基于群体药代动力学与机器学习模型的万古霉素精准给药
本研究分析1140份万古霉素治疗药物监测样本,开发并比较五种机器学习模型以预测24小时AUC。人工神经网络(ANN)模型表现最佳,R2达0.920±0.027,CCC为0.960±0.011,可作为即时床旁临床决策支持工具辅助个体化给药。
要点
- ANN模型预测万古霉素清除率的R2为0.920±0.027,CCC为0.960±0.011。
- SHAP分析显示实测浓度、胱抑素C和末次剂量为最具影响力的预测特征。
- 该模型可部署为即时床旁CDSS工具,辅助TDM指导的剂量调整。
核心结论
- ANN模型在预测万古霉素个体化清除率方面具有高准确性、稳健性和临床安全性,可作为即时床旁CDSS工具使用。
研究设计与样本
- 研究分析了1140份万古霉素TDM样本,开发并比较了五种机器学习模型,其中表现最佳的ANN模型在独立测试集上进行了验证。
主要发现
- ANN(MLP)模型综合性能最佳,R2为0.920±0.027,CCC为0.960±0.011,RMSE为0.498±0.076 L/h,MPE为1.290±1.774。
- SHAP分析识别出实测浓度(DV)、胱抑素C(Cys,mg/L)和末次剂量为三个最具影响力的预测特征。
关键数值与推荐
- 模型性能评估指标包括R2、RMSE、Lin一致性相关系数(CCC)、平均百分比误差(MPE)和平均绝对百分比误差(MAPE)。
- ANN模型R2为0.920±0.027,CCC为0.960±0.011,RMSE为0.498±0.076 L/h,MPE为1.290±1.774。
临床怎么用
- 该ANN模型可部署为即时床旁临床决策支持系统(CDSS)工具,辅助临床医生快速个体化万古霉素给药方案,提高目标AUC/MIC达成率。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
AIMS: Achieving the target AUC/MIC remains a critical challenge in vancomycin therapeutic drug monitoring, with traditional empirical dosing regimens often leading to suboptimal outcomes. This study aimed to develop and validate a novel population pharmacokinetic (PopPK)-informed machine learning model to optimize TDM-guided dose adjustments. By accurately predicting the 24-h area under the curve (AUC), the model assists clinicians in rapidly individualizing regimens, thereby improving target attainment, reducing subsequent modifications and minimizing toxicity. METHODS: A total of 1140 vancomycin TDM samples were analysed. Five machine learning models were developed and compared. Model performance assessed using R2, RMSE, Lin's concordance correlation coefficient (CCC), mean percentage error (MPE) and mean absolute percentage error (MAPE). The top-performing model (ANN) was subsequently validated on an independent test set. Its performance, interpretability and clinical safety were further examined using SHAP analysis, Bland-Altman plots, error grid analysis (EGA) and ROC curve evaluation. RESULTS: The ANN (MLP) model demonstrated the best comprehensive performance. It achieved the highest R2 (0.920 ± 0.027) and CCC (0.960 ± 0.011), coupled with the lowest RMSE (0.498 ± 0.076 L/h) and minimal systematic bias (MPE: 1.290 ± 1.774). SHAP analysis identified DV (measured concentration), Cys (mg/L) and Last dose as the three most influential predictive features. CONCLUSIONS: The ANN model achieved exceptional accuracy, robustness and clinical safety in predicting individualized vancomycin clearance. This model is deployable as an instantaneous, point-of-care CDSS tool, offering a powerful new pathway to solve the long-standing challenges of accessibility and accuracy in routine TDM practice.
引用
- Shi L, Hu N, Ling J, et al. Model-informed vancomycin precision dosing by population pharmacokinetics combined with machine learning algorithms. Br J Clin Pharmacol. 2026. PMID: 42159999. doi:10.1002/bcp.70621
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。