UNASSIGNED: 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.
UNASSIGNED: 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.
UNASSIGNED: The PPK-based machine learning approach emerges as a superior option for predicting TAC concentrations in Chinese renal transplant recipients.
■来自127名中国肾移植患者的常规TAC监测数据分为训练(80%)和测试(20%)数据集。使用训练组数据开发了PPK模型。然后基于来自PPK基本模型的个体药代动力学数据建立ML模型。使用来自测试组的数据比较了基于PPK的ML模型和贝叶斯预测方法的预测性能。
■最终的PPK模型,合并血细胞比容和CYP3A5基因型作为协变量,成功建立。使用PPK基本模型对TAC的个体预测,术后日期,CYP3A5基因型,和血细胞比容在ML模型构建中显示出改进的排名。XGBoost,基于TACPPK,表现出最佳的预测性能。
■基于PPK的机器学习方法成为预测中国肾移植受者TAC浓度的首选方法。