Population Pharmacokinetic Modeling Combined With Machine Learning Approach Improved Tacrolimus Trough Concentration Prediction in Chinese Adult Liver Transplant Recipients

This study aimed to develop and evaluate a population pharmacokinetic (PPK) combined machine learning approach to predict tacrolimus trough concentrations for Chinese adult liver transplant recipients in the early post-transplant period. Tacrolimus trough concentrations were retrospectively collected from routine monitoring records of liver transplant recipients and divided into the training dataset (1287 concentrations in 145 recipients) and the test dataset (296 concentrations in 36 recipients). A PPK model was first established using NONMEM. Then a machine learning model of Xgboost was adapted to fit the estimated individual pharmacokinetic parameters obtained from the PPK model with Bayesian forecasting. The performance of the final PPK model and Xgboost model was compared in the test dataset. In the final PPK model, tacrolimus daily dose, postoperative days, hematocrit, aspartate aminotransferase, and concomitant with voriconazole were identified to significantly influence the clearance. The postoperative days along with hematocrit significantly influence the volume of distribution. In the Xgboost model, the first five predictors for predicting the clearance were concomitant with voriconazole, sex, SNPs of CYP3A4*1G and CYP3A5*3 in recipients, and tacrolimus daily dose, for the volume of distribution were postoperative days, age, weight, total bilirubin and Graft: recipient weight ratio. In the test dataset, the Xgboost model showed the minimum median prediction error of tacrolimus concentrations than the PPK model with or without Bayesian forecasting. In conclusion, a PPK combined machine learning approach could improve the prediction of tacrolimus concentrations for Chinese adult liver transplant recipients in the early post-transplant period. This article is protected by copyright. All rights reserved.