基于多算法挖掘与人口药理动力学相结合,预测老年患者的万科米辛度
Pan Ma1, Huan Ma1, Ruixiang Liu1
1Department of Pharmacy, Southwest Hospital, The First Affiliated Hospital of Army Medical University, Gaotanyan Street 30, Chongqing, 400038, China.
这项研究开发了一种机器学习模型,用于预测老年患者的万科米辛水平,从而改善个性化剂量. 该模型整合了人群药理动力学 (popPK),以提高药物管理的准确性.
科学领域:
- 药理动力学和药理动力学
- 机器学习在医学中的应用
- 老年人药理学 老年人药理学
背景情况:
- 范科米辛的药理动力学显示出高度的个体间变异性,特别是在老年患者中.
- 在这种人群中,个性化的万科米辛剂量对于优化治疗结果和最大限度地减少毒性至关重要.
研究的目的:
- 开发一个整合机器学习和人口药理动力学 (popPK) 的预测模型,用于在老年人中个性化管理万科米辛.
- 通过使用先进的特征选择技术,识别影响万科米辛血度的关键特征.
主要方法:
- 对33个特征的回顾性分析,包括popPK参数 (清除率,分布量).
- 使用集体机器学习算法 (SVR,LGBM,CatBoost) 结合Shapley附加解释来进行特征选择.
- 用popPK参数和没有popPK参数对模型性能进行比较,以评估其影响.
主要成果:
- 整体模型,使用16个优化的功能,显著优于具有所有功能的模型.
- 关键绩效指标包括R2为0.656,MAE为3.458和MSE为28.103.
- 获得的高精度:81.82%在±5 mg/L内,76.62%在±30%内.
结论:
- 成功开发了一种快速,具有成本效益的预测模型,用于估计老年患者的万科米血度.
- 该模型为临床医生提供了一种有价值的工具,以优化万科米辛的剂量方案,提高治疗疗效和患者安全.
更多相关视频
14:39Semi-Targeted Ultra-High-Performance Chromatography Coupled to Mass Spectrometry Analysis of Phenolic Metabolites in Plasma of Elderly Adults
Published on: April 22, 2022
12:18A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
相关概念视频
Analysis of Population Pharmacokinetic Data
Model Approaches for Pharmacokinetic Data: 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...
Model-Independent Approaches for Pharmacokinetic Data: Noncompartmental Analysis
One important characteristic of noncompartmental analyses is that drug exposure increases proportionally with increasing doses. This...
One-Compartment Open Model: Wagner-Nelson and Loo Riegelman Method for ka Estimation
On...
Analysis Methods of Pharmacokinetic Data: Model and 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...
One-Compartment Open Model for IV Bolus Administration: Estimation of Elimination Rate Constant, Half-Life and Volume of Distribution
