Translational Prediction of Hemodialysis Clearance Integrating Molecular Structure and Dialysis Conditions
Clinical and Translational Science · 2026
DOI: 10.1111/cts.70746 ↗Kurz gefasst
Fachartikel in der Zeitschrift Clinical and Translational Science, 2026. Verfasst von Takahiko Aoyama und 7 weiteren Autor:innen. Beteiligte Einrichtung: Laboratory of Clinical Pharmacometrics, School of Pharmacy, Nihon University, Chiba, Japan. Hauptthemen laut MEDLINE: Renal Dialysis. Die Arbeit nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Quantitative prediction of drug removal by hemodialysis is essential for rational dose design in patients with renal failure. We aimed to develop a machine learning‐based quantitative structure–pharmacokinetic relationship (QSPKR) model to predict hemodialysis clearance (CL HD ) using molecular descriptors and dialysis conditions. CL HD data were compiled from published clinical studies, yielding a dataset comprising 46 compounds; 457 measurements; 7 dialysis membrane types; and dialysis parameters, including blood flow rate ( Q B ) and dialysate flow rate ( Q D ). Recursive feature elimination revealed six key predictors, which were used to construct and compare five models: lasso regression, random forest, support vector machine, averaged neural network, and extreme gradient boosting (XGBoost) models. Feature contributions were interpreted using Shapley additive explanations (SHAP) analysis. Among the models, XGBoost demonstrated the highest predictive performance (root mean square error = 51.71 mL/min; R 2 = 0.614). The SHAP analysis revealed that lipophilicity was the most influential predictor. The effects of Q B and Q D on CL HD were nonlinear and saturable, consistent with the established dialysis clearance theory. CL HD can be predicted from molecular structure and dialysis parameters using a QSPKR‐based machine learning approach, providing a practical framework for estimating drug clearance and assisting in the preliminary evaluation of drug dialyzability when empirical data are limited.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Laboratory of Clinical Pharmacometrics, School of Pharmacy, Nihon University, Chiba, Japan.
- Division of Emergency and Critical Care Medicine, Department of Acute Medicine, Nihon University School of Medicine, Tokyo, Japan.
- Department of Pharmacy, Nihon University Itabashi Hospital, Tokyo, Japan.
ORCID-Profile: Takahiko Aoyama, Tsukasa Kuwana, Junko Yamaguchi, Kosaku Kinoshita, Yasuhiro Tsuji
Zitieren
APA
Aoyama, T., Kuwana, T., Sato, A., Ohashi, H., Yamaguchi, J., Imai, T., Kinoshita, K., & Tsuji, Y. (2026). Translational Prediction of Hemodialysis Clearance Integrating Molecular Structure and Dialysis Conditions. Clinical and Translational Science. https://doi.org/10.1111/cts.70746
Vancouver
Aoyama T, Kuwana T, Sato A, Ohashi H, Yamaguchi J, Imai T, et al. Translational Prediction of Hemodialysis Clearance Integrating Molecular Structure and Dialysis Conditions. Clinical and Translational Science. 2026. doi:10.1111/cts.70746
BibTeX
@article{Aoyama2026,
author = {Aoyama, Takahiko and Kuwana, Tsukasa and Sato, Atsushi and Ohashi, Haruka and Yamaguchi, Junko and Imai, Toru and Kinoshita, Kosaku and Tsuji, Yasuhiro},
title = {Translational Prediction of Hemodialysis Clearance Integrating Molecular Structure and Dialysis Conditions},
journal = {Clinical and Translational Science},
year = {2026},
doi = {10.1111/cts.70746}
}
EUVIMED