Prediction of teicoplanin plasma concentration in critically ill patients: a combination of machine learning and population pharmacokinetics
作者全名:"Ma, Pan; Shang, Shenglan; Liu, Ruixiang; Dong, Yuzhu; Wu, Jiangfan; Gu, Wenrui; Yu, Mengchen; Liu, Jing; Li, Ying; Chen, Yongchuan"
作者地址:"[Ma, Pan; Liu, Ruixiang; Gu, Wenrui; Chen, Yongchuan] Army Med Univ, Affiliated Hosp 1, Dept Pharm, Chongqing 400038, Peoples R China; [Shang, Shenglan; Yu, Mengchen; Liu, Jing] Gen Hosp Cent Theater Command, Dept Clin Pharm, Wuhan 430070, Hubei, Peoples R China; [Dong, Yuzhu] Chongqing Med Univ, Affiliated Hosp 3, Dept Pharm, Chongqing 401120, Peoples R China; [Wu, Jiangfan] Chongqing Med Univ, Affiliated Hosp 1, Dept Pharm, Chongqing 400016, Peoples R China; [Li, Ying] Army Med Univ, Affiliated Hosp 1, Med Big Data & Artificial Intelligence Ctr, Chongqing 400038, Peoples R China"
通信作者:"Chen, YC (通讯作者),Army Med Univ, Affiliated Hosp 1, Dept Pharm, Chongqing 400038, Peoples R China."
来源:JOURNAL OF ANTIMICROBIAL CHEMOTHERAPY
ESI学科分类:PHARMACOLOGY & TOXICOLOGY
WOS号:WOS:001300146700001
JCR分区:Q1
影响因子:5.2
年份:2024
卷号:79
期号:11
开始页:2815
结束页:2827
文献类型:Article
关键词:
摘要:"Background Teicoplanin has been widely used in patients with infections caused by Staphylococcus aureus, especially for critically ill patients. The pharmacokinetics (PK) of teicoplanin vary between individuals and within the same individual. We aim to establish a prediction model via a combination of machine learning and population PK (PPK) to support personalized medication decisions for critically ill patients.Methods A retrospective study was performed incorporating 33 variables, including PPK parameters (clearance and volume of distribution). Multiple algorithms and Shapley additive explanations were employed for feature selection of variables to determine the strongest driving factors.Results The performance of each algorithm with PPK parameters was superior to that without PPK parameters. The composition of support vector regression, categorical boosting and a backpropagation neural network (7:2:1) with the highest R2 (0.809) was determined as the final ensemble model. The model included 15 variables after feature selection, of which the predictive performance was superior to that of models considering all variables or using only PPK. The R2, mean absolute error, mean squared error, absolute accuracy (+/- 5 mg/L) and relative accuracy (+/- 30%) of external validation were 0.649, 3.913, 28.347, 76.12% and 76.12%, respectively.Conclusions Our study offers a non-invasive, fast and cost-effective prediction model of teicoplanin plasma concentration in critically ill patients. The model serves as a fundamental tool for clinicians to determine the effective plasma concentration range of teicoplanin and formulate individualized dosing regimens accordingly."
基金机构:Science and Health Joint Medical Research Project of Chongqing [2023QNXM031]; China Postdoctoral Science Foundation [2022M713859]; Postdoctoral Scientific Research Foundation of General Hospital of Central Theater Command [20211227KY22]
基金资助正文:"This research was supported by the Science and Health Joint Medical Research Project of Chongqing (2023QNXM031), China Postdoctoral Science Foundation (2022M713859) and Postdoctoral Scientific Research Foundation of General Hospital of Central Theater Command (20211227KY22)."