Central Aortic Blood Pressure Waveform Estimation with a Temporal Convolutional Network

• Published in: IEEE journal of biomedical and health informatics Vol. 27; no. 7; pp. 3622 - 3632
• Main Authors: Liu, Wenyan, Du, Shuo, Pang, Na, Zhang, Liangyu, Sun, Guozhe, Xiao, Hanguang, Zhao, Qi, Xu, Lisheng, Yao, Yudong, Alastruey, Jordi, Avolio, Alberto
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.07.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Aorta; Arterial Pressure; Artificial neural networks; Biomedical measurement; Biomedical monitoring; Blood pressure; Blood Pressure - physiology; Blood Pressure Determination - methods; Brain modeling; Cardiovascular diseases; Central aortic blood pressure waveform; Computational efficiency; Computational modeling; Computer applications; Computing costs; Convolution; Data acquisition; Feature extraction; Heart Rate; Humans; Long short-term memory; Measurement methods; Neural networks; Neural Networks, Computer; radial blood pressure waveform; Root-mean-square errors; sequence model; Signal processing; temporal convolutional network; Testing time; Training; Transfer functions; Waveforms
• ISSN: 2168-2194; 2168-2208; 2168-2208
• DOI: 10.1109/JBHI.2023.3268886

A novel temporal convolutional network (TCN) model is utilized to reconstruct the central aortic blood pressure (aBP) waveform from the radial blood pressure waveform. The method does not need manual feature extraction as traditional transfer function approaches. The data acquired by the SphygmoCor CVMS device in 1,032 participants as a measured database and a public database of 4,374 virtual healthy subjects were used to compare the accuracy and computational cost of the TCN model with the published convolutional neural network and bi-directional long short-term memory (CNN-BiLSTM) model. The TCN model was compared with CNN-BiLSTM in the root mean square error (RMSE). The TCN model generally outperformed the existing CNN-BiLSTM model in terms of accuracy and computational cost. For the measured and public databases, the RMSE of the waveform using the TCN model was 0.55 ± 0.40 mmHg and 0.84 ± 0.29 mmHg, respectively. The training time of the TCN model was 9.63 min and 25.51 min for the entire training set; the average test time was around 1.79 ms and 8.58 ms per test pulse signal from the measured and public databases, respectively. The TCN model is accurate and fast for processing long input signals, and provides a novel method for measuring the aBP waveform. This method may contribute to the early monitoring and prevention of cardiovascular disease.