic Leukemia-LymphomaMetabolomicsMachine LearningAntimetabolites, AntineoplasticMetabolomeHumansFemaleMaleChildChild, PreschoolPredictive Learning ModelsBiomarkersAdolescentPrognosisInfant

Stichwörter der Autor:innen

biomarkerhigh‐dose methotrexateliver injurymachine learningmetabolomicspediatric acute lymphoblastic leukemia

Substanzen

MethotrexateAntimetabolites, AntineoplasticBiomarkers

Autor:innen und Institutionen

  • National Center for Clinical Laboratories, Institute of Geriatric Medicine, Chinese Academy of Medical Sciences, Beijing Hospital/National Center of Gerontology, Beijing, China.
  • National Center for Clinical Laboratories, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China.
  • Division of Laboratory Medicine, Hebei Yanda Lu Daopei Hospital, Langfang, China.
  • Department of Hematology, Hebei Yanda Lu Daopei Hospital, Langfang, China.
  • Division of Laboratory Medicine, Beijing Lu Daopei Hospital, Beijing, China.
  • Precision Medicine Center, Beijing Lu Daopei Institute of Hematology, Beijing, China.

ORCID-Profile: Xiaoran Feng

Förderung

  • National Special Project for Science and Technology Basic Work of the Ministry of Science and Technology of China

Zitieren

APA

Guo, K., Wang, L., Feng, X., Yang, J., Zhang, X., Zhao, Y., Ma, Y., He, J., Zhang, M., Lang, W., Zhang, J., Zhao, Y., Zhang, G., Li, W., Wang, H., Zhang, G., Yang, Y., Yang, X., Wu, Y., …, & Peng, M. (2026). Metabolomic Profiling and Machine Learning‐Based Prediction of High‐Dose Methotrexate‐Induced Liver Injury in Pediatric Acute Lymphoblastic Leukemia. Pediatric Blood & Cancer, 73(9). https://doi.org/10.1002/1545-5017.70424

Vancouver

Guo K, Wang L, Feng X, Yang J, Zhang X, Zhao Y, et al. Metabolomic Profiling and Machine Learning‐Based Prediction of High‐Dose Methotrexate‐Induced Liver Injury in Pediatric Acute Lymphoblastic Leukemia. Pediatric Blood & Cancer. 2026;73(9). doi:10.1002/1545-5017.70424

BibTeX
@article{Guo2026,
  author = {Guo, Kai and Wang, Lei and Feng, Xiaoran and Yang, Junfang and Zhang, Xian and Zhao, Ying and Ma, Yating and He, Jiujiang and Zhang, Min and Lang, Wenjing and Zhang, Jin and Zhao, Yaru and Zhang, Gailing and Li, Wenqian and Wang, Hongchun and Zhang, Gangwei and Yang, Yunxiao and Yang, Xiaotong and Wu, Yan and Liu, Hongxing and Peng, Mingting},
  title = {Metabolomic Profiling and Machine Learning‐Based Prediction of High‐Dose Methotrexate‐Induced Liver Injury in Pediatric Acute Lymphoblastic Leukemia},
  journal = {Pediatric Blood & Cancer},
  year = {2026},
  volume = {73},
  number = {9},
  doi = {10.1002/1545-5017.70424}
}
Kostenlos starten →