Sign Up Submit Enquiry

Dosing prediction of valproic acid in pediatric patients with epilepsy: population pharmacokinetic model or machine learning model?

Home Dosing prediction of valproic acid in pediatric patients with epilepsy: population pharmacokinetic model or machine learning model?

Related Articles

Contact us

Article Content

Abstract

Purpose

This study develops and compares population pharmacokinetics (PopPK) models and machine learning methods, including neural networks, to predict steady-state trough concentrations in pediatric patients and provide improved dosing recommendations.

Methods

Valproic acid concentration data were collected from 490 pediatric epilepsy patients treated at Beijing Tiantan Hospital and Beijing Children’s Hospital. We developed predictive models employing PopPK, maximum a posteriori Bayesian (MAPB), multiple linear regression (MLR), machine learning (including Random Forest, XGBoost, and LightGBM for feature selection), and neural network techniques. The predictive accuracy of these models was then rigorously tested through external validation using the independent dataset from Beijing Children’s Hospital. Upon identifying the optimal model, dosing regimens for various clinical scenarios were derived and presented.

Results

Under the same dataset modeling conditions, the original PopPK models showed limited predictive performance. Transforming these models into multiple linear regression enhanced prediction accuracy. Moreover, when prior data was available, the MAPB method significantly boosted prediction performance. Machine learning and neural networks showed higher accuracy, with neural networks achieving an F30 value above 80%.

Conclusion

This study explored model optimization strategies and compared machine learning and neural network models alongside traditional PopPK. It introduced an advanced method to predict drug concentrations and stable trough dosing regimens in pediatric epilepsy treatment, reducing the need for frequent, invasive blood tests in TDM. These improvements enhanced the efficacy and safety of valproic acid therapy for children, supporting the development of personalized treatment plans.

Explore related subjects

Discover the latest articles and news from researchers in related subjects, suggested using machine learning.

  • Drugs
  • Machine Learning
  • Pharmacokinetics
  • Predictive medicine
  • Predictive markers
  • Statistical Learning

Data availability

No datasets were generated or analysed during the current study.

References

  1. Landmark CJ, Johannessen SI, Tomson T (2016) Dosing strategies for antiepileptic drugs: from a standard dose for all to individualised treatment by implementation of therapeutic drug monitoring. Epileptic Disord 18(4):367–383

    Article PubMed Google Scholar

  2. Haddad PM, Das A, Ashfaq M, Wieck A (2009) A review of valproate in psychiatric practice. Expert Opin Drug Metab Toxicol 5(5):539–551

    Article CAS PubMed Google Scholar

  3. Li Y, Dong N, Qin YX, Dai HR, Hu YH, Zhao YT et al (2022) Therapeutic drug monitoring of perampanel in children diagnosed with epilepsy: focus on influencing factors on the plasma concentration-to-dose ratio. Epilepsia Open 7(4):737–746

    Article PubMed PubMed Central Google Scholar

  4. Yatham LN, Kennedy SH, Parikh SV, Schaffer A, Bond DJ, Frey BN et al (2018) Canadian Network for Mood and Anxiety Treatments (CANMAT) and International Society for Bipolar Disorders (ISBD) 2018 guidelines for the management of patients with bipolar disorder. Bipolar Disord 20(2):97–170

    Article PubMed PubMed Central Google Scholar

  5. Damnjanović I, Tsyplakova N, Stefanović N, Tošić T, Catić-Đorđević A, Karalis V (2023) Joint use of population pharmacokinetics and machine learning for optimizing antiepileptic treatment in pediatric population. Ther Adv Drug Saf 14:1581633561

    Article Google Scholar

  6. Hsu CW, Lai EC, Chen YB, Kao HY (2024) Valproic acid monitoring: serum prediction using a machine learning framework from multicenter real-world data. J Affect Disord 347:85–91

    Article CAS PubMed Google Scholar

  7. Mei S, Feng W, Zhu L, Yu Y, Yang W, Gao B et al (2017) Genetic polymorphisms and valproic acid plasma concentration in children with epilepsy on valproic acid monotherapy. Seizure 51:22–26

    Article PubMed Google Scholar

  8. Mei S, Feng W, Zhu L, Li X, Yu Y, Yang W et al (2018) Effect of CYP2C19, UGT1A8, and UGT2B7 on valproic acid clearance in children with epilepsy: a population pharmacokinetic model. Eur J Clin Pharmacol 74(8):1029–1036

    Article CAS PubMed Google Scholar

  9. Hara M, Masui K, Eleveld DJ, Struys M, Uchida O (2017) Predictive performance of eleven pharmacokinetic models for propofol infusion in children for long-duration anaesthesia. Br J Anaesth 118(3):415–423

    Article CAS PubMed Google Scholar

  10. Zhang HX, Sheng CC, Liu LS, Luo B, Fu Q, Zhao Q et al (2019) Systematic external evaluation of published population pharmacokinetic models of mycophenolate mofetil in adult kidney transplant recipients co-administered with tacrolimus. Br J Clin Pharmacol 85(4):746–761

    Article CAS PubMed PubMed Central Google Scholar

  11. Wang YL, Guilhaumou R, Blin O, Velly L, Marsot A (2020) External evaluation of population pharmacokinetic models for continuous administration of meropenem in critically ill adult patients. Eur J Clin Pharmacol 76(9):1281–1289

    Article CAS PubMed Google Scholar

  12. Wei S, Chen J, Zhao Z, Mei S (2023) External validation of population pharmacokinetic models of vancomycin in postoperative neurosurgical patients. Eur J Clin Pharmacol 79(8):1031–1042

    Article CAS PubMed Google Scholar

  13. Methaneethorn J (2018) A systematic review of population pharmacokinetics of valproic acid. Br J Clin Pharmacol 84(5):816–834

    Article PubMed PubMed Central Google Scholar

  14. Sharma A, Singh B (2020) AE-LGBM: Sequence-based novel approach to detect interacting protein pairs via ensemble of autoencoder and LightGBM. Comput Biol Med 125:103964

    Article CAS PubMed Google Scholar

  15. Gumaei A, Al-Rakhami M, Mahmoud Al Rahhal M, Raddah H Albogamy F, Al Maghayreh E, AlSalman H (2020) Prediction of COVID-19 confirmed cases using gradient boosting regression method. Comput Mater Continua 66 (1):315–329.

  16. Yang F, Wang HZ, Mi H, Lin CD, Cai WW (2009) Using random forest for reliable classification and cost-sensitive learning for medical diagnosis. BMC Bioinformatics, 10 Suppl 1 (Suppl 1):S22.

  17. Tike A, Tavarageri S (2017) A medical price prediction system using hierarchical decision trees.2017 IEEE International Conference on Big Data (Big Data), 3904–3913.

  18. Takemura A, Shimizu A, Hamamoto K (2010) Discrimination of breast tumors in ultrasonic images using an ensemble classifier based on the AdaBoost algorithm with feature selection. IEEE Trans Med Imaging 29(3):598–609

    Article PubMed Google Scholar

  19. Khan PW, Park S, Lee S, Byun Y, Mohammad M, Miralinaghi M (2022) Electric kickboard demand prediction in spatiotemporal dimension using clustering-aided bagging regressor. J Adv Transp 2022:1–15

    Article Google Scholar

  20. Sidey-Gibbons JAM,Sidey-Gibbons CJ (2019) Machine learning in medicine: a practical introduction. BMC Med Res Methodol 19(1).

  21. Albawi S, Mohammed TA, Al-Zawi S (2017) Understanding of a convolutional neural network. International Conference on Engineering and Technology (ICET) 2017:1–6

    Google Scholar

  22. Zhang J, Zheng Y, Qi D, Li R, Yi X (2016) DNN-based prediction model for spatio-temporal data. In Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (SIGSPACIAL ’16). Association for Computing Machinery, NY, USA, Article 92, 1–4.

  23. Hinton GE, Srivastava N, Krizhevsky A, Sutskever I, Salakhutdinov RR (2012) Improving neural networks by preventing co-adaptation of feature detectors. Cornell University Library arXiv.org, Ithaca

    Google Scholar

  24. Keskar NS, Socher R (2017) Improving generalization performance by switching from Adam to SGD. Cornell University Library arXiv.org, Ithaca

    Google Scholar

  25. Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. Cornell University Library arXiv.org, Ithaca

    Google Scholar

  26. Smith LN (2017) Cyclical learning rates for training neural networks. 2017 IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE 464–472

  27. Zaccara G, Messori A, Moroni F (1988) Clinical pharmacokinetics of valproic acid–1988. Clin Pharmacokinet 15(6):367–389

    Article CAS PubMed Google Scholar

  28. Klopfenstein Q, Vaiter S (2021) Linear support vector regression with linear constraints. Mach Learn 110(7):1939–1974

    Article Google Scholar

  29. Qamar A, Asim M, Maamar Z, Saeed S, Baker T (2022) A Quality – of – Things model for assessing the Internet – of – Things’ nonfunctional properties. Trans Emerg Telecommun Technol 33(8).

  30. Misra S, Li H (2020) Noninvasive fracture characterization based on the classification of sonic wave travel times. Machine Learning for Subsurface Characterization 2020:243–287

    Article Google Scholar

  31. Buja A, Mease D, Wyner AJ (2007) Comment: Boosting algorithms: regularization, prediction and model fitting. Stat Sci 22(4).

  32. Breiman L (1996) Bagging predictors. Mach Learn 2(24):123–140

    Article Google Scholar

  33. Kamiński B, Jakubczyk M, Szufel P (2018) A framework for sensitivity analysis of decision trees. Cent Eur J Oper Res 26(1):135–159

    Article PubMed Google Scholar

  34. Thian YL, Ng DW, Hallinan JTPD, Jagmohan P, Sia SY, Mohamed JSA, Quek ST, Feng M (2022) Effect of training data volume on performance of convolutional neural network pneumothorax classifiers. J Digit Imaging 35(4):881–892

    Article PubMed PubMed Central Google Scholar

  35. Lustgarten JL, Gopalakrishnan V, Grover H, Visweswaran S (2008) Improving classification performance with discretization on biomedical datasets. AMIA Annu Symp Proc 2008:445–449

    PubMed PubMed Central Google Scholar

  36. Schmidhuber J (2015) Deep learning in neural networks: an overview. Neural Netw 61:85–117

    Article PubMed Google Scholar

  37. Huang S, Xu Q, Yang G, Ding J, Pei Q (2025) Machine learning for prediction of drug concentrations: application and challenges. Clin Pharmacol Ther 117(5):1236–1247

    Article CAS PubMed Google Scholar

Download references

Acknowledgements

We thank all authors of the included studies for their hard work.

Funding

Shenghui Mei was supported by the National Key R&D Program of China (2020YFC2008306) and Beijing Municipal Administration of Hospitals Incubating Program (PX2024020).

Author information

Author notes

  1. Jingcheng Chen, Jiacheng Wang, and Kai Li contributed equally to this work and should be considered co-first authors.

Authors and Affiliations

  1. Department of Pharmacy, Fengtai District, Beijing Tiantan Hospital, Capital Medical University, 119 Nansihuan West Road, Beijing, 100070, People’s Republic of China

    Jingcheng Chen, Kai Li, Yujie Wu, Ziqian Wang, Jin Guo, Zhigang Zhao & Shenghui Mei

  2. Department of Clinical Pharmacology, College of Pharmaceutical Sciences, Capital Medical University, Beijing, 100069, People’s Republic of China

    Jingcheng Chen, Kai Li, Yujie Wu, Ziqian Wang, Jin Guo, Zhigang Zhao & Shenghui Mei

  3. Department of Neurology, Beijing Children’s Hospital, Capital Medical University, 56 Nanlishi Road Xicheng District, Beijing, 100045, People’s Republic of China

    Weixing Feng

  4. Shenzhen International Graduate School, Tsinghua University, Shenzhen, 518055, People’s Republic of China

    Jiacheng Wang

  5. National Graduate College for Engineers, Tsinghua University, Beijing, 100084, People’s Republic of China

    Jiacheng Wang

Contributions

J.C. contributed to conceptualization (equal), formal analysis (equal), methodology (equal), software (equal), original draft preparation (equal), and review and editing (equal). J.W. was responsible for formal analysis (equal), software (equal), original draft preparation (equal), and review and editing (equal). K.L. led the validation, contributed to formal analysis (equal), original draft preparation (equal), and review and editing (equal). Y.W. supported the investigation. Z.W. also supported the investigation. J.G. led the data curation. Z.Z. and W.F. equally provided resources. S.M. led project administration, contributed to conceptualization (equal), investigation (equal), and provided resources (equal).

Corresponding authors

Correspondence to Weixing Feng or Shenghui Mei.

Ethics declarations

Ethics approval

This study was approved by the Ethics Committee of Beijing Tiantan Hospital and Beijing Children’s Hospital, Capital Medical University, Beijing, China (KY2022-018–02). Informed consent was obtained from the patients or legal guardians in accordance with the guidelines of the Declaration of Helsinki.

Consent to participate

Not applicable.

Consent for publication

Not applicable.

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

ESM1

(DOCX 1.78 MB)

ESM2

(DOCX 196 KB)

(MP4 12.9 MB)

ESM4

(DOCX 28.0 KB)

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Cite this article

Chen, J., Wang, J., Li, K. et al. Dosing prediction of valproic acid in pediatric patients with epilepsy: population pharmacokinetic model or machine learning model?. Eur J Clin Pharmacol (2025). https://doi.org/10.1007/s00228-025-03874-y

Download citation

  • Received 
  • Accepted 
  • Published 
  • DOI  https://doi.org/10.1007/s00228-025-03874-y

Keywords

  • Pediatrics
  • Epilepsy
  • Valproic acid
  • Pharmacokinetics
  • Machine learning
  • Neural networks, Computer

 

Copyright © All rights reserved Designed and Developed by Digital Flavers

WhatsApp