Predicting Pharmacokinetics of Drugs Using Artificial Intelligence Tools: A Systematic Review.

Advanced Search

Mahnaz Ahmadi, Bahareh Alizadeh, Seyed Mohammad Ayyoubzadeh, Mahdiye Abiyarghamsari

Author Information

Mahnaz Ahmadi: Student Research Committee, School of Pharmacy, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
Bahareh Alizadeh: Protein Technology Research Center, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
Seyed Mohammad Ayyoubzadeh: Department of Health Information Management, School of Allied Medical Sciences, Tehran University of Medical Sciences, Tehran, Iran.
Mahdiye Abiyarghamsari: Department of Clinical Pharmacy, School of Pharmacy, Shahid Beheshti University of Medical Sciences, Tehran, 1991953381, Iran. ghamsari@sbmu.ac.ir.

PMID: 38457092 DOI: 10.1007/s13318-024-00883-7

BACKGROUND AND OBJECTIVE: Pharmacokinetic studies encompass the examination of the absorption, distribution, metabolism, and excretion of bioactive compounds. The pharmacokinetics of drugs exert a substantial influence on their efficacy and safety. Consequently, the investigation of pharmacokinetics holds great importance. However, laboratory-based assessment necessitates the use of numerous animals, various materials, and significant time. To mitigate these challenges, alternative methods such as artificial intelligence have emerged as a promising approach. This systematic review aims to review existing studies, focusing on the application of artificial intelligence tools in predicting the pharmacokinetics of drugs.
METHODS: A pre-prepared search strategy based on related keywords was used to search different databases (PubMed, Scopus, Web of Science). The process involved combining articles, eliminating duplicates, and screening articles based on their titles, abstracts, and full text. Articles were selected based on inclusion and exclusion criteria. Then, the quality of the included articles was assessed using an appraisal tool.
RESULTS: Ultimately, 23 relevant articles were included in this study. The clearance parameter received the highest level of investigation, followed by the area under the concentration-time curve (AUC) parameter, in pharmacokinetic studies. Among the various models employed in the articles, Random Forest and eXtreme Gradient Boosting (XGBoost) emerged as the most commonly utilized ones. Generalized Linear Models and Elastic Nets (GLMnet) and Random Forest models showed the most performance in predicting clearance.
CONCLUSION: Overall, artificial intelligence tools offer a robust, rapid, and precise means of predicting various pharmacokinetic parameters based on a dataset containing information of patients or drugs.

Wagner JG. History of pharmacokinetics. Pharmacol Ther. 1981;12(3):537–62. [DOI: 10.1016/0163-7258(81)90097-8]
Lucas AJ, Sproston JL, Barton P, Riley RJ. Estimating human ADME properties, pharmacokinetic parameters and likely clinical dose in drug discovery. Expert Opin Drug Discov. 2019;14(12):1313–27. [DOI: 10.1080/17460441.2019.1660642]
Eddershaw PJ, Beresford AP, Bayliss MK. ADME/PK as part of a rational approach to drug discovery. Drug Discov Today. 2000;5(9):409–14. [DOI: 10.1016/S1359-6446(00)01540-3]
Turfus S, Delgoda R, Picking D, Gurley B. Pharmacokinetics. In: Pharmacognosy: fundamentals, applications and strategy. The Netherlands, Amsterdam: Elsevier Inc; 2017. p. 495–512. [DOI: 10.1016/B978-0-12-802104-0.00025-1]
Lu Z, Kaspera R, Naritomi Y, Wang T. Dose finding in single dose studies by allometric scaling. In: Hock FJ, Gralinski MR, editors. Drug discovery and evaluation: methods in clinical pharmacology. Cham: Springer International Publishing; 2020. p. 671–81. [DOI: 10.1007/978-3-319-68864-0_3]
Erhardtsen E. Pharmacokinetics of recombinant activated factor VII (rFVIIa). in Semin. Thromb. Hemost. 2000.
Kapalka GM. Nutritional and herbal therapies for children and adolescents: a handbook for mental health clinicians. Academic Press; 2009.
Zhu X, Zhang M, Wen Y, Shang D. Machine learning advances the integration of covariates in population pharmacokinetic models: valproic acid as an example. Front Pharmacol. 2022;13: 994665. [>PMCID: ]

Kumar V, Faheem M, Lee KW. A decade of machine learning-based predictive models for human pharmacokinetics: advances and challenges. Drug Discov Today. 2022;27(2):529–37. [DOI: 10.1016/j.drudis.2021.09.013]
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. Clin Pharmacokinet. 2021;60(11):1435–48. [DOI: 10.1007/s40262-021-01033-x]
Labriffe M, Woillard J-B, Debord J, Marquet P. Machine learning algorithms to estimate everolimus exposure trained on simulated and patient pharmacokinetic profiles. CPT Pharmacomet Syst Pharmacol. 2022;11(8):1018–28. [DOI: 10.1002/psp4.12810]
Hughes JH, Keizer RJ. A hybrid machine learning/pharmacokinetic approach outperforms maximum a posteriori Bayesian estimation by selectively flattening model priors. CPT Pharmacomet Syst Pharmacol. 2021;10(10):1150–60. [DOI: 10.1002/psp4.12684]
Mahesh B. Machine learning algorithms-a review. Int J Sci Res. 2020;9(1):381–6.
Chicco D, Warrens MJ, Jurman G. The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. PeerJ Comput Sci. 2021;7: e623. [>PMCID: ]

Hassan CAU, Khan MS, Shah MA. Comparison of machine learning algorithms in data classification. In 2018 24th international conference on automation and computing (ICAC). 2018. IEEE.

Muhamedyev R, Yakunin K, Iskakov S et al. Comparative analysis of classification algorithms. In 2015 9th international conference on application of information and communication technologies (AICT). 2015. IEEE.

Nidhra S, Yanamadala M, Afzal W, Torkar R. Knowledge transfer challenges and mitigation strategies in global software development—a systematic literature review and industrial validation. Int J Inf Manage. 2013;33(2):333–55. [DOI: 10.1016/j.ijinfomgt.2012.11.004]
Einarson KA, Bendtsen KM, Li K, et al. Molecular representations in machine-learning-based prediction of pk parameters for insulin analogs. ACS Omega. 2023;8(26):23566–78. [>PMCID: ]

Obrezanova O, Martinsson A, Whitehead T, et al. Prediction of in vivo pharmacokinetic parameters and time-exposure curves in rats using machine learning from the chemical structure. Mol Pharm. 2022;19(5):1488–504. [DOI: 10.1021/acs.molpharmaceut.2c00027]
Kwapien K, Nittinger E, He J, et al. Implications of additivity and nonadditivity for machine learning and deep learning models in drug design. ACS Omega. 2022;7(30):26573–81. [>PMCID: ]

Destere A, Marquet P, Labriffe M, et al. A hybrid algorithm combining population pharmacokinetic and machine learning for isavuconazole exposure prediction. Pharm Res. 2023;40(4):951–9. [DOI: 10.1007/s11095-023-03507-y]
Kamiya Y, Handa K, Miura T, et al. Machine learning prediction of the three main input parameters of a simplified physiologically based pharmacokinetic model subsequently used to generate time-dependent plasma concentration data in humans after oral doses of 212 disparate chemicals. Biol Pharm Bull. 2022;45(1):124–8. [DOI: 10.1248/bpb.b21-00769]
Wang X, Liu M, Zhang L, et al. Optimizing pharmacokinetic property prediction based on integrated datasets and a deep learning approach. J Chem Inf Model. 2020;60(10):4603–13. [DOI: 10.1021/acs.jcim.0c00568]
Karalis VD. Machine learning in bioequivalence: towards identifying an appropriate measure of absorption rate. Appl Sci. 2022;13(1):418. [DOI: 10.3390/app13010418]
Hsiao Y-W, Fagerholm U, Norinder U. In silico categorization of in vivo intrinsic clearance using machine learning. Mol Pharm. 2013;10(4):1318–21. [DOI: 10.1021/mp300484r]
Li X, Tang L, Li Z, et al. Prediction of ADMET properties of anti-breast cancer compounds using three machine learning algorithms. Molecules. 2023;28(5):2326. [>PMCID: ]

Yang L, Jin C, Yang G, et al. Transformer-based deep learning method for optimizing ADMET properties of lead compounds. Phys Chem Chem Phys. 2023;25(3):2377–85. [DOI: 10.1039/D2CP05332B]
Destere A, Marquet P, Gandonnière CS, et al. A hybrid model associating population pharmacokinetics with machine learning: a case study with iohexol clearance estimation. Clin Pharmacokinet. 2022;61(8):1157–65. [DOI: 10.1007/s40262-022-01138-x]
Brereton AE, MacKinnon S, Safikhani Z, et al. Predicting drug properties with parameter-free machine learning: pareto-optimal embedded modeling (POEM). Mach Learn Sci Technol. 2020;1(2):025008. [DOI: 10.1088/2632-2153/ab891b]
Wang X, Sun Y, Ling L, et al. Gaultheria leucocarpa var. yunnanensis for treating rheumatoid arthritis—an assessment combining machine learning-guided ADME properties prediction, network pharmacology, and pharmacological assessment. Front Pharmacol. 2021;12:704040. [>PMCID: ]

An T, Chen Y, Chen Y, et al. A machine learning-based approach to ERα bioactivity and drug ADMET prediction. Front Genet. 2023;13:1087273. [>PMCID: ]

Keutzer L, You H, Farnoud A, et al. Machine learning and pharmacometrics for prediction of pharmacokinetic data: differences, similarities and challenges illustrated with rifampicin. Pharmaceutics. 2022;14(8):1530. [>PMCID: ]

Cobre A, Böger B, Fachi MM, et al. Machine learning-based virtual screening, molecular docking, drug-likeness, pharmacokinetics and toxicity analyses to identify new natural inhibitors of the glycoprotein spike (S1) of SARS-CoV-2. Quím Nova. 2023;46(5):450–59.

Hughes JH, Keizer RJ. A hybrid machine learning/pharmacokinetic approach outperforms maximum a posteriori Bayesian estimation by selectively flattening model priors. Cpt-Pharmacomet Syst Pharmacol. 2021;10(10):1150–60. [DOI: 10.1002/psp4.12684]
Iwata H, Matsuo T, Mamada H, et al. Prediction of total drug clearance in humans using animal data: proposal of a multimodal learning method based on deep learning. J Pharm Sci. 2021;110(4):1834–41. [DOI: 10.1016/j.xphs.2021.01.020]
Iwata H, Matsuo T, Mamada H, et al. Predicting total drug clearance and volumes of distribution using the machine learning-mediated multimodal method through the imputation of various nonclinical data. J Chem Inf Model. 2022;62(17):4057–65. [>PMCID: ]

Khusial R, Bies RR, Akil A. Deep learning methods applied to drug concentration prediction of olanzapine. Pharmaceutics. 2023;15(4):1139. [>PMCID: ]

Ponthier L, Marquet P, Moes DJA, et al. Application of machine learning to predict tacrolimus exposure in liver and kidney transplant patients given the MeltDose formulation. Eur J Clin Pharmacol. 2023;79(2):311–9. [DOI: 10.1007/s00228-022-03445-5]
Hirsh J, Warkentin TE, Dalen JE, et al. Heparin: mechanism of action, pharmacokinetics, dosing considerations, monitoring, efficacy, and safety. Chest. 1995;108(4):258S-275S. [DOI: 10.1378/chest.108.4_Supplement.258S]
Benedetti MS, Whomsley R, Poggesi I, et al. Drug metabolism and pharmacokinetics. Drug Metab Rev. 2009;41(3):344–90. [DOI: 10.1080/10837450902891295]
Rowland M, Benet LZ, Graham GG. Clearance concepts in pharmacokinetics. J Pharmacokinet Biopharm. 1973;1(2):123–36. [DOI: 10.1007/BF01059626]
Urso R, Blardi P, Giorgi G. A short introduction to pharmacokinetics. Eur Rev Med Pharmacol Sci. 2002;6:33–44.
Han YR, Lee PI, Pang KS. Finding Tmax and Cmax in multicompartmental models. Drug Metab Disposition. 2018;46(11):1796–804. [DOI: 10.1124/dmd.118.082636]
Smith DA, Beaumont K, Maurer TS, Di L. Volume of distribution in drug design. J Med Chem. 2015;58(15):5691–8. [DOI: 10.1021/acs.jmedchem.5b00201]
Krauss C, Do XA, Huck N. Deep neural networks, gradient-boosted trees, random forests: Statistical arbitrage on the S&P 500. Eur J Oper Res. 2017;259(2):689–702. [DOI: 10.1016/j.ejor.2016.10.031]
Hu J, Szymczak S. A review on longitudinal data analysis with random forest. Brief Bioinform. 2023;24(2):bbad002. [>PMCID: ]