相关实验视频

Updated: Jun 30, 2025

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

使用图形神经网络检测患有多抗药性肠道细菌感染风险的患者:一项回顾性研究

Racha Gouareb¹, Alban Bornet^1,2, Dimitrios Proios^1,2

¹Department of Radiology and Medical Informatics, University of Geneva, Geneva, Switzerland.

Health data science

|March 15, 2024

概括

一个图形神经网络模型有效地预测了多抗药性肠道细菌的住院殖民,优于传统方法. 这种方法通过识别高风险患者来加强感染控制.

科学领域:

计算生物学是一种计算生物学.
传染病流行病学传染病流行病学
机器学习在医疗保健中的应用

背景情况:

肠杆菌群是常见的肠道细菌,但它们在其他地方的殖民可能会导致严重的感染.
多药耐药 (MDR) 菌株在医院环境中构成重大威胁.
预测患者殖民是预防感染的关键.

研究的目的:

开发和评估基于图形的机器学习模型,用于预测MDR Enterobacteriaceae的住院殖民.
评估网络拓和患者互动对预测准确性的影响.
识别高风险患者进行针对性的感染控制干预.

主要方法:

使用图形神经网络 (GNN) 模型来分析患者交互网络.
用临床和时空数据丰富了患者节点.
模拟了网络拓,包括病房和护理人员的互动.
模型性能使用接收器操作特征曲线 (AUROC) 下的面积来评估.

主要成果:

该GNN模型实现了AUROC分数在0.91和0.96之间,显著超过了后勤回归基线 (0.88).
与病房相关的网络配置显示出优异的预测性能 (0.91感应,0.96传导).
对于特定的MDR Enterobacteriaceae,如Citrobacter freundii (0.94) 和Enterobacter cloacae (0.98) 观察到高的AUROC值.

结论:

基于图形的拓特征增强了机器学习模型的性能,用于预测Enterobacteriaceae殖民.
GNN为感染预防和控制计划提供了一个有前途的工具.
早期发现患有MDR Enterobacteriaceae殖民风险的患者可以改善患者的治疗结果.

更多相关视频

Author Spotlight: Advancing Rapid Detection of Respiratory Pathogens Using Microfluidic Chip

Author Spotlight: Advancing Rapid Detection of Respiratory Pathogens Using Microfluidic Chip

Published on: March 29, 2024

Rapid and Specific Detection of Acinetobacter baumannii Infections Using a Recombinase Polymerase Amplification/Cas12a-based System

Rapid and Specific Detection of Acinetobacter baumannii Infections Using a Recombinase Polymerase Amplification/Cas12a-based System

Published on: April 25, 2025

相关概念视频

Protein Networks

Protein Networks

An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...