Mechanism‐informed machine learning for individualized tacrolimus dose adjustment in the early post‐kidney transplant period
British Journal of Clinical Pharmacology · 2026
DOI: 10.1002/bcp.70448 ↗Kurz gefasst
Fachartikel in der Zeitschrift British Journal of Clinical Pharmacology, 2026. Verfasst von Hui Yu und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pharmaceutical Sciences, University of Michigan, Ann Arbor, MI, 48109, USA. Hauptthemen laut MEDLINE: Tacrolimus, Kidney Transplantation, Immunosuppressive Agents, Machine Learning. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Research Stimulus Award from the University of Michigan College of Pharmacy.
Abstract (Originalsprache)
Aim
Tacrolimus dosing in the early post‐kidney transplant period is challenging due to a narrow therapeutic index and substantial interindividual pharmacokinetic (PK) variability. This study aimed to develop and validate mechanism‐informed machine learning (ML) models to support individualized tacrolimus dosing during this critical period.
Methods
A total of 4311 tacrolimus trough concentrations (C trough ) within 7 days post‐transplant were obtained from 1624 kidney transplant recipients. Two ML models, Gated Recurrent Unit (GRU) and eXtreme Gradient Boosting (XGBoost), were developed to predict C trough and recommend doses to achieve target levels. Both models incorporated PK principles based on linear pharmacokinetics. Model performance was compared to a traditional Bayesian population PK (PopPK) model and purely data‐driven ML models via internal cross‐validation and external validation.
Results
The mechanism‐informed GRU model outperformed the Bayesian PopPK model in both internal validation (MSE = 7.81 vs . 9.27 ng 2 /mL 2 , R 2 = 0.537 vs . 0.450) and external validation (MSE = 6.09 vs . 8.96 ng 2 /mL 2 , R 2 = 0.397 vs . 0.211). The mechanism‐informed XGBoost model performed comparably to the GRU model. The incorporation of PK principles enhanced model interpretability and generalizability without reducing accuracy. When clinically administered doses, determined by conventional therapeutic drug monitoring, fell within the GRU model's recommended range, subsequent C trough reached the therapeutic target (8–12 ng/mL) in 51.3% of cases, compared to 37.0% overall (p < 0.01).
Conclusion
Mechanism‐informed ML models offer a robust and interpretable approach for individualized tacrolimus dosing, with the potential to improve therapeutic target attainment by enabling accurate dose adjustments in the early post‐transplant period.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Pharmaceutical Sciences, University of Michigan, Ann Arbor, MI, 48109, USA.
- Department of Clinical Pharmacy, University of Michigan, Ann Arbor, MI, 48109, USA.
ORCID-Profile: Hui Yu
Förderung
- Research Stimulus Award from the University of Michigan College of Pharmacy
Zitieren
APA
Yu, H., Qin, Z., Smith, L. S., Park, J. M., & Zhu, H. J. (2026). Mechanism‐informed machine learning for individualized tacrolimus dose adjustment in the early post‐kidney transplant period. British Journal of Clinical Pharmacology. https://doi.org/10.1002/bcp.70448
Vancouver
Yu H, Qin Z, Smith LS, Park JM, Zhu HJ. Mechanism‐informed machine learning for individualized tacrolimus dose adjustment in the early post‐kidney transplant period. British Journal of Clinical Pharmacology. 2026. doi:10.1002/bcp.70448
BibTeX
@article{Yu2026,
author = {Yu, Hui and Qin, Zihan and Smith, Logan S and Park, Jeong M and Zhu, Hao-Jie},
title = {Mechanism‐informed machine learning for individualized tacrolimus dose adjustment in the early post‐kidney transplant period},
journal = {British Journal of Clinical Pharmacology},
year = {2026},
doi = {10.1002/bcp.70448}
}
EUVIMED