Frontiers in Medical Science Research, 2025, 7(4); doi: 10.25236/FMSR.2025.070406.
Wen Huang1,2, Ying Li2, Jiangyan Lu2, Nansong Wang2
1School of Life Sciences and Biopharmaceutical Science, Shenyang Pharmaceutical University, Shenyang, 110016, China
2Department of Pharmacy, The University of Hong Kong-Shenzhen Hospital, Shenzhen, Guangdong, 518000, China
This study aims to determine if integrating machine learning (ML) approaches with power analysis for correlated covariates enhances predictive performance in modeling. Two drugs were selected to apply population pharmacokinetics methodology. Parameter-covariate relationships were estimated using stepwise covariate modeling (SCM). Power analysis identified correlated true covariates for each parameter chosen by SCM. If correlated true covariates were identified, ML methods further selected the most significant covariate. The calibrated model utilizing this significant covariate was compared to the SCM model, evaluating performance using relative error. Non-compartment analysis (NCA) calculated individual reference AUC, enabling comparison of AUCs from calibrated and SCM models with the reference AUC to assess predictive performance. Results showed that calibrated models outperformed SCM models, with R² values exceeding 80%. Overall, the calibrated models predicted AUC more accurately than the SCM models. Power analysis helped eliminate false covariates among correlated ones, while ML methods provided criteria for selecting covariates from the identified true covariates. Thus, combining these methods can enhance population pharmacokinetic model predictions.
machine learning, calibrated models, pharmacokinetic
Wen Huang, Ying Li, Jiangyan Lu, Nansong Wang. Machine Learning Approaches Combined with Power Analysis to Improve the Prediction of Population Pharmacokinetic Modeling. Frontiers in Medical Science Research (2025), Vol. 7, Issue 4: 47-55. https://doi.org/10.25236/FMSR.2025.070406.
[1] WORKGROUP E M, MARSHALL S F, BURGHAUS R, et al. Good Practices in Model-Informed Drug Discovery and Development: Practice, Application, and Documentation [J]. CPT Pharmacometrics Syst Pharmacol, 2016, 5(3): 93-122.
[2] MARSHALL S, MADABUSHI R, MANOLIS E, et al. Model-Informed Drug Discovery and Development: Current Industry Good Practice and Regulatory Expectations and Future Perspectives [J]. CPT Pharmacometrics Syst Pharmacol, 2019, 8(2): 87-96.
[3] ZOU Y, TANG F, NG C M. A Modified Hybrid Wald’s Approximation Method for Efficient Covariate Selection in Population Pharmacokinetic Analysis [J]. The AAPS Journal, 2021, 23(2): 37.
[4] WAHLBY U, JONSSON E N, KARLSSON M O. Comparison of stepwise covariate model building strategies in population pharmacokinetic-pharmacodynamic analysis [J]. AAPS PharmSci, 2002, 4(4): E27.
[5] RIBBING J, JONSSON E N. Power, selection bias and predictive performance of the Population Pharmacokinetic Covariate Model [J]. J Pharmacokinet Pharmacodyn, 2004, 31(2): 109-34.
[6] UECKERT S, KARLSSON M O, HOOKER A C. Accelerating Monte Carlo power studies through parametric power estimation [J]. J Pharmacokinet Pharmacodyn, 2016, 43(2): 223-34.
[7] RETOUT S, COMETS E, SAMSON A, et al. Design in nonlinear mixed effects models: optimization using the Fedorov-Wynn algorithm and power of the Wald test for binary covariates [J]. Stat Med, 2007, 26(28): 5162-79.
[8] UECKERT S, HENNIG S, NYBERG J, et al. Optimizing disease progression study designs for drug effect discrimination [J]. J Pharmacokinet Pharmacodyn, 2013, 40(5): 587-96.
[9] KLOPROGGE F, SIMPSON J A, DAY N P, et al. Statistical power calculations for mixed pharmacokinetic study designs using a population approach [J]. Aaps j, 2014, 16(5): 1110-8.
[10] VONG C, BERGSTRAND M, NYBERG J, et al. Rapid sample size calculations for a defined likelihood ratio test-based power in mixed-effects models [J]. AAPS J, 2012, 14(2): 176-86.
[11] AYRAL G, SI ABDALLAH J-F, MAGNARD C, et al. A novel method based on unbiased correlations tests for covariate selection in nonlinear mixed effects models: The COSSAC approach [J]. CPT: Pharmacometrics & Systems Pharmacology, 2021, 10(4): 318-29.
[12] TANG B H, GUAN Z, ALLEGAERT K, et al. Drug Clearance in Neonates: A Combination of Population Pharmacokinetic Modelling and Machine Learning Approaches to Improve Individual Prediction [J]. Clin Pharmacokinet, 2021, 60(11): 1435-48.
[13] LIANG H, TSUI B Y, NI H, et al. Evaluation and accurate diagnoses of pediatric diseases using artificial intelligence [J]. Nat Med, 2019, 25(3): 433-8.
[14] KHANDELWAL A, KRASOWSKI M D, RESCHLY E J, et al. Machine learning methods and docking for predicting human pregnane X receptor activation [J]. Chem Res Toxicol, 2008, 21(7): 1457-67.
[15] JEON J, NIM S, TEYRA J, et al. A systematic approach to identify novel cancer drug targets using machine learning, inhibitor design and high-throughput screening [J]. Genome Med, 2014, 6(7): 57.
[16] KANG S H, POYNTON M R, KIM K M, et al. Population pharmacokinetic and pharmacodynamic models of remifentanil in healthy volunteers using artificial neural network analysis [J]. Br J Clin Pharmacol, 2007, 64(1): 3-13.
[17] MCCOMB M, BIES R, RAMANATHAN M. Machine learning in pharmacometrics: Opportunities and challenges [J]. Br J Clin Pharmacol, 2022, 88(4): 1482-99.
[18] YANG J. Fast TreeSHAP: Accelerating SHAP Value Computation for Trees [J]. 2021.
[19] ALTMANN A, TOLOSI L, SANDER O, et al. Permutation importance: a corrected feature importance measure [J]. Bioinformatics, 2010, 26(10): 1340-7.
[20] BIDESHWAR K. KATARIA S A V H F E A. The Pharmacokinetics of Propofol in Children Using Three Different Data Analysis Approaches [J]. 1994, 80: 104–22.
[21] ROSS A K, DAVIS P J, DEAR GD G L, et al. Pharmacokinetics of remifentanil in anesthetized pediatric patients undergoing elective surgery or diagnostic procedures [J]. Anesth Analg, 2001, 93(6): 1393-401, table of contents.
[22] SCHNIDER T W, MINTO C F, GAMBUS P L, et al. The influence of method of administration and covariates on the pharmacokinetics of propofol in adult volunteers [J]. Anesthesiology, 1998, 88(5): 1170-82.
[23] TRAUB S L, KICHEN L. Estimating ideal body mass in children [J]. Am J Hosp Pharm, 1983, 40(1): 107-10.
[24] SAHINOVIC M M, STRUYS M, ABSALOM A R. Clinical Pharmacokinetics and Pharmacodynamics of Propofol [J]. Clin Pharmacokinet, 2018, 57(12): 1539-58.
[25] KAMINSKI B, JAKUBCZYK M, SZUFEL P. A framework for sensitivity analysis of decision trees [J]. Cent Eur J Oper Res, 2018, 26(1): 135-59.
[26] SVETNIK V, LIAW A, TONG C, et al. Random Forest: A Classification and Regression Tool for Compound Classification and QSAR Modeling [J]. Journal of Chemical Information and Computer Sciences, 2003, 43(6): 1947-58.
[27] RETOUT S D S, MENTRE F. Development and implementation of the population Fisher [J]. Comput Methods Programs Biomed, 2001, 65(2): 141–51.
[28] MINTO CHARLES F, SCHNIDER THOMAS W, EGAN TALMAGE D, et al. Influence of Age and Gender on the Pharmacokinetics and Pharmacodynamics of Remifentanil: I. Model Development [J]. Anesthesiology, 1997, 86(1): 10-23.