Estimation of drug exposure by machine learning based on simulations from published pharmacokinetic models: The example of tacrolimus

• DOI: 10.1016/j.phrs.2021.105578
• Publication Date: 2021-03-26T23:16:47Z
• Authors: Jean-Baptiste Woi...; Marc Labriffe; Aurélie Prémaud; Pierre Marquet
• Keywords: Adult; 0301 basic medicine; mean prediction error POPPK; AUC; therapeutic drug monitoring; MAP-BE; Machine learning Monte Carlo simulations Tacrolimus Xgboost Therapeutic drug monitoring Population pharmacokinetics AI; maximum a posteriori Bayesian estimates; Models, Biological; Tacrolimus; TDM; Machine Learning; 03 medical and health sciences; area-under the curve; machine learning MPE; Humans; population pharmacokinetic RMSE; artificial intelligence; mean prediction error; ML; RMSE; Root mean square error; 004; 3. Good health; maximum a posteriori Bayesian estimates ML; machine learning; Area Under Curve; [SDV.SP.PHARMA]Life Sciences [q-bio]/Pharmaceutical sciences/Pharmacology; POPPK; population pharmacokinetic; area-under the curve MAP-BE; MPE; Monte Carlo Method; Root mean square error TDM; Immunosuppressive Agents; artificial intelligence AUC

We previously demonstrated that Machine learning (ML) algorithms can accurately estimate drug area under the curve (AUC) of tacrolimus or mycophenolate mofetil (MMF) based on limited information, as well as or even better than maximum a posteriori Bayesian estimation (MAP-BE). However, the major limitation in the development of such ML algorithms is the limited availability of large databases of concentration vs. time profiles for such drugs. The objectives of this study were: (i) to develop a Xgboost model to estimate tacrolimus inter-dose AUC based on concentration-time profiles obtained from a literature population pharmacokinetic (POPPK) model using Monte Carlo simulation; and (ii) to compare its performance with that of MAP-BE in external datasets of rich concentration-time profiles. The population parameters of a previously published PK model were used in the mrgsolve R package to simulate 9000 rich interdose tacrolimus profiles (one concentration simulated every 30 min) at steady-state. Data splitting was performed to obtain a training set (75%) and a test set (25%). Xgboost algorithms able to estimate tacrolimus AUC based on 2 or 3 concentrations were developed in the training set and the model with the lowest RMSE in a ten-fold cross-validation experiment was evaluated in the test set, as well as in 4 independent, rich PK datasets from transplant patients. ML algorithms based on 2 or 3 concentrations and a few covariates yielded excellent AUC estimation in the external validation datasets (relative bias < 5% and relative RMSE < 10%), comparable to those obtained with MAP-BE. In conclusion, Xgboost machine learning models trained on concentration-time profiles simulated using literature POPPK models allow accurate tacrolimus AUC estimation based on sparse concentration data. This study paves the way to the development of artificial intelligence at the service of precision therapeutic drug monitoring in different therapeutic areas.