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

Woillard, Jean‐Baptiste; Labriffe, Marc; Prémaud, Aurélie; Marquet, Pierre

doi:10.1016/j.phrs.2021.105578

Cited by 37 publications

(39 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For each scenario, 1000 subjects were used for the simulation. The PK parameters and their BSVs used in simulations for LSS are listed in Table 1, and the proportional residual error was set to 0.01% for the Monte Carlo simulations to avoid unrealistic concentration‐time profiles 51 …”

Section: Methodsmentioning

confidence: 99%

“…The PK parameters and their BSVs used in simulations for LSS are listed in Table 1, and the proportional residual error was set to 0.01% for the Monte Carlo simulations to avoid unrealistic concentrationtime profiles. 51 The total mycophenolic acid concentration-time profiles (1 sample every 0.5 hour) at steady state were obtained from the simulations. The simulation data set was randomly assigned to training (n = 750) and test (n = 250) subsets.…”

Section: Simulation Analysismentioning

confidence: 99%

See 1 more Smart Citation

Effect of Meal Timings and Meal Content on the AUC_0‐12h of Mycophenolic Acid: A Simulation Study

Qian

Jiao

Zhong

2022

Clinical Pharm in Drug Dev

View full text Add to dashboard Cite

Meal timings and content related to gallbladder emptying in the enterohepatic circulation are important for explaining the high variability in mycophenolic acid exposure. The limited sampling strategy (LSS) was established to estimate the area under the plasma concentration–time curve from time 0 to 12 hours (AUC0‐12h) of mycophenolic acid in therapeutic drug monitoring. The aim of this study is to investigate the effect of meal timings and content on the AUC0‐12h of mycophenolic acid and to assess the influence of meals on LSS. A mycophenolic acid pharmacokinetic model with a mechanism‐based enterohepatic circulation process was employed to perform simulations under various assumed meal scenarios. The simulations were compared to evaluate the effect of meal timings and meal content on mycophenolic acid AUC0‐12h. Monte Carlo simulations were performed using the meal parameter with the greatest impact on mycophenolic acid AUC0‐12h as a variable. The corresponding LSS equations were established, and the predictive performance was assessed. Both the meal timings and meal content affected the mycophenolic acid AUC0‐12h, and the postdose fasting period had the greatest impact. The predictive performance of the LSS is sensitive to the postdose fasting period. Therefore, meal timings may improve the estimation of mycophenolic acid AUC0‐12h and the efficacy of therapeutic drug monitoring.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Simulation Analysismentioning

confidence: 99%

Effect of Meal Timings and Meal Content on the AUC_0‐12h of Mycophenolic Acid: A Simulation Study

Qian

Jiao

Zhong

2022

Clinical Pharm in Drug Dev

View full text Add to dashboard Cite

show abstract

“…The authors show that an ensemble model integrating both an artificial neural network (ANN) and a population PK model best described remifentanil plasma concentration over time [ 5 ]. In addition, Woillard et al [ 6 , 7 ] have shown that the XGBoost algorithm is appropriate for predictions of tacrolimus and mycophenolate mofetil exposure. Woillard et al [ 6 ] and Poynton et al [ 5 ] were some of the first authors to apply ML to PK datasets.…”

Section: Introductionmentioning

confidence: 99%

“…In addition, Woillard et al [ 6 , 7 ] have shown that the XGBoost algorithm is appropriate for predictions of tacrolimus and mycophenolate mofetil exposure. Woillard et al [ 6 ] and Poynton et al [ 5 ] were some of the first authors to apply ML to PK datasets. While ML has the advantage of being fast and efficient, as well as being able to handle large datasets, PM models are based on biological mechanisms, contributing to mechanistical understanding, biological interpretability of the results and the potential to simulate in silico experiments from the model.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning and Pharmacometrics for Prediction of Pharmacokinetic Data: Differences, Similarities and Challenges Illustrated with Rifampicin

Keutzer

you²,

Farnoud³

et al. 2022

Pharmaceutics

View full text Add to dashboard Cite

Pharmacometrics (PM) and machine learning (ML) are both valuable for drug development to characterize pharmacokinetics (PK) and pharmacodynamics (PD). Pharmacokinetic/pharmacodynamic (PKPD) analysis using PM provides mechanistic insight into biological processes but is time- and labor-intensive. In contrast, ML models are much quicker trained, but offer less mechanistic insights. The opportunity of using ML predictions of drug PK as input for a PKPD model could strongly accelerate analysis efforts. Here exemplified by rifampicin, a widely used antibiotic, we explore the ability of different ML algorithms to predict drug PK. Based on simulated data, we trained linear regressions (LASSO), Gradient Boosting Machines, XGBoost and Random Forest to predict the plasma concentration-time series and rifampicin area under the concentration-versus-time curve from 0–24 h (AUC0–24h) after repeated dosing. XGBoost performed best for prediction of the entire PK series (R2: 0.84, root mean square error (RMSE): 6.9 mg/L, mean absolute error (MAE): 4.0 mg/L) for the scenario with the largest data size. For AUC0–24h prediction, LASSO showed the highest performance (R2: 0.97, RMSE: 29.1 h·mg/L, MAE: 18.8 h·mg/L). Increasing the number of plasma concentrations per patient (0, 2 or 6 concentrations per occasion) improved model performance. For example, for AUC0–24h prediction using LASSO, the R2 was 0.41, 0.69 and 0.97 when using predictors only (no plasma concentrations), 2 or 6 plasma concentrations per occasion as input, respectively. Run times for the ML models ranged from 1.0 s to 8 min, while the run time for the PM model was more than 3 h. Furthermore, building a PM model is more time- and labor-intensive compared with ML. ML predictions of drug PK could thus be used as input into a PKPD model, enabling time-efficient analysis.

show abstract

“…A previous study has reported that an ensemble model that integrates artificial neural networks and non-linear mixed-effects modeling (NONMEM) generates more powerful predictions than either method ( Poynton et al, 2009 ). Furthermore, owing to the potential roles of ML and AI in connecting big data to pharmacometrics ( McComb et al, 2022 ), these combined approaches have been used to accurately estimate pharmacokinetic parameters (e.g., drug exposure and drug clearance) ( Tang et al, 2021 ; Woillard et al, 2021 ). Nevertheless, various complex mathematical models for drugs and diseases generally need to be understood and chosen to use these methods, where this may render the modeling process laborious and time consuming ( Zhu et al, 2021a ).…”

Section: Introductionmentioning

confidence: 99%

An interpretable stacking ensemble learning framework based on multi-dimensional data for real-time prediction of drug concentration: The example of olanzapine

Zhu

Xiao

et al. 2022

Front. Pharmacol.

View full text Add to dashboard Cite

Background and Aim: Therapeutic drug monitoring (TDM) has evolved over the years as an important tool for personalized medicine. Nevertheless, some limitations are associated with traditional TDM. Emerging data-driven model forecasting [e.g., through machine learning (ML)-based approaches] has been used for individualized therapy. This study proposes an interpretable stacking-based ML framework to predict concentrations in real time after olanzapine (OLZ) treatment.Methods: The TDM-OLZ dataset, consisting of 2,142 OLZ measurements and 472 features, was formed by collecting electronic health records during the TDM of 927 patients who had received OLZ treatment. We compared the performance of ML algorithms by using 10-fold cross-validation and the mean absolute error (MAE). The optimal subset of features was analyzed by a random forest-based sequential forward feature selection method in the context of the top five heterogeneous regressors as base models to develop a stacked ensemble regressor, which was then optimized via the grid search method. Its predictions were explained by using local interpretable model-agnostic explanations (LIME) and partial dependence plots (PDPs).Results: A state-of-the-art stacking ensemble learning framework that integrates optimized extra trees, XGBoost, random forest, bagging, and gradient-boosting regressors was developed for nine selected features [i.e., daily dose (OLZ), gender_male, age, valproic acid_yes, ALT, K, BW, MONO#, and time of blood sampling after first administration]. It outperformed other base regressors that were considered, with an MAE of 0.064, R-square value of 0.5355, mean squared error of 0.0089, mean relative error of 13%, and ideal rate (the percentages of predicted TDM within ± 30% of actual TDM) of 63.40%. Predictions at the individual level were illustrated by LIME plots, whereas the global interpretation of associations between features and outcomes was illustrated by PDPs.Conclusion: This study highlights the feasibility of the real-time estimation of drug concentrations by using stacking-based ML strategies without losing interpretability, thus facilitating model-informed precision dosing.

show abstract

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

Cited by 37 publications

References 16 publications

Effect of Meal Timings and Meal Content on the AUC_0‐12h of Mycophenolic Acid: A Simulation Study

Effect of Meal Timings and Meal Content on the AUC_0‐12h of Mycophenolic Acid: A Simulation Study

Machine Learning and Pharmacometrics for Prediction of Pharmacokinetic Data: Differences, Similarities and Challenges Illustrated with Rifampicin

An interpretable stacking ensemble learning framework based on multi-dimensional data for real-time prediction of drug concentration: The example of olanzapine

Contact Info

Product

Resources

About

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

Cited by 37 publications

References 16 publications

Effect of Meal Timings and Meal Content on the AUC0‐12h of Mycophenolic Acid: A Simulation Study

Effect of Meal Timings and Meal Content on the AUC0‐12h of Mycophenolic Acid: A Simulation Study

Machine Learning and Pharmacometrics for Prediction of Pharmacokinetic Data: Differences, Similarities and Challenges Illustrated with Rifampicin

An interpretable stacking ensemble learning framework based on multi-dimensional data for real-time prediction of drug concentration: The example of olanzapine

Contact Info

Product

Resources

About

Effect of Meal Timings and Meal Content on the AUC_0‐12h of Mycophenolic Acid: A Simulation Study

Effect of Meal Timings and Meal Content on the AUC_0‐12h of Mycophenolic Acid: A Simulation Study