计算机应用与软件2025，Vol.42Issue(6)：100-108,9.DOI:10.3969/j.issn.1000-386x.2025.06.014
基于类时空间图卷积的心脑血管病死亡率预测
CARDIOVASCULAR AND CEREBROVASCULAR DISEASE MORTALITY PREDICTION BASED ON SPATIAL-LIKE TEMPORAL GRAPH CONVOLUTIONAL
摘要
Abstract
Existing clinical prediction models are difficult to effectively utilize medical record data with many missing values and often only consider the time-series information of a single patient,ignoring the potential connections between similar patients.A spatial-like temporal graph convolutional model BSim-STGCN is proposed to address the above problems.The model designed a global missing information capture mechanism for obtaining the current missing representation of missing values in the entire time series.A spatial-like graph convolution(Spatial-like GCN)based on patient similarity was proposed to model dependencies between similar patients.Experiments on two real datasets show that the prediction accuracy of the BSim-STGCN model outperforms other clinical prediction models.关键词
心脑血管疾病/缺失值处理/患者相似度/图卷积神经网络/死亡率预测Key words
Cardiovascular and cerebrovascular disease/Missing value completion/Patient similarity/Graph convo-lutional neural network/Mortality prediction分类
信息技术与安全科学引用本文复制引用
王晨舒,刘志锋..基于类时空间图卷积的心脑血管病死亡率预测[J].计算机应用与软件,2025,42(6):100-108,9.基金项目
社会发展"江苏省重点研发计划"项目(BE2018627). （BE2018627）
