多模式可解释的数据驱动模型用于早期预测多药物耐药性,使用多变量时间序列
Óscar Escudero-Arnanz1, Sergio Martínez-Agüero1, Paula Martín-Palomeque1
1Department of Signal Theory and Communications, Telematics and Computing Systems, Rey Juan Carlos University, 28942 Fuenlabrada, Spain.
这项研究引入了可解释的深度神经网络,以预测和理解重症监护室 (ICU) 中的多药性耐药性 (MDR),使用电子健康记录 (EHR). 这些模型提高了预测准确度,并确定了改善患者结果的关键风险因素.
科学领域:
- 医疗信息学 医疗信息学
- 医疗保健中的机器学习
- 临床数据分析 临床数据分析
背景情况:
- 电子健康记录 (EHR) 包含有价值的多模式患者数据,包括静态人口统计和动态多变量时间序列 (MTS).
- 整合静态和时间数据可以提高临床预测,但深度神经网络 (DNN) 缺乏可解释性,阻碍了临床采用.
- 在重症监护室 (ICU) 中,多药性耐药性 (MDR) 构成了重大挑战,需要准确的预测和理解.
研究的目的:
- 开发可解释的多式联网DNN架构,用于预测和理解ICU中MDR的出现.
- 整合静态人口统计数据与时间变量,以获得整体的患者健康视图.
- 为了提高临床决策支持的预测性能和模型解释性.
主要方法:
- 建议可解释的多式联网DNN架构集成静态和时间EHR数据.
- 结合特征选择与注意力机制和后期可解释性工具.
- 使用曲线下的接收器操作特征面积 (ROC AUC) 评估模型性能.
主要成果:
- 实现ROC AUC为76.90±3.10,显著超过基线模型的表现.
- 该方法有效地减少了特征冗余,并突出了MDR的关键风险因素.
- 通过集成的特征选择和注意力机制,证明了改进的模型准确性和稳定性.
结论:
- 拟议的框架提供了一个可扩展和可解释的解决方案,用于使用EHR数据在ICU中进行MDR预测.
- 该方法提高了预测准确度,同时提供了对风险因素的关键解释性见解.
- 支持及时,基于证据的干预措施,以改善重症监护机构患者的治疗结果.
更多相关视频
08:46Implementation of In Vitro Drug Resistance Assays: Maximizing the Potential for Uncovering Clinically Relevant Resistance Mechanisms
Published on: December 9, 2015
14:51Pooled shRNA Library Screening to Identify Factors that Modulate a Drug Resistance Phenotype
Published on: June 17, 2022
相关概念视频
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...
Multicompartment Models: Overview
These models offer a more comprehensive representation of drug behavior in the body than one-compartment models. They accommodate the complexity of drug distribution,...
Analysis of Population Pharmacokinetic Data
Pharmacokinetic Models: Overview
There are three primary types of models: empirical, compartment, and physiological. Empirical models, with minimal...
Model Approaches for Pharmacokinetic Data: Compartment Models
Two primary types of compartment models are recognized: mammillary and catenary. The more...
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...
