arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1705.04524cs.LGcs.AImath.DSstat.ML
收藏

基于深度循环神经网络的长期血压预测

Long-term Blood Pressure Prediction with Deep Recurrent Neural Networks

The Chinese University of Hong Kong(香港中文大学);Key Laboratory for Health Informatics of the Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology(中国科学院健康信息学重点实验室,深圳先进技术研究院)

Peng Su, Xiao-Rong Ding, Yuan-Ting Zhang, Jing Liu, Fen Miao, Ni Zhao

摘要:

用于动脉血压(BP)估计的现有方法直接将输入生理信号映射到输出BP值,而没有明确地对BP动态中的潜在时间依赖性进行建模。因此,这些模型在很长一段时间内遭受精度衰减,因此需要频繁校准。在这项工作中,我们解决这个问题,制定BP估计作为一个序列预测问题,其中输入和目标都是时间序列。我们提出了一种新的深度递归神经网络(RNN),由多层长短期记忆(LSTM)网络组成,该网络包含(1)双向结构以访问输入序列的大规模上下文信息,以及(2)残余连接以允许深度RNN中的梯度更有效地传播。在静态BP数据集上对所提出的深度RNN模型进行了测试,收缩压(SBP)和舒张压(DBP)预测的均方根误差(RMSE)分别为3.90和2.66 mmHg,超过了传统BP预测模型的准确性。在多天BP数据集上,深度RNN在第1天SBP预测后的第1天、第2天、第4天和第6个月分别实现了3.84、5.25、5.80和5.81 mmHg的RMSE,相应的DBP预测分别为1.80、4.78、5.0和5.21 mmHg,优于所有先前的模型,具有显著的改进。实验结果表明,建模的BP动力学的时间依赖性显着提高长期BP预测精度。

英文摘要:

Existing methods for arterial blood pressure (BP) estimation directly map the input physiological signals to output BP values without explicitly modeling the underlying temporal dependencies in BP dynamics. As a result, these models suffer from accuracy decay over a long time and thus require frequent calibration. In this work, we address this issue by formulating BP estimation as a sequence prediction problem in which both the input and target are temporal sequences. We propose a novel deep recurrent neural network (RNN) consisting of multilayered Long Short-Term Memory (LSTM) networks, which are incorporated with (1) a bidirectional structure to access larger-scale context information of input sequence, and (2) residual connections to allow gradients in deep RNN to propagate more effectively. The proposed deep RNN model was tested on a static BP dataset, and it achieved root mean square error (RMSE) of 3.90 and 2.66 mmHg for systolic BP (SBP) and diastolic BP (DBP) prediction respectively, surpassing the accuracy of traditional BP prediction models. On a multi-day BP dataset, the deep RNN achieved RMSE of 3.84, 5.25, 5.80 and 5.81 mmHg for the 1st day, 2nd day, 4th day and 6th month after the 1st day SBP prediction, and 1.80, 4.78, 5.0, 5.21 mmHg for corresponding DBP prediction, respectively, which outperforms all previous models with notable improvement. The experimental results suggest that modeling the temporal dependencies in BP dynamics significantly improves the long-term BP prediction accuracy.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑