EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine Learning-Based Algorithm for Tacrolimus Dose Optimization in Hospitalized Kidney Transplant Patients

Dong Jin Park iD, Mihyeong Kim, Hyungjin Cho, Jung Soo Kim, Jeongkye Hwang, Jehoon Lee

Diagnostics · 21.11.2025 · 15 (23) · 2948

DOI: 10.3390/diagnostics15232948 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 21.11.2025. Verfasst von Dong Jin Park und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Laboratory Medicine, Eunpyeong St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul 03083, Republic of Kor…. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Tacrolimus is a cornerstone immunosuppressant in kidney transplantation, but its narrow therapeutic index and marked inter-patient variability complicate dose optimization. Conventional therapeutic drug monitoring (TDM) relies on empirical adjustments that often overlook individual pharmacokinetics. Machine learning (ML) offers a precision dosing alternative by integrating diverse clinical and biochemical variables into predictive models.

Methods

We retrospectively analyzed 1351 data points from 87 kidney transplant patients at Eunpyeong St. Mary’s Hospital (April 2019–November 2023). Clinical, demographic, and laboratory information, including tacrolimus trough levels and dosing history, were extracted from electronic medical records. Four predictive models—XGBoost, CatBoost, LightGBM, and a multilayer perceptron (MLP)—were trained to forecast next-day tacrolimus concentrations, and model serum creatinine level performance was evaluated using R-squared (R2), mean absolute error (MAE), and root-mean-squared error (RMSE). An ensemble model with weighted soft voting was applied to enhance predictive accuracy, and model interpretability was assessed using SHapley Additive exPlanations (SHAP).

Results

The ensemble model achieved the best overall performance (R2 = 0.6297, MAE = 1.0181, RMSE = 1.2999), outperforming all individual models, whereas the MLP model showed superior predictive power among single models, reflecting the significance of nonlinear interactions in tacrolimus pharmacokinetics. SHAP analysis highlighted prior tacrolimus levels, cumulative dose, renal function markers (eGFR level, serum creatinine level), and albumin concentration as the most influential predictors.

Conclusions

We present a robust ML-based algorithm for tacrolimus dose optimization in hospitalized kidney transplant recipients. By improving predictions of tacrolimus concentrations, the model may help reduce inter-patient dose variability and lower the risk of nephrotoxicity, supporting safer and more individualized immunosuppressive management. This approach advances AI-driven precision medicine in transplant care, offering a pathway to safer and more effective immunosuppression.

Schlagwörter

Stichwörter der Autor:innen

artificial intelligencekidney transplantationmachine learningtacrolimustherapeutic drug monitoring

Autor:innen und Institutionen

  • Department of Laboratory Medicine, Eunpyeong St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul 03083, Republic of Korea.
  • Division of Vascular and Transplant Surgery, Department of Surgery, Eunpyeong St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul 03083, Republic of Korea.
  • Industry-Academic Cooperation Foundation, The Catholic University of Korea, Seoul 03083, Republic of Korea.

ORCID-Profile: Dong Jin Park

Zitieren

APA

Park, D. J., Kim, M., Cho, H., Kim, J. S., Hwang, J., & Lee, J. (2025). Machine Learning-Based Algorithm for Tacrolimus Dose Optimization in Hospitalized Kidney Transplant Patients. Diagnostics, 15(23), 2948. https://doi.org/10.3390/diagnostics15232948

Vancouver

Park DJ, Kim M, Cho H, Kim JS, Hwang J, Lee J. Machine Learning-Based Algorithm for Tacrolimus Dose Optimization in Hospitalized Kidney Transplant Patients. Diagnostics. 2025;15(23):2948. doi:10.3390/diagnostics15232948

BibTeX
@article{Park2025,
  author = {Park, Dong Jin and Kim, Mihyeong and Cho, Hyungjin and Kim, Jung Soo and Hwang, Jeongkye and Lee, Jehoon},
  title = {Machine Learning-Based Algorithm for Tacrolimus Dose Optimization in Hospitalized Kidney Transplant Patients},
  journal = {Diagnostics},
  year = {2025},
  volume = {15},
  number = {23},
  pages = {2948},
  doi = {10.3390/diagnostics15232948}
}
Kostenlos starten →