Graph convolutional network-based fusion model to predict risk of hospital acquired infections.
Graph convolutional network-based fusion model to predict risk of hospital acquired infections.
复制标题
基于图卷积网络的融合模型来预测医院获得性感染的风险。
DOI：
10.1093/jamia/ocad045
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Patel,BhavikN
中科院分区：
文献类型：
--
作者：
Tariq,Amara;Lancaster,Lin;Elugunti,Praneetha;Siebeneck,Eric;Noe,Katherine;Borah,Bijan;Moriarty,James;Banerjee,Imon;Patel,BhavikN
摘要目的医院获得性感染（HAIs）是美国十大主要死亡原因之一。虽然目前的HAI风险预测标准仅利用了一组狭窄的预定义临床变量，但我们提出了一种基于图卷积神经网络（GNN）的模型，该模型包含了各种临床特征。我们基于gnn的模型基于全面的临床病史和人口统计学定义了患者的相似性，并预测了所有类型的HAI，而不是专注于单一亚型。在38 327例住院病例中训练了HAI模型，在18 609例住院病例中训练了手术部位感染（SSI）预测的独特模型。两种模型都在不同地理位置的不同感染率地点进行了内部和外部测试。结果该方法优于所有基线（单模态模型和停留时间LoS），在接受者工作特征下的内部和外部测试的实现面积为0.86 0.84-0.88和0.79 0.75-0.83 (HAI), 0.79 0.75-0.83和0.76 0.71-0.76 （SSI）。成本效益分析表明，基于较低的平均成本（1651vs 1915）， GNN建模优于标准LoS模型策略。本文提出的HAI风险预测模型不仅考虑了患者的临床特征，而且考虑了患者图边所示的相似患者的临床特征，可以估计患者的个体化感染风险。结论该模型可以预防或早期发现HAI，从而降低医院的LoS和相关死亡率，最终降低医疗成本。
Abstract Objective Hospital acquired infections (HAIs) are one of the top 10 leading causes of death within the United States. While current standard of HAI risk prediction utilizes only a narrow set of predefined clinical variables, we propose a graph convolutional neural network (GNN)-based model which incorporates a wide variety of clinical features. Materials and Methods Our GNN-based model defines patients’ similarity based on comprehensive clinical history and demographics and predicts all types of HAI rather than focusing on a single subtype. An HAI model was trained on 38 327 unique hospitalizations while a distinct model for surgical site infection (SSI) prediction was trained on 18 609 hospitalization. Both models were tested internally and externally on a geographically disparate site with varying infection rates. Results The proposed approach outperformed all baselines (single-modality models and length-of-stay LoS) with achieved area under the receiver operating characteristics of 0.86 0.84–0.88 and 0.79 0.75–0.83 (HAI), and 0.79 0.75–0.83 and 0.76 0.71–0.76 (SSI) for internal and external testing. Cost-effective analysis shows that the GNN modeling dominated the standard LoS model strategy on the basis of lower mean costs (1651vs 1915). Discussion The proposed HAI risk prediction model can estimate individualized risk of infection for patient by taking into account not only the patient’s clinical features, but also clinical features of similar patients as indicated by edges of the patients’ graph. Conclusions The proposed model could allow prevention or earlier detection of HAI, which in turn could decrease hospital LoS and associated mortality, and ultimately reduce the healthcare cost.