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

Abstract

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.

pyDarwin: A Machine Learning Enhanced Automated Nonlinear Mixed‐Effect Model Selection Toolbox

“…Bies et al demonstrated that the genetic algorithm (GA), as a combinatorial optimization approach, can efficiently develop a robust optimal model in an enormous search space. More recently, Keutzer et al 7 applied supervised ML algorithms, such as random forest (RF) and gradient boosting machine, in selecting the key features in the process of implementing a PK model of rifampicin. These applications have convincingly demonstrated the enormous potential of applying ML to nonlinear mixed-effect model selection.…”

Reinventing Therapeutic Proteins: Optimizing Investments and Meeting Humanitarian Needs

“…Clinically tested effects of galcanezumab dose (120mg and 240mg), validated through PK modeling, indicated a steady decrease in the concentration of free ligands resulting in the development of efficacious dose regimens. 160 A PK and target engagement (molecular interaction) study of anti-interferon-γ-induced protein 10 (IP-10) mAb was characterized, which concluded optimal dose strategy and scheduling of drug administration, i.e., approximately eight subcutaneously delivered dose intervals were required weekly in this case to reach steady state. 161 Specialized cell-based bioassays or potency assays, including ELISA, binding assays, competitive assays, cell signaling, ligand binding, proliferation, and proliferation suppression, are essential in ascertaining the mechanism of action and similarity with the parent molecule.…”

Pharmacometrics in tuberculosis: progress and opportunities

“…Although still a relatively undeveloped area, experience with the application of ML/AI approaches for investigating doseexposure relationships is growing -an application of ML to predict rifampicin PK is a recent example [16] .…”

“…Artificial intelligence (AI) and machine learning (ML) techniques are becoming more frequently applied to health care [14] , and their use in pharmacometrics is no exception [15] . Within the pharma-ceutical industry, they have been applied successfully to drug discovery, and there is an opportunity to utilize classical pharmacometric tools together with AI/ML in order to enhance drug development [16] .…”