Continuous blood pressure measurement from one-channel electrocardiogram signal using deep-learning techniques

作者：

Highlights：

• A novel approach is proposed for continuous blood pressure measurement using one-channel ECG signal for ubiquitous healthcare application.

• A deep learning architecture combined ResNet with LSTM is proposed to discover the spatial-temporal information of the ECG signal for BP modeling.

• The performance is validated on datasets involving ICU patients and arrhythmias patients, and thus indicated good reliability.

摘要

•A novel approach is proposed for continuous blood pressure measurement using one-channel ECG signal for ubiquitous healthcare application.•A deep learning architecture combined ResNet with LSTM is proposed to discover the spatial-temporal information of the ECG signal for BP modeling.•The performance is validated on datasets involving ICU patients and arrhythmias patients, and thus indicated good reliability.

论文关键词：Blood pressure,Residual network,Long short-term memory,ECG

论文评审过程：Received 26 September 2019, Revised 24 June 2020, Accepted 24 June 2020, Available online 27 June 2020, Version of Record 16 July 2020.

论文官网地址：https://doi.org/10.1016/j.artmed.2020.101919