Woillard Jean-Baptiste, Labriffe Marc, Marquet Pierre
Univ. Limoges, P&T, Limoges, France.
INSERM, P&T, U1248, Limoges, France; and.
Ther Drug Monit. 2025 Jul 23. doi: 10.1097/FTD.0000000000001346.
Cyclosporine (CsA), an immunosuppressant widely used in solid-organ transplantation, requires precise therapeutic drug monitoring to balance its efficacy and toxicity. The interdose area under the concentration-time curve (AUC0-12 h) is considered to be a superior metric of drug exposure compared with single concentration measurements but is, nevertheless, resource-intensive. Machine learning (ML) offers a novel approach for AUC prediction by leveraging patient-specific data without relying on traditional pharmacokinetic assumptions. This study intended to develop and evaluate XGBoost ML models for predicting CsA AUC0-12 h using either two or three blood concentrations and to compare their performance against maximum a posteriori Bayesian estimation (MAP-BE) based on population pharmacokinetic models.
Using data from 2009 patients and 6360 dose-adjustment requests on the Immunosuppressant Bayesian Dose Adjustment website (https://abis.chu-limoges.fr/), supervised ML models were trained with predictors including CsA concentrations at predefined time points (C0, C1, and C3), dose, age, and sampling time deviations. External validation was performed using rich pharmacokinetic profiles of kidney, heart, lung, and bone marrow transplant recipients.
The three-sample XGBoost model achieved high accuracy in kidney transplant recipients (root mean square error [RMSE] <3%, RMSE<8.2%), closely matching the MAP-BE performance (rMPE <3%, RMSE <8.7%). The two-sample ML model demonstrated lower precision and higher variability but remained applicable in constrained sampling scenarios. The performance was reduced in heart and lung recipients for both ML and MAP-BE, reflecting the limited representation of these populations in the data set.
ML-based AUC prediction is a promising alternative to MAP-BE, particularly for kidney transplantation. Future studies should focus on expanding datasets, incorporating additional transplant types, and refining ML models for broader applicability.
环孢素（CsA）是一种广泛用于实体器官移植的免疫抑制剂，需要精确的治疗药物监测以平衡其疗效和毒性。与单次浓度测量相比，浓度-时间曲线下的给药间期面积（AUC0-12 h）被认为是药物暴露的更优指标，但仍然资源密集。机器学习（ML）通过利用患者特定数据提供了一种预测AUC的新方法，而无需依赖传统的药代动力学假设。本研究旨在开发和评估使用两个或三个血药浓度预测CsA AUC0-12 h的XGBoost ML模型，并将其性能与基于群体药代动力学模型的最大后验贝叶斯估计（MAP-BE）进行比较。
使用免疫抑制剂贝叶斯剂量调整网站（https://abis.chu-limoges.fr/）上2009例患者的6360次剂量调整请求数据，使用包括预定义时间点（C0、C1和C3）的CsA浓度、剂量、年龄和采样时间偏差等预测变量训练监督ML模型。使用肾、心、肺和骨髓移植受者的丰富药代动力学数据进行外部验证。
三样本XGBoost模型在肾移植受者中实现了高精度（均方根误差[RMSE]<3%，RMSE<8.2%），与MAP-BE性能密切匹配（相对平均预测误差[rMPE]<3%，RMSE<8.7%）。两样本ML模型显示出较低的精度和较高的变异性，但在受限采样情况下仍然适用。ML和MAP-BE在心脏和肺移植受者中的性能均有所下降，反映了这些人群在数据集中的代表性有限。
基于ML的AUC预测是MAP-BE的一种有前景的替代方法，特别是对于肾移植。未来的研究应集中于扩大数据集、纳入更多移植类型以及改进ML模型以实现更广泛的适用性。
