Department of Pharmacy, Xinhua Hospital, Shanghai Jiaotong University School of Medicine, Shanghai, China.
Beijing Medicinovo Technology Co. Ltd., Beijing, China.
Expert Rev Clin Pharmacol. 2021 Jun;14(6):761-771. doi: 10.1080/17512433.2021.1911642. Epub 2021 Apr 9.
Despite therapeutic vancomycin is regularly monitored, its dose requirements vary considerably between individuals. Various innovative vancomycin dosing strategies have been developed for dose optimization; however, the utilization of individual factors and extensibility is insufficient. We aimed to develop an optimal dosing algorithm for vancomycin based on the high-dimensional data using the proposed variable engineering and machine-learning methods.
This study proposed a variable engineering process that automatically generates second-order variable interactions. We performed an initial examination of independent variables and interactive variables using eXtreme Gradient Boosting. The vancomycin dose prediction model was established based on the derived variables.
Based on the evaluation of the model performance in the validation cohort, our algorithm accounted for 67.5% of variations in the vancomycin doses. Subgroup analysis showed better performance in patients with medium and high body weight (with the ideal predictive percentage of 72.7% and 73.7%), and low and medium levels of serum creatinine (with the ideal predictive percentage of 77.8% and 73.1%) than in other groups.
The new vancomycin dose prediction model is potentially useful for patients whose population profiles are similar to those of our patients and yielded desired reference of clinical indicators with specific breakpoints.
尽管万古霉素的治疗剂量经常得到监测，但个体之间的剂量需求差异很大。为了优化剂量，已经开发出各种创新的万古霉素给药策略；然而，个体因素的利用和可扩展性仍然不足。我们旨在使用提出的变量工程和机器学习方法，基于高维数据为万古霉素开发最佳给药算法。
本研究提出了一种变量工程过程，该过程可以自动生成二阶变量交互作用。我们使用极端梯度提升对自变量和交互变量进行了初步检查。基于推导的变量建立了万古霉素剂量预测模型。
基于验证队列中模型性能的评估，我们的算法解释了万古霉素剂量变化的 67.5%。亚组分析显示，在体重中等和较高的患者（理想预测百分比为 72.7%和 73.7%）以及血清肌酐水平较低和中等的患者（理想预测百分比为 77.8%和 73.1%）中，该算法的性能更好，而在其他组中则表现不佳。
新的万古霉素剂量预测模型对于人群特征与我们的患者相似的患者可能是有用的，并且针对特定的临界点产生了所需的临床指标参考。
