Skip to main content
SpringerLink
Log in

Optimization of Ganciclovir and Valganciclovir Starting Dose in Children by Machine Learning

  • Original Research Article
  • Published:
Clinical Pharmacokinetics Aims and scope Submit manuscript

Abstract

Background and Objectives

Ganciclovir (GCV) and valganciclovir (VGCV) show large interindividual pharmacokinetic variability, particularly in children. The objectives of this study were (1) to develop machine learning (ML) algorithms trained on simulated pharmacokinetics profiles obtained by Monte Carlo simulations to estimate the best ganciclovir or valganciclovir starting dose in children and (2) to compare its performances on real-world profiles to previously published equation derived from literature population pharmacokinetic (POPPK) models achieving about 20% of profiles within the target.

Materials and Methods

The pharmacokinetic parameters of four literature POPPK models in addition to the World Health Organization (WHO) growth curve for children were used in the mrgsolve R package to simulate 10,800 pharmacokinetic profiles. ML algorithms were developed and benchmarked to predict the probability to reach the steady-state, area-under-the-curve target (AUC0–24 within 40–60 mg × h/L) based on demographic characteristics only. The best ML algorithm was then used to calculate the starting dose maximizing the target attainment. Performances were evaluated for ML and literature formula in a test set and in an external set of 32 and 31 actual patients (GCV and VGCV, respectively).

Results

A combination of Xgboost, neural network, and random forest algorithms yielded the best performances and highest target attainment in the test set (36.8% for GCV and 35.3% for the VGCV). In actual patients, the best GCV ML starting dose yielded the highest target attainment rate (25.8%) and performed equally for VGCV with the Franck model formula (35.3% for both).

Conclusion

The ML algorithms exhibit good performances in comparison with previously validated models and should be evaluated prospectively.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Zuhair M, Smit GSA, Wallis G, Jabbar F, Smith C, Devleesschauwer B, et al. Estimation of the worldwide seroprevalence of cytomegalovirus: a systematic review and meta-analysis. Rev Med Virol. 2019;29: e2034.

    Article  PubMed  Google Scholar 

  2. Hayes M, Newman AM, Boge CLK, Galetaki DM, Elgarten CW, Freedman JL, et al. Incidence of CMV infection and disease and adverse events associated with antiviral therapy in a retrospective cohort of allogeneic hematopoietic cell transplant recipients at an academic children’s hospital. J Pediatr Infect Dis Soc. 2021;10:910–8.

    Article  CAS  Google Scholar 

  3. Downes KJ, Sharova A, Boge CLK, Vader D, Mitrou M, Hayes M, et al. CMV infection and management among pediatric solid organ transplant recipients. Pediatr Transpl. 2022;26: e14220.

    Article  Google Scholar 

  4. Manuel O, Kralidis G, Mueller NJ, Hirsch HH, Garzoni C, van Delden C, et al. Impact of antiviral preventive strategies on the incidence and outcomes of cytomegalovirus disease in solid organ transplant recipients. Am J Transpl. 2013;13:2402–10.

    Article  CAS  Google Scholar 

  5. Kotton CN, Kumar D, Caliendo AM, Huprikar S, Chou S, Danziger-Isakov L, et al. The third international consensus guidelines on the management of cytomegalovirus in solid-organ transplantation. Transplantation. 2018;102:900–31.

    Article  PubMed  Google Scholar 

  6. Rastogi S, Ricci A, Jin Z, Bhatia M, George D, Garvin JH, et al. Clinical and economic impact of cytomegalovirus infection among children undergoing allogeneic hematopoietic cell transplantation. Biol Blood Marrow Transpl. 2019;25:1253–9.

    Article  Google Scholar 

  7. Bateman CM, Kesson A, Powys M, Wong M, Blyth E. Cytomegalovirus infections in children with primary and secondary immune deficiencies. Viruses. 2021;13:2001.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  8. Franck B, Autmizguine J, Marquet P, Ovetchkine P, Woillard J-B. Pharmacokinetics, pharmacodynamics, and therapeutic drug monitoring of valganciclovir and ganciclovir in transplantation. Clin Pharmacol Ther. 2022;112:233–76.

    Article  CAS  PubMed  Google Scholar 

  9. Padullés A, Colom H, Bestard O, Melilli E, Sabé N, Rigo R, et al. Contribution of population pharmacokinetics to dose optimization of ganciclovir-valganciclovir in solid-organ transplant patients. Antimicrob Agents Chemother. 2016;60:1992–2002.

    Article  PubMed  PubMed Central  Google Scholar 

  10. Peled O, Berkovitch M, Rom E, Bilavsky E, Bernfeld Y, Dorfman L, et al. Valganciclovir dosing for cytomegalovirus prophylaxis in pediatric solid-organ transplant recipients: a prospective pharmacokinetic study. Pediatr Infect Dis J. 2017;36:745–50.

    Article  PubMed  Google Scholar 

  11. Jorga K, Reigner B, Chavanne C, Alvaro G, Frey N. Pediatric dosing of ganciclovir and valganciclovir: how model-based simulations can prevent underexposure and potential treatment failure. CPT Pharmacometr Syst Pharmacol. 2019;8:167–76.

    Article  CAS  Google Scholar 

  12. Ponthier L, Ensuque P, Destere A, Marquet P, Labriffe M, Jacqz-Aigrain E, et al. Optimization of vancomycin initial dose in term and preterm neonates by machine learning. Pharm Res. 2022;39:2497–506.

    Article  CAS  PubMed  Google Scholar 

  13. Yao B-F, Wu Y-E, Tang B-H, Hao G-X, Jacqz-Aigrain E, van den Anker J, et al. Predictive performance of pharmacokinetic model-based virtual trials of vancomycin in neonates: mathematics matches clinical observation. Clin Pharmacokinet. 2022;61:1027–38.

    Article  CAS  PubMed  Google Scholar 

  14. Woillard J-B, Labriffe M, Prémaud A, Marquet P. Estimation of drug exposure by machine learning based on simulations from published pharmacokinetic models: the example of tacrolimus. Pharmacol Res. 2021;167: 105578.

    Article  CAS  PubMed  Google Scholar 

  15. https://www.who.int/tools/child-growth-standards.

  16. Franck B, Woillard J-B, Théorêt Y, Bittencourt H, Demers E, Briand A, et al. Population pharmacokinetics of ganciclovir and valganciclovir in paediatric solid organ and stem cell transplant recipients. Br J Clin Pharmacol. 2021;87:3105–14.

    Article  CAS  PubMed  Google Scholar 

  17. Schwartz GJ, Brion LP, Spitzer A. The use of plasma creatinine concentration for estimating glomerular filtration rate in infants, children, and adolescents. Pediatr Clin North Am. 1987;34:571–90.

    Article  CAS  PubMed  Google Scholar 

  18. Elmokadem A, Riggs MM, Baron KT. Quantitative systems pharmacology and physiologically-based pharmacokinetic modeling with mrgsolve: a hands-on tutorial. CPT Pharmacometrics Syst Pharmacol. 2019;8:883–93.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  19. Nguyen T, Oualha M, Briand C, Bendavid M, Béranger A, Benaboud S, et al. Population pharmacokinetics of intravenous ganciclovir and oral valganciclovir in a pediatric population to optimize dosing regimens. Antimicrob Agents Chemother. 2021;65:e02254-e2320.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  20. Facchin A, Elie V, Benyoub N, Magreault S, Maisin A, Storme T, et al. Population pharmacokinetics of ganciclovir after valganciclovir in renal transplant children. Antimicrob Agents Chemother. 2019;63:e01192-19, AAC.01192-19.

  21. Razonable RR, Humar A. Cytomegalovirus in solid organ transplant recipients–guidelines of the American society of transplantation infectious diseases community of practice. Clin Transplant. 2019;33: e13512.

    Article  PubMed  Google Scholar 

  22. Labriffe M, Woillard J-B, Debord J, Marquet P. Machine learning algorithms to estimate everolimus exposure trained on simulated and patient pharmacokinetic profiles. CPT Pharmacometr Syst Pharmacol. 2022;11:1018.

    Article  CAS  Google Scholar 

  23. Kuhn M, Wickham H. tidymodels: Easily Install and Load the ‘Tidymodels’ Packages version 1.1.0 from CRAN. [Internet]. https://rdrr.io/cran/tidymodels/

  24. Chen T, Guestrin C. XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining [Internet]. San Francisco California USA: ACM; 2016 [cited 2021 Jun 30]. p. 785–94. https://doi.org/10.1145/2939672.2939785.

  25. Cheng B, Titterington DM. Neural networks: a review from a statistical perspective. Stat Sci [Internet]. 1994. https://doi.org/10.1214/ss/1177010638.full.

    Article  Google Scholar 

  26. Breiman L. No title found. Mach Learn [Internet]. 2001;45:5–32. https://doi.org/10.1023/A:1010933404324.

    Article  Google Scholar 

  27. Couch S, Kuhn M. Tidy Model Stacking Version 1.0.2. https://stacks.tidymodels.org/

  28. Pescovitz MD, Ettenger RB, Strife CF, Sherbotie JR, Thomas SE, McDiarmid S, et al. Pharmacokinetics of oral valganciclovir solution and intravenous ganciclovir in pediatric renal and liver transplant recipients. Transpl Infect Dis. 2010;12:195–203.

    Article  CAS  PubMed  Google Scholar 

  29. Åsberg A, Bjerre A, Neely M. New algorithm for valganciclovir dosing in pediatric solid organ transplant recipients. Pediatr Transplant. 2014;18:103–11.

  30. Bououda M, Uster DW, Sidorov E, Labriffe M, Marquet P, Wicha SG, et al. A machine learning approach to predict interdose vancomycin exposure. Pharm Res. 2022;39:721–31.

    Article  CAS  PubMed  Google Scholar 

  31. Uster DW, Stocker SL, Carland JE, Brett J, Marriott DJE, Day RO, et al. A model averaging/selection approach improves the predictive performance of model-informed precision dosing: vancomycin as a case study. Clin Pharmacol Ther. 2021;109:175–83.

    Article  CAS  PubMed  Google Scholar 

  32. Smits A, Kulo A, N de Hoon J, Allegaert K. Pharmacokinetics of drugs in neonates: pattern recognition beyond compound specific observations. CPD [Internet]. 2012 [cited 2022 Jan 4];18:3119–46. http://www.eurekaselect.com/openurl/content.php?genre=article&issn=1381-6128&volume=18&issue=21&spage=3119

  33. Biccler JL, Eloranta S, de Nully BP, Frederiksen H, Jerkeman M, Jørgensen J, et al. Optimizing outcome prediction in diffuse large b-cell lymphoma by use of machine learning and nationwide lymphoma registries: a Nordic lymphoma group study. JCO Clin Cancer Inform. 2018;2:1–13.

    Article  PubMed  Google Scholar 

  34. Shakhovska N, Yakovyna V, Chopyak V. A new hybrid ensemble machine-learning model for severity risk assessment and post-COVID prediction system. Math Biosci Eng. 2022;19:6102–23.

    Article  PubMed  Google Scholar 

Download references

Acknowledgements

The authors thanks Karen Poole for manuscript editing.

Author information

Authors and Affiliations

  1. Pharmacology and Transplantation, INSERM U1248, Université de Limoges, 2 Rue du Pr Descottes, 87000, Limoges, France

    Laure Ponthier, Pierre Marquet, Marc Labriffe & Jean-Baptiste Woillard

  2. Department of Pediatrics, University Hospital of Limoges, Limoges, France

    Laure Ponthier

  3. Research Center, Centre Hospitalier Universitaire Sainte-Justine, Montreal, QC, Canada

    Julie Autmizguine

  4. Department of Pediatrics, Centre Hospitalier Universitaire Sainte-Justine, Montreal, QC, Canada

    Julie Autmizguine & Philippe Ovetchkine

  5. Department of Pharmacology and Physiology, Université de Montréal, Montreal, QC, Canada

    Julie Autmizguine

  6. Department of Clinical and Biological Pharmacology and Pharmacovigilance, Clinical Investigation Center, CIC-P 1414, Rennes, France

    Benedicte Franck

  7. University of Rennes, Centre Hospitalier Universitaire Rennes, École des Hautes Études en Santé Publique, IRSET (Institut de Recherche en Santé, Environnement et Travail), UMR S 1085, Rennes, France

    Benedicte Franck

  8. Department of Transplantation Medicine, Oslo University Hospital-Rikshospitalet, Oslo, Norway

    Anders Åsberg

  9. Section of Pharmacology and Pharmaceutical Biosciences, Department of Pharmacy, University of Oslo, Oslo, Norway

    Anders Åsberg

  10. Department of Pharmacology, Toxicology and Pharmacovigilance, University Hospital of Nice, Nice, France

    Alexandre Destere

  11. Department of Pharmacology, Toxicology and Pharmacovigilance, University Hospital of Limoges, Limoges, France

    Pierre Marquet, Marc Labriffe & Jean-Baptiste Woillard

Authors
  1. Laure Ponthier
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Julie Autmizguine
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Benedicte Franck
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Anders Åsberg
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Philippe Ovetchkine
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Alexandre Destere
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Pierre Marquet
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Marc Labriffe
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Jean-Baptiste Woillard
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jean-Baptiste Woillard.

Ethics declarations

Competing Interests

The authors have no competing interests to declare in relation to this work.

Funding information

No funding was received for this study.

Ethics approval

Not applicable.

Consent to participate

Not applicable.

Consent for publication

Not applicable.

Data availability

The datasets generated during and/or analyzed during the current study are not publicly available due to privacy and ethical restrictions but are available from the corresponding author on reasonable request.

Data transparency

All the values of covariates and the code used to simulate them are available at https://github.com/ponthL/ganciclovir_first_dose.git.

Author contributions

LP, JBW, PM, ML contributed to the study conception and design. Material preparation, data collection and analysis were performed by BF, AA, JA, PO. AD developed the shiny app. The first draft of the manuscript was written by LP and JBW and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.

Supplementary Information

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

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ponthier, L., Autmizguine, J., Franck, B. et al. Optimization of Ganciclovir and Valganciclovir Starting Dose in Children by Machine Learning. Clin Pharmacokinet 63, 539–550 (2024). https://doi.org/10.1007/s40262-024-01362-7

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s40262-024-01362-7

Search

Navigation