用药物数据和机器学习模型提高严重病情成人的死亡率预测
Brian Murray1, Tianyi Zhang2, Zhetao Chen3
1Department of Clinical Pharmacy, University of Colorado Skaggs School of Pharmacy, Aurora, CO.
Critical care explorations
|October 10, 2025
概括
机器学习 (ML) 和高级回归模型没有改善ICU成年人的医院死亡率预测,即使有药物治疗方案复杂性 (MRC) 数据. 在一些ML模型中,MRC数据显示中等重要性,但整体预测性能没有显著提升.
科学领域:
- 关键护理医学 关键护理医学
- 医疗信息学 医疗信息学
- 医疗保健中的机器学习
背景情况:
- 传统的回归模型在预测ICU成年人死亡率方面表现出有限的改善,而药物治疗方案复杂性 (MRC) 数据.
- 机器学习 (ML) 为提高死亡率预测准确度提供了一个潜在的途径.
研究的目的:
- 将ML方法与传统和先进的回归方法进行比较,以预测ICU成人的医院死亡率.
- 评估将MRC数据纳入各种预测模型的影响.
主要方法:
- 使用基线和24小时ICU变量 (包括MRC-ICU) 开发了监督分类ML模型 (随机森林,SVM,XGBoost).
- 传统和先进的回归模型使用逐步选择进行了优化.
- 模型性能是使用接收器操作特征 (AUROC) 曲线下的面积来评估的.
主要成果:
- ML模型实现了0.82-0.85之间的AUROC;高级回归模型产生了0.84-0.86.86的AUROC.
- 传统的回归模型显示AUROC在0.72-0.86.6之间.
- 在XGBoost和随机森林模型中,MRC-ICU数据具有中度的特征重要性.
- 在外部验证队列中,模型性能下降.
结论:
- 与传统方法相比,ML和高级回归方法并没有显著改善医院死亡率预测,尽管包括了MRC数据.
- 在特定的ML模型中,MRC数据对预测有适度的贡献.
- 可能需要进一步的研究来优化ML用于ICU死亡率预测.
相关概念视频
Pharmacokinetic Models: Comparison and Selection Criterion
334
Physiological and compartmental models are valuable tools used in studying biological systems. These models rely on differential equations to maintain mass balance within the system, ensuring an accurate representation of the dynamic processes at play.
Physiological models take a detailed approach by considering specific molecular processes. They can predict drug distribution, metabolism, and elimination changes, providing a comprehensive understanding of how drugs interact with the body.
Physiological models take a detailed approach by considering specific molecular processes. They can predict drug distribution, metabolism, and elimination changes, providing a comprehensive understanding of how drugs interact with the body.
334
Drug Dosing: Geriatric Patients
225
Elderly individuals encompass a diverse population with varying degrees of age-related physiological changes. Defining the elderly presents challenges, as the geriatric population is often arbitrarily categorized as individuals older than 65. However, many individuals in this group lead active and healthy lives, with an increasing number surpassing 85 years and falling into the older elderly category. Physiological changes associated with aging impact performance capacity and homeostatic...
225
Model Approaches for Pharmacokinetic Data: Distributed Parameter Models
242
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...
242
Mechanistic Models: Compartment Models in Individual and Population Analysis
245
Mechanistic models are utilized in individual analysis using single-source data, but imperfections arise due to data collection errors, preventing perfect prediction of observed data. The mathematical equation involves known values (Xi), observed concentrations (Ci), measurement errors (εi), model parameters (ϕj), and the related function (ƒi) for i number of values. Different least-squares metrics quantify differences between predicted and observed values. The ordinary least...
245
Pharmacokinetic Models: Overview
1.9K
Pharmacokinetic models utilize mathematical analysis to achieve a detailed quantitative understanding of a drug's life cycle within the body. They are instrumental in simulating a drug's pharmacokinetic parameters, predicting drug concentrations over time, optimizing dosage regimens, linking concentrations with pharmacologic activity, and estimating potential toxicity.
There are three primary types of models: empirical, compartment, and physiological. Empirical models, with minimal...
There are three primary types of models: empirical, compartment, and physiological. Empirical models, with minimal...
1.9K
Pharmacokinetics in Geriatric Patients: Effect of Age on Drug Excretion
234
In geriatric patients, renal physiology undergoes significant changes, including diminished renal blood flow and a lower glomerular filtration rate (GFR), leading to alterations in medication clearance. Drugs such as aminoglycoside antibiotics, lithium, and digoxin, which rely on glomerular filtration for removal from the body, particularly impact pharmacokinetics. These drugs tend to have slower clearance rates in older adults, necessitating careful dosage considerations.Evaluation of renal...
234

