Gouareb Racha, Bornet Alban, Proios Dimitrios, Pereira Sónia Gonçalves, Teodoro Douglas
Department of Radiology and Medical Informatics, University of Geneva, Geneva, Switzerland.
HES-SO University of Applied Arts Sciences and Arts of Western Switzerland, Geneva, Switzerland.
Health Data Sci. 2023 Nov 20;3:0099. doi: 10.34133/hds.0099. eCollection 2023.
: While Enterobacteriaceae bacteria are commonly found in the healthy human gut, their colonization of other body parts can potentially evolve into serious infections and health threats. We investigate a graph-based machine learning model to predict risks of inpatient colonization by multidrug-resistant (MDR) Enterobacteriaceae. Colonization prediction was defined as a binary task, where the goal is to predict whether a patient is colonized by MDR Enterobacteriaceae in an undesirable body part during their hospital stay. To capture topological features, interactions among patients and healthcare workers were modeled using a graph structure, where patients are described by nodes and their interactions are described by edges. Then, a graph neural network (GNN) model was trained to learn colonization patterns from the patient network enriched with clinical and spatiotemporal features. The GNN model achieves performance between 0.91 and 0.96 area under the receiver operating characteristic curve (AUROC) when trained in inductive and transductive settings, respectively, up to 8% above a logistic regression baseline (0.88). Comparing network topologies, the configuration considering ward-related edges (0.91 inductive, 0.96 transductive) outperforms the configurations considering caregiver-related edges (0.88, 0.89) and both types of edges (0.90, 0.94). For the top 3 most prevalent MDR Enterobacteriaceae, the AUROC varies from 0.94 for up to 0.98 for using the best-performing GNN model. Topological features via graph modeling improve the performance of machine learning models for Enterobacteriaceae colonization prediction. GNNs could be used to support infection prevention and control programs to detect patients at risk of colonization by MDR Enterobacteriaceae and other bacteria families.
虽然肠杆菌科细菌在健康人体肠道中普遍存在，但它们在身体其他部位的定植可能会演变成严重感染并对健康构成威胁。我们研究了一种基于图的机器学习模型，以预测耐多药（MDR）肠杆菌科细菌导致的住院患者定植风险。定植预测被定义为一个二元任务，目标是预测患者在住院期间是否在不理想的身体部位被MDR肠杆菌科细菌定植。为了捕捉拓扑特征，使用图结构对患者与医护人员之间的相互作用进行建模，其中患者由节点描述，它们之间的相互作用由边描述。然后，训练一个图神经网络（GNN）模型，从富含临床和时空特征的患者网络中学习定植模式。当分别在归纳和转导设置下进行训练时，GNN模型在接收器操作特征曲线（AUROC）下的性能在0.91至0.96之间，比逻辑回归基线（0.88）高出8%。比较网络拓扑结构，考虑病房相关边的配置（归纳设置下为0.91，转导设置下为0.96）优于考虑护理人员相关边的配置（0.88，0.89）以及两种边都考虑的配置（0.90，0.94）。对于最常见的3种MDR肠杆菌科细菌，使用性能最佳的GNN模型时，AUROC从的0.94到的0.98不等。通过图建模的拓扑特征提高了机器学习模型对肠杆菌科细菌定植预测的性能。GNN可用于支持感染预防和控制计划，以检测有被MDR肠杆菌科细菌和其他细菌家族定植风险的患者。
