论文标题
使用多任务盖式复发单元从电子健康记录中预测心血管疾病的发作
Prediction of the onset of cardiovascular diseases from electronic health records using multi-task gated recurrent units
论文作者
论文摘要
在这项工作中，我们提出了一个多任务复发性神经网络，其注意力机制可在不同时间范围内从电子健康记录（EHR）预测心血管事件。将所提出的方法与使用NHS基金会信托的5年数据进行比较，将标准的临床风险预测变量（QRISK）和机器学习替代方案进行比较。考虑到最大的时间范围，该模型在预测中风（AUC = 0.85）和心肌梗塞（AUC = 0.89）方面的表现优于标准临床风险评分，考虑到最大的时间范围。使用\ gls {mt}设置的好处在很短的时间范围内变得可见，这导致AUC增加在2-6％之间。此外，我们探讨了单个特征和注意力重量在预测心血管事件中的重要性。我们的结果表明，复发性的神经网络方法受益于医院的纵向信息，并演示了如何将机器学习技术应用于二级护理。
In this work, we propose a multi-task recurrent neural network with attention mechanism for predicting cardiovascular events from electronic health records (EHRs) at different time horizons. The proposed approach is compared to a standard clinical risk predictor (QRISK) and machine learning alternatives using 5-year data from a NHS Foundation Trust. The proposed model outperforms standard clinical risk scores in predicting stroke (AUC=0.85) and myocardial infarction (AUC=0.89), considering the largest time horizon. Benefit of using an \gls{mt} setting becomes visible for very short time horizons, which results in an AUC increase between 2-6%. Further, we explored the importance of individual features and attention weights in predicting cardiovascular events. Our results indicate that the recurrent neural network approach benefits from the hospital longitudinal information and demonstrates how machine learning techniques can be applied to secondary care.
