EUVIMEDEUVIMED entdecken
Crossref

Machine learning approach for dosage individualization of azithromycin in children with community‐acquired pneumonia

Bo-Hao Tang, Shu-Meng Fu, Li-Yuan Tian, Xin-Fang Zhang, Bu-Fan Yao, Wei Zhang, Yue-E Wu, Yue Zhou, Ya-Kun Wang, Guo-Xiang Hao, John van den Anker, Yi Zheng iD und 1 weitere

British Journal of Clinical Pharmacology · 2025

DOI: 10.1002/bcp.70050 ↗

Kurz gefasst

Fachartikel in der Zeitschrift British Journal of Clinical Pharmacology, 2025. Verfasst von Bo-Hao Tang und 12 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pharmacy, The Second Hospital, Cheeloo College of Medicine, Shandong University, Jinan, China. Hauptthemen laut MEDLINE: Azithromycin, Machine Learning, Community-Acquired Infections, Anti-Bacterial Agents. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 37 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Distinguished Young and Middle-aged Scholar of Shandong University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aims

The uncertainty about the efficacy and safety of currently used azithromycin dosing regimens in children warrants individualized therapy. The area under the plasma concentration‐time curve over 24 h (AUC 0‐24 ) of azithromycin correlates best with its effectiveness. The aim of this study was to evaluate the ability of machine learning (ML) to predict the AUC 0‐24 of azithromycin in children with community‐acquired pneumonia.

Methods

Various ML algorithms were used to build ML models based on simulated pharmacokinetic profiles from a published population pharmacokinetic model. A priori‐ML model predicted AUC 0‐24 using patients' characteristics and after the trough concentration ( C 0 ) became available, a posteriori‐ML model was built for improved prediction. Statistical methods and pharmacodynamic (PD) evaluation methods were used to evaluate the ML model's predictive accuracy in a real‐world study. ML‐optimized doses were evaluated by calculating the probability of PD target attainment in virtual trials compared with guideline‐recommended doses.

Results

The AUC 0‐24 can be predicted by priori‐ML model using the CatBoost algorithm with dosing regimen and two covariates as predictors (weight, alanine aminotransferase) before initial administration. A posteriori‐ML model using CatBoost algorithm was built with adding C 0 as a predictor. In real‐world validation, the mean absolute prediction error of the priori‐ML and posteriori‐ML models was less than 30%. The accuracy (determining whether the PD target is met) of the priori‐ML model was 76.3%, whereas that of the posteriori‐ML model increased to 90.4%.

Conclusions

ML models were established to predict the AUC 0‐24 of azithromycin successfully and could be used for individual dose adjustment in children before treatment and after obtaining C 0 .

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AzithromycinMachine LearningCommunity-Acquired InfectionsAnti-Bacterial AgentsModels, BiologicalPneumoniaHumansChildMaleArea Under CurveFemaleChild, PreschoolInfantAlgorithmsPrecision MedicineDose-Response Relationship, DrugDrug Dosage CalculationsAdolescentCommunity-Acquired Pneumonia

Stichwörter der Autor:innen

azithromycinchildrenindividual therapymachine‐learningpharmacometrics

Substanzen

AzithromycinAnti-Bacterial Agents

Autor:innen und Institutionen

  • Department of Pharmacy, The Second Hospital, Cheeloo College of Medicine, Shandong University, Jinan, China.
  • Department of Clinical Pharmacy, Institute of Clinical Pharmacology, Key Laboratory of Chemical Biology (Ministry of Education), NMPA Key Laboratory for Clinical Research and Evaluation of Innovative Drug, School of Pha…
  • Department of Respiratory Care, Children's Hospital of Hebei Province affiliated to Hebei Medical University, Shijiazhuang, China.
  • Division of Clinical Pharmacology, Children's National Hospital, Washington, DC, USA.
  • Departments of Pediatrics, Pharmacology & Physiology, Genomics & Precision Medicine, the George Washington University School of Medicine and Health Sciences, Washington, DC, USA.

ORCID-Profile: Yi Zheng, Wei Zhao

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Distinguished Young and Middle-aged Scholar of Shandong University
  • Innovation and Development Joint Fund of the Natural Science Foundation of Shandong Province
  • Natural Science Foundation of Shandong Province
  • Clinical Medical Talent Training Program funded by the Hebei Provincial Government in 2021
  • Medical Science Research Project Program of Hebei Province in 2022
  • National Basic Research Program of China

Zitieren

APA

Tang, B. H., Fu, S. M., Tian, L. Y., Zhang, X. F., Yao, B. F., Zhang, W., Wu, Y. E., Zhou, Y., Wang, Y. K., Hao, G. X., van den Anker, J., Zheng, Y., & Zhao, W. (2025). Machine learning approach for dosage individualization of azithromycin in children with community‐acquired pneumonia. British Journal of Clinical Pharmacology. https://doi.org/10.1002/bcp.70050

Vancouver

Tang BH, Fu SM, Tian LY, Zhang XF, Yao BF, Zhang W, et al. Machine learning approach for dosage individualization of azithromycin in children with community‐acquired pneumonia. British Journal of Clinical Pharmacology. 2025. doi:10.1002/bcp.70050

BibTeX
@article{Tang2025,
  author = {Tang, Bo-Hao and Fu, Shu-Meng and Tian, Li-Yuan and Zhang, Xin-Fang and Yao, Bu-Fan and Zhang, Wei and Wu, Yue-E and Zhou, Yue and Wang, Ya-Kun and Hao, Guo-Xiang and van den Anker, John and Zheng, Yi and Zhao, Wei},
  title = {Machine learning approach for dosage individualization of azithromycin in children with community‐acquired pneumonia},
  journal = {British Journal of Clinical Pharmacology},
  year = {2025},
  doi = {10.1002/bcp.70050}
}
Kostenlos starten →