背景:预测个人因COVID-19死亡的风险对于计划和优化资源至关重要。然而,由于现实世界的死亡率相对较低,特别是在香港这样的地方,由于数据集的不平衡特性,这使得建立准确的预测模型变得困难。这项研究介绍了图形卷积网络(GCN)的创新应用,以使用高度不平衡的数据集预测COVID-19患者的生存。与传统模式不同,GCN利用数据内的结构关系,增强预测准确性和鲁棒性。通过将人口统计和实验室数据集成到GCN框架中,我们的方法解决了类不平衡,并证明了预测准确性的显著提高。
方法:该队列包括2020年1月23日至12月31日在香港42家公立医院收治的符合研究标准的所有连续阳性COVID-19患者(n=7,606)。我们提出了基于人群的图卷积神经网络(GCN)模型,年龄和性别作为预测生存结果的输入。此外,我们将我们提出的模型与Cox比例风险(CPH)模型进行了比较,传统的机器学习模型,和过采样机器学习模型。此外,对测试集进行了子组分析,以便更深入地了解每个患者节点与其邻居之间的关系,揭示不准确预测的可能根本原因。
结果:GCN模型是表现最好的模型,AUC为0.944,显著优于所有其他模型(p<0.05),包括过采样CPH模型(0.708),线性回归(0.877),线性判别分析(0.860),K-最近邻(0.834),高斯预测因子(0.745)和支持向量机(0.847)。根据Kaplan-Meier的估计,GCN模型在低风险和高风险个体之间表现出良好的可判性(p<0.0001)。基于使用加权得分的子分析,尽管GCN模型能够很好地区分不同的预测组,假阴性(FN)和真阴性(TN)组之间的分离不充分。
结论:GCN模型大大优于所有其他机器学习方法和基准CPH模型。因此,当应用于这个不平衡的COVID生存数据集时,采用人口图表示可能是实现良好预测的一种方法。
BACKGROUND: Predicting an individual\'s risk of death from COVID-19 is essential for planning and optimising resources. However, since the real-world mortality rate is relatively low, particularly in places like Hong Kong, this makes building an accurate prediction model difficult due to the imbalanced nature of the dataset. This study introduces an innovative application of graph convolutional networks (GCNs) to predict COVID-19 patient survival using a highly imbalanced dataset. Unlike traditional models, GCNs leverage structural relationships within the data, enhancing predictive accuracy and robustness. By integrating demographic and laboratory data into a GCN framework, our approach addresses class imbalance and demonstrates significant improvements in prediction accuracy.
METHODS: The cohort included all consecutive positive COVID-19 patients fulfilling study criteria admitted to 42 public hospitals in Hong Kong between January 23 and December 31, 2020 (n = 7,606). We proposed the population-based graph convolutional neural network (GCN) model which took blood test results, age and sex as inputs to predict the survival outcomes. Furthermore, we compared our proposed model to the Cox Proportional Hazard (CPH) model, conventional machine learning models, and oversampling machine learning models. Additionally, a subgroup analysis was performed on the test set in order to acquire a deeper understanding of the relationship between each patient node and its neighbours, revealing possible underlying causes of the inaccurate predictions.
RESULTS: The GCN model was the top-performing model, with an AUC of 0.944, considerably outperforming all other models (p < 0.05), including the oversampled CPH model (0.708), linear regression (0.877), Linear Discriminant Analysis (0.860), K-nearest neighbours (0.834), Gaussian predictor (0.745) and support vector machine (0.847). With Kaplan-Meier estimates, the GCN model demonstrated good discriminability between low- and high-risk individuals (p < 0.0001). Based on subanalysis using the weighted-in score, although the GCN model was able to discriminate well between different predicted groups, the separation was inadequate between false negative (FN) and true negative (TN) groups.
CONCLUSIONS: The GCN model considerably outperformed all other machine learning methods and baseline CPH models. Thus, when applied to this imbalanced COVID survival dataset, adopting a population graph representation may be an approach to achieving good prediction.