Use of Machine Learning for Dosage Individualization of Vancomycin in Neonates

Bo-Hao Tang, Department of Clinical Pharmacy, Key Laboratory of Chemical Biology (Ministry of Education), School of Pharmaceutical Sciences, Cheeloo College of Medicine, Shandong University, Jinan, China.
Jin-Yuan Zhang, Beijing Medicinovo Technology Co. Ltd., Beijing, China.
Karel Allegaert, Department of Development and Regeneration, KU Leuven, Leuven, Belgium.
Guo-Xiang Hao, Department of Clinical Pharmacy, Key Laboratory of Chemical Biology (Ministry of Education), School of Pharmaceutical Sciences, Cheeloo College of Medicine, Shandong University, Jinan, China.
Bu-Fan Yao, Department of Clinical Pharmacy, Key Laboratory of Chemical Biology (Ministry of Education), School of Pharmaceutical Sciences, Cheeloo College of Medicine, Shandong University, Jinan, China.
Stephanie Leroux, Department of Pediatrics, CHU de Rennes, Rennes, France.
Alison H. Thomson, Strathclyde Institute of Pharmacy and Biomedical Sciences, University of Strathclyde, Glasgow, UK.
Ze Yu, Beijing Medicinovo Technology Co. Ltd., Beijing, China.
Fei Gao, Beijing Medicinovo Technology Co. Ltd., Beijing, China.
Yi Zheng, Department of Clinical Pharmacy, Key Laboratory of Chemical Biology (Ministry of Education), School of Pharmaceutical Sciences, Cheeloo College of Medicine, Shandong University, Jinan, China.
Yue Zhou, Department of Clinical Pharmacy, Key Laboratory of Chemical Biology (Ministry of Education), School of Pharmaceutical Sciences, Cheeloo College of Medicine, Shandong University, Jinan, China.
Edmund V. Capparelli, Pediatric Pharmacology and Drug Discovery, University of California, San Diego, CA, USA.
Valerie Biran, Neonatal Intensive Care Unit, Hospital Robert Debre, Paris, France.
Nicolas Simon, Service de Pharmacologie Clinique, CAP-TV, Aix Marseille Univ, APHM, INSERM, IRD, SESSTIM, Hop Sainte Marguerite, Marseille, France.
Bernd Meibohm, Department of Pharmaceutical Sciences, University of Tennessee Health Science Center, Memphis, TN, USA.
Yoke-Lin Lo, Department of Pharmacy, Faculty of Medicine, University of Malaya, Kuala Lumpur, Malaysia.
Remedios Marques, Department of Pharmacy Services, La Fe Hospital, Valencia, Spain.
Jose-Esteban Peris, Department of Pharmacy and Pharmaceutical Technology, University of Valencia, Valencia, Spain.
Irja Lutsar, Institute of Medical Microbiology, University of Tartu, Tartu, Estonia.
Jumpei Saito, Department of Pharmacy, National Children's Hospital National Center for Child Health and Development, Tokyo, Japan.
Evelyne Jacqz-Aigrain, Department of Pediatric Pharmacology and Pharmacogenetics, Hospital Robert Debre, APHP, Paris, France.
John van den Anker, Division of Clinical Pharmacology, Children's National Hospital, Washington, DC, USA.
Yue-E Wu, Department of Clinical Pharmacy, Key Laboratory of Chemical Biology (Ministry of Education), School of Pharmaceutical Sciences, Cheeloo College of Medicine, Shandong University, Jinan, China.
Wei Zhao, Department of Clinical Pharmacy, Key Laboratory of Chemical Biology (Ministry of Education), School of Pharmaceutical Sciences, Cheeloo College of Medicine, Shandong University, Jinan, China. zhao4wei2@hotmail.com.

Document Type

Journal Article

Publication Date

6-10-2023

Journal

Clinical pharmacokinetics

DOI

10.1007/s40262-023-01265-z

Abstract

BACKGROUND AND OBJECTIVE: High variability in vancomycin exposure in neonates requires advanced individualized dosing regimens. Achieving steady-state trough concentration (C) and steady-state area-under-curve (AUC) targets is important to optimize treatment. The objective was to evaluate whether machine learning (ML) can be used to predict these treatment targets to calculate optimal individual dosing regimens under intermittent administration conditions. METHODS: C were retrieved from a large neonatal vancomycin dataset. Individual estimates of AUC were obtained from Bayesian post hoc estimation. Various ML algorithms were used for model building to C and AUC. An external dataset was used for predictive performance evaluation. RESULTS: Before starting treatment, C can be predicted a priori using the Catboost-based C-ML model combined with dosing regimen and nine covariates. External validation results showed a 42.5% improvement in prediction accuracy by using the ML model compared with the population pharmacokinetic model. The virtual trial showed that using the ML optimized dose; 80.3% of the virtual neonates achieved the pharmacodynamic target (C in the range of 10-20 mg/L), much higher than the international standard dose (37.7-61.5%). Once therapeutic drug monitoring (TDM) measurements (C) in patients have been obtained, AUC can be further predicted using the Catboost-based AUC-ML model combined with C and nine covariates. External validation results showed that the AUC-ML model can achieve an prediction accuracy of 80.3%. CONCLUSION: C-based and AUC-based ML models were developed accurately and precisely. These can be used for individual dose recommendations of vancomycin in neonates before treatment and dose revision after the first TDM result is obtained, respectively.

Department

Pediatrics

Link to Full Text

Share

COinS