Adoption of Machine Learning in Pharmacometrics: An Overview of Recent Implementations and Their Considerations

Overview

Journal Pharmaceutics

Publisher MDPI

Date 2022 Sep 23

PMID 36145562

Authors

Alexander Janssen

Frank C Bennis

Ron A A Mathot

Affiliations

Soon will be listed here.

Abstract

Pharmacometrics is a multidisciplinary field utilizing mathematical models of physiology, pharmacology, and disease to describe and quantify the interactions between medication and patient. As these models become more and more advanced, the need for advanced data analysis tools grows. Recently, there has been much interest in the adoption of machine learning (ML) algorithms. These algorithms offer strong function approximation capabilities and might reduce the time spent on model development. However, ML tools are not yet an integral part of the pharmacometrics workflow. The goal of this work is to discuss how ML algorithms have been applied in four stages of the pharmacometrics pipeline: data preparation, hypothesis generation, predictive modelling, and model validation. We will also discuss considerations before the use of ML algorithms with respect to each topic. We conclude by summarizing applications that hold potential for adoption by pharmacometricians.

Citing Articles

From Prospective Evaluation to Practice: Model-Informed Dose Optimization in Oncology.

Agema B, Koch B, Mathijssen R, Koolen S Drugs. 2025; .

PMID: 39939511 DOI: 10.1007/s40265-025-02152-6.

Artificial Intelligence and Machine Learning Applications to Pharmacokinetic Modeling and Dose Prediction of Antibiotics: A Scoping Review.

Varela-Rey I, Bandin-Vilar E, Toja-Camba F, Canizo-Outeirino A, Cajade-Pascual F, Ortega-Hortas M Antibiotics (Basel). 2025; 13(12).

PMID: 39766593 PMC: 11672403. DOI: 10.3390/antibiotics13121203.

Mixed effect estimation in deep compartment models: Variational methods outperform first-order approximations.

Janssen A, Bennis F, Cnossen M, Mathot R J Pharmacokinet Pharmacodyn. 2024; 51(6):797-808.

PMID: 38965175 PMC: 11579087. DOI: 10.1007/s10928-024-09931-w.

Simulating realistic patient profiles from pharmacokinetic models by a machine learning postprocessing correction of residual variability.

Kaikousidis C, Bies R, Dokoumetzidis A CPT Pharmacometrics Syst Pharmacol. 2024; 13(9):1476-1487.

PMID: 38877660 PMC: 11533097. DOI: 10.1002/psp4.13182.

Covariate modeling in pharmacometrics: General points for consideration.

Sanghavi K, Ribbing J, Rogers J, Ahmed M, Karlsson M, Holford N CPT Pharmacometrics Syst Pharmacol. 2024; 13(5):710-728.

PMID: 38566433 PMC: 11098153. DOI: 10.1002/psp4.13115.

References

McComb M, Bies R, Ramanathan M . Machine learning in pharmacometrics: Opportunities and challenges. Br J Clin Pharmacol. 2021; 88(4):1482-1499. DOI: 10.1111/bcp.14801. View

Ribbing J, Jonsson E . Power, selection bias and predictive performance of the Population Pharmacokinetic Covariate Model. J Pharmacokinet Pharmacodyn. 2004; 31(2):109-34. DOI: 10.1023/b:jopa.0000034404.86036.72. View

Xu Y, Lou H, Chen J, Jiang B, Yang D, Hu Y . Application of a Backpropagation Artificial Neural Network in Predicting Plasma Concentration and Pharmacokinetic Parameters of Oral Single-Dose Rosuvastatin in Healthy Subjects. Clin Pharmacol Drug Dev. 2020; 9(7):867-875. DOI: 10.1002/cpdd.809. View

Gong X, Hu M, Zhao L . Big Data Toolsets to Pharmacometrics: Application of Machine Learning for Time-to-Event Analysis. Clin Transl Sci. 2018; 11(3):305-311. PMC: 5944589. DOI: 10.1111/cts.12541. View

Guerra R, Carvalho A, Mateus P . Model selection for clustering of pharmacokinetic responses. Comput Methods Programs Biomed. 2018; 162:11-18. DOI: 10.1016/j.cmpb.2018.05.002. View

Lundberg S, Erion G, Chen H, DeGrave A, Prutkin J, Nair B . From Local Explanations to Global Understanding with Explainable AI for Trees. Nat Mach Intell. 2020; 2(1):56-67. PMC: 7326367. DOI: 10.1038/s42256-019-0138-9. View

Bram D, Parrott N, Hutchinson L, Steiert B . Introduction of an artificial neural network-based method for concentration-time predictions. CPT Pharmacometrics Syst Pharmacol. 2022; 11(6):745-754. PMC: 9197537. DOI: 10.1002/psp4.12786. View

Chiu Y, Chen H, Zhang T, Zhang S, Gorthi A, Wang L . Predicting drug response of tumors from integrated genomic profiles by deep neural networks. BMC Med Genomics. 2019; 12(Suppl 1):18. PMC: 6357352. DOI: 10.1186/s12920-018-0460-9. View

Kapralos I, Dokoumetzidis A . Population Pharmacokinetic Modelling of the Complex Release Kinetics of Octreotide LAR: Defining Sub-Populations by Cluster Analysis. Pharmaceutics. 2021; 13(10). PMC: 8537465. DOI: 10.3390/pharmaceutics13101578. View

10.

Kanders S, Pisanu C, Bandstein M, Jonsson J, Castelao E, Pistis G . A pharmacogenetic risk score for the evaluation of major depression severity under treatment with antidepressants. Drug Dev Res. 2019; 81(1):102-113. PMC: 7028038. DOI: 10.1002/ddr.21609. View

11.

Ismail M, Sale M, Yu Y, Pillai N, Liu S, Pflug B . Development of a genetic algorithm and NONMEM workbench for automating and improving population pharmacokinetic/pharmacodynamic model selection. J Pharmacokinet Pharmacodyn. 2021; 49(2):243-256. DOI: 10.1007/s10928-021-09782-9. View

12.

Sibieude E, Khandelwal A, Girard P, Hesthaven J, Terranova N . Population pharmacokinetic model selection assisted by machine learning. J Pharmacokinet Pharmacodyn. 2021; 49(2):257-270. PMC: 8940812. DOI: 10.1007/s10928-021-09793-6. View

13.

Wang R, Shao X, Zheng J, Saci A, Qian X, Pak I . A Machine-Learning Approach to Identify a Prognostic Cytokine Signature That Is Associated With Nivolumab Clearance in Patients With Advanced Melanoma. Clin Pharmacol Ther. 2019; 107(4):978-987. DOI: 10.1002/cpt.1724. View

14.

Wu H, Wu L . A multiple imputation method for missing covariates in non-linear mixed-effects models with application to HIV dynamics. Stat Med. 2001; 20(12):1755-69. DOI: 10.1002/sim.816. View

15.

Chaturvedula A, Calad-Thomson S, Liu C, Sale M, Gattu N, Goyal N . Artificial Intelligence and Pharmacometrics: Time to Embrace, Capitalize, and Advance?. CPT Pharmacometrics Syst Pharmacol. 2019; 8(7):440-443. PMC: 6657004. DOI: 10.1002/psp4.12418. View

16.

Janssen A, Leebeek F, Cnossen M, Mathot R . Deep compartment models: A deep learning approach for the reliable prediction of time-series data in pharmacokinetic modeling. CPT Pharmacometrics Syst Pharmacol. 2023; 11(7):934-945. PMC: 9286722. DOI: 10.1002/psp4.12808. View

17.

Ulas C, Das D, Thrippleton M, Valdes Hernandez M, Armitage P, Makin S . Convolutional Neural Networks for Direct Inference of Pharmacokinetic Parameters: Application to Stroke Dynamic Contrast-Enhanced MRI. Front Neurol. 2019; 9:1147. PMC: 6331464. DOI: 10.3389/fneur.2018.01147. View

18.

Ciuculete D, Bandstein M, Benedict C, Waeber G, Vollenweider P, Lind L . A genetic risk score is significantly associated with statin therapy response in the elderly population. Clin Genet. 2016; 91(3):379-385. DOI: 10.1111/cge.12890. View

19.

Xiang R, Wang W, Yang L, Wang S, Xu C, Chen X . A Comparison for Dimensionality Reduction Methods of Single-Cell RNA-seq Data. Front Genet. 2021; 12:646936. PMC: 8021860. DOI: 10.3389/fgene.2021.646936. View

20.

Danhof M, de Lange E, Della Pasqua O, Ploeger B, Voskuyl R . Mechanism-based pharmacokinetic-pharmacodynamic (PK-PD) modeling in translational drug research. Trends Pharmacol Sci. 2008; 29(4):186-91. DOI: 10.1016/j.tips.2008.01.007. View