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

Bo-Hao Tang, Department of Pharmacy, The Second Hospital, Cheeloo College of Medicine, Shandong University, Jinan, China.
Shu-Meng Fu, 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 Pharmaceutical Sciences, Cheeloo College of Medicine, Shandong University, Jinan, China.
Li-Yuan Tian, Department of Respiratory Care, Children's Hospital of Hebei Province affiliated to Hebei Medical University, Shijiazhuang, China.
Xin-Fang Zhang, 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 Pharmaceutical Sciences, Cheeloo College of Medicine, Shandong University, Jinan, China.
Bu-Fan Yao, 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 Pharmaceutical Sciences, Cheeloo College of Medicine, Shandong University, Jinan, China.
Wei Zhang, 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 Pharmaceutical Sciences, Cheeloo College of Medicine, Shandong University, Jinan, China.
Yue-E Wu, 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 Pharmaceutical Sciences, Cheeloo College of Medicine, Shandong University, Jinan, China.
Yue Zhou, 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 Pharmaceutical Sciences, Cheeloo College of Medicine, Shandong University, Jinan, China.
Ya-Kun Wang, Department of Respiratory Care, Children's Hospital of Hebei Province affiliated to Hebei Medical University, Shijiazhuang, China.
Guo-Xiang Hao, 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 Pharmaceutical Sciences, Cheeloo College of Medicine, Shandong University, Jinan, China.
John van den Anker, Division of Clinical Pharmacology, Children's National Hospital, Washington, DC, USA.
Yi Zheng, 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 Pharmaceutical Sciences, Cheeloo College of Medicine, Shandong University, Jinan, China.
Wei Zhao, Department of Pharmacy, The Second Hospital, Cheeloo College of Medicine, Shandong University, Jinan, China.

Document Type

Journal Article

Publication Date

4-3-2025

Journal

British journal of clinical pharmacology

DOI

10.1002/bcp.70050

Keywords

azithromycin; children; individual therapy; machine‐learning; pharmacometrics

Abstract

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) 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 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 using patients' characteristics and after the trough concentration (C) 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 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 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 of azithromycin successfully and could be used for individual dose adjustment in children before treatment and after obtaining C.

Department

Pediatrics

Link to Full Text

Share

COinS