相关实验视频
Updated: May 16, 2025

07:42
A Data-Driven Approach to Quantifying Immune States in Sepsis
Published on: February 7, 2025
123
机器学习和人群药理动力学:一种混合方法,以优化败血症患者的万科米辛治疗
Keyu Chen1, Chuhui Wang1, Yu Wei1
1Department of Pharmacy, The First Affiliated Hospital of Xi'an Jiaotong University, Xi'an, China.
Microbiology spectrum
|March 31, 2025
概括
预测败血症患者的万科米辛暴露是至关重要的. 混合模型在没有度数据的情况下表现出色,而贝叶斯模型是最好的,指导精确的万科米辛剂量.
科学领域:
- 药理学和临床药学 药理学和临床药学
- 生物统计学和健康信息学
- 计算医学是一种计算医学.
背景情况:
- 准确的万科米辛暴露预测对于优化败血症患者治疗至关重要.
- 传统的人口药理动力学 (PPK) 模型在预测药物暴露方面存在局限性.
- 机器学习 (ML) 提供了潜在的优势,但在败血症中选择最佳范胺剂量的模型仍然不清楚.
研究的目的:
- 为了比较四种模型的预测性能:人口药理动力学 (PPK),贝叶斯学,机器学习 (ML) 和混合PPK-ML.
- 评估这些模型在预测万科米辛24小时度-时间曲线 (AUC24) 下的区域.
- 为准确剂量选择最佳模型提供指导,基于可用的万科米辛度数据.
主要方法:
- 利用来自MIMIC-IV数据库的4,059名接受静脉注射万科米辛治疗的败血症患者的数据.
- 开发并测试了四种不同的模型:PPK,贝叶斯式,ML (随机森林) 和混合PPK-ML方法.
- 通过使用包括平均绝对百分比误差 (MAPE) 和R2在持有测试集中的指标来评估模型性能.
主要成果:
- 没有万科米辛度数据,混合模型表现出优异的性能 (58%的MAPE比PPK更好,比贝叶斯的17%).
- 有了可用的度数据,贝叶斯模型表现最好 (MAPE:13.37%) 与PPK (68.17%),随机森林 (34.17%) 和混合 (28.52%) 相比.
结论:
- 在没有度数据的情况下,建议使用混合PPK-ML模型来预测万科米辛AUC24.
- 贝叶斯模型是最好的选择,当可获得康胺度数据时.
- 这些发现支持量身定制的万科米辛剂量策略,以改善败血症患者的治疗结果.
相关概念视频
Analysis of Population Pharmacokinetic Data
203
Analysis of population pharmacokinetic data involves studying the behavior of drugs within diverse populations to understand their pharmacokinetic parameters. Traditional pharmacokinetic methods typically involve collecting samples from a few individuals and estimating these parameters. While these methods are commonly used, they have limitations in capturing the variability in drug response among individuals or heterogeneous populations. Population pharmacokinetics is employed to address these...
203
Nonlinear Pharmacokinetics: Overview
214
Nonlinear or dose-dependent pharmacokinetics is a phenomenon that occurs when the pharmacokinetic parameters of certain drugs deviate from linear pharmacokinetics at higher doses. These drugs do not follow the expected first-order kinetics, where the rate of drug elimination is directly proportional to the drug concentration. Instead, they exhibit a nonlinear relationship, which can be attributed to several factors.
Nonlinearity can arise due to the saturation of plasma protein-binding or...
Nonlinearity can arise due to the saturation of plasma protein-binding or...
214
Model Approaches for Pharmacokinetic Data: Compartment Models
61
Compartmental analysis is a widely adopted approach to characterizing drug pharmacokinetics. It uses compartment models that conceptualize the body as a collection of reversibly communicating compartments, each representing a group of tissues exhibiting similar drug distribution characteristics. The movement rate of the drug between these compartments is typically described by first-order kinetics.
Two primary types of compartment models are recognized: mammillary and catenary. The more...
Two primary types of compartment models are recognized: mammillary and catenary. The more...
61
Analysis Methods of Pharmacokinetic Data: Model and Model-Independent Approaches
66
Drug disposition in the body is a complex process and can be studied using two major approaches: the model and the model-independent approaches.
The model approach uses mathematical models to describe changes in drug concentration over time. Pharmacokinetic models help characterize drug behavior in patients, predict drug concentration in the body fluids, calculate optimum dosage regimens, and evaluate the risk of toxicity. However, ensuring that the model fits the experimental data accurately...
The model approach uses mathematical models to describe changes in drug concentration over time. Pharmacokinetic models help characterize drug behavior in patients, predict drug concentration in the body fluids, calculate optimum dosage regimens, and evaluate the risk of toxicity. However, ensuring that the model fits the experimental data accurately...
66
Model Approaches for Pharmacokinetic Data: Distributed Parameter Models
48
Pharmacokinetic models are mathematical constructs that represent and predict the time course of drug concentrations in the body, providing meaningful pharmacokinetic parameters. These models are categorized into compartment, physiological, and distributed parameter models.
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
48
Two-Compartment Open Model: IV Infusion
178
A two-compartment model is a vital tool in pharmacokinetics, providing an essential understanding of drug behavior, especially for those administered via zero-order intravenous infusion. This model outlines two compartments: the central compartment, where elimination occurs, and the peripheral compartment.
The model illustrates the decrease in plasma drug concentration from the central compartment with a specific equation. It shows that under steady-state conditions, the drug's input rate...
The model illustrates the decrease in plasma drug concentration from the central compartment with a specific equation. It shows that under steady-state conditions, the drug's input rate...
178

