Skip to main content

ORIGINAL RESEARCH article

Front. Pharmacol.
Sec. Drug Metabolism and Transport
Volume 15 - 2024 | doi: 10.3389/fphar.2024.1389271
This article is part of the Research Topic Drug Metabolism and Transport: The Frontier of Personalized Medicine Volume II View all 5 articles

Improving prediction of Tacrolimus concentration using a combination of population pharmacokinetic modeling and machine learning in Chinese renal transplant recipients

Provisionally accepted
Yu-Ping Wang Yu-Ping Wang 1Xiao-Ling Lu Xiao-Ling Lu 1Kun Shao Kun Shao 2Hao-Qiang Shi Hao-Qiang Shi 1Pei-Jun Zhou Pei-Jun Zhou 2Bing Chen Bing Chen 3*
  • 1 1. Department of Pharmacy, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
  • 2 2. Center for Organ Transplantation, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
  • 3 Department of Pharmacy, Ruijin Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China

The final, formatted version of the article will be published soon.

    AIMS: The population pharmacokinetic (PPK) model-based machine learning (ML) approach offers a novel perspective on individual concentration prediction. This study aimed to establish a PPKbased ML model for predicting tacrolimus (TAC) concentrations in Chinese renal transplant recipients. METHODS: Conventional TAC monitoring data from 127 Chinese renal transplant patients were divided into training (80%) and testing (20%) datasets. A PPK model was developed using the training group data. ML models were then established based on individual pharmacokinetic data derived from the PPK basic model. The prediction performances of the PPK-based ML model and Bayesian forecasting approach were compared using data from the test group. RESULTS: The final PPK model, incorporating hematocrit and CYP3A5 genotypes as covariates, was successfully established. Individual predictions of TAC using the PPK basic model, postoperative date, CYP3A5 genotype, and hematocrit showed improved rankings in ML model construction. XGBoost, based on the TAC PPK, exhibited the best prediction performance. CONCLUSION: The PPK-based machine learning approach emerges as a superior option for predicting TAC concentrations in Chinese renal transplant recipients.

    Keywords: Yu-Ping Wang and Xiao-Ling Lu contributed equally to the study Renal transplant recipients, Population pharmacokinetic, machine learning, XGBboost, Tacrolimus

    Received: 21 Feb 2024; Accepted: 15 Apr 2024.

    Copyright: © 2024 Wang, Lu, Shao, Shi, Zhou and Chen. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Bing Chen, Department of Pharmacy, Ruijin Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, 200025, China

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.