采用融合的U-net模型连续无创动脉血压预测方法

doi:10.3778/j.issn.1002-8331.2211-0031

摘要/Abstract

摘要： 持续的血压监测有助于心血管疾病的诊断和治疗。由于目前使用机器学习和深度学习通过人工提取特征参数来预测血压的方法，无法重建完整的血压信号，提出了基于融合的U-net模型的连续无创动脉血压测量方法。首先将原始光电容积脉搏波（PPG）信号作为输入，减少人工提取特征参数的误差；然后使用U-net网络重构动脉血压信号，为进一步提高预测血压波形精度，将重构的血压信号作为MultiResUnet网络的输入，采用MultiRes模块从数据中学习不同特征，Res Path模块缓解编码器和解码器之间的语义差异，使得模型学习变得更加容易。融合的U-net网络在MIMIC-Ⅲ数据集中的受试者评估中预测的动脉血压（ABP）波形与实际波形高度相关。计算出的收缩压（SBP）、舒张压（DBP）和平均压（MAP）的平均绝对误差分别为2.20±4.30 mmHg、1.82±3.146 mmHg和2.25±2.86 mmHg，且该方法符合美国医疗仪器促进协会（AAMI）的标准，同时在英国高压协会（BHS）标准中达到A级。

关键词: 动脉血压（ABP）, 电容积脉搏波（PPG）, 无创, U-net

Abstract: Continuous blood pressure monitoring is helpful to the diagnosis and treatment of cardiovascular diseases. At present, machine learning and deep learning are used to predict blood pressure by manually extracting feature parameters. This method cannot reconstruct complete blood pressure signals. Therefore, a continuous non-invasive arterial blood pressure measurement method based on the fused U-net model is proposed. Firstly, the original photoplethysmogram (PPG) signal is used as the input to reduce the error of manually extracting feature parameters. Secondly, the U-net network is used to reconstruct the arterial blood pressure signal. In order to further improve the accuracy of the predicted blood pressure waveform, the reconstructed blood pressure signal is used as the input of the MultiResUnet network. The MultiRes module is used to learn different features from the data. The Res Path module alleviates the semantic differences between the encoder and the decoder, making the model learning easier. The arterial blood pressure (ABP) waveform predicted by the fused U-net network in the subject evaluation of MIMIC -Ⅲ dataset is highly correlated with the actual waveform. The calculated mean absolute errors of systolic blood pressure (SBP), diastolic blood pressure (DBP) and mean pressure (MAP) are 2.20 ± 4.30 mmHg, 1.82 ± 3.146 mmHg and 2.25 ± 2.86 mmHg. The method satisfies the requirements of the Association for the Advancement of Medical Instrumentation (AAMI) standard and reaches Grade A in the British High Pressure Society (BHS) standard.

Key words: arterial blood pressure (ABP), photoplethysmogram (PPG), non-invasive, U-net

王军昂, 张立新, 王赛, 吴凯枫, 阚希, 陈乃源. 采用融合的U-net模型连续无创动脉血压预测方法[J]. 计算机工程与应用, 2024, 60(4): 324-330.

WANG Jun’ang, ZHANG Lixin, WANG Sai, WU Kaifeng, KAN Xi, CHEN Naiyuan. Predication Method of Continuous Non-Invasive Arterial Blood Pressure Using Fusion U-net Model[J]. Computer Engineering and Applications, 2024, 60(4): 324-330.

参考文献

[1] LAFLAMME M A, MURRY C E. Heart regeneration[J]. Nature, 2011, 473(7347): 326-335.
[2] TOWNSEND N, WILSON L, BHATNAGAR P, et al. Cardiovascular disease in Europe: epidemiological update 2016[J]. European Heart Journal, 2016, 37(42): 3232-3245.
[3] World Health Organization. A global brief on hypertension: silent killer, global public health crisis: World Health Day 2013[R]. World Health Organization, 2013.
[4] ?PINAR J. Hypertension and ischemic heart disease[J]. Cor et Vasa, 2012, 54(6): e433-e438.
[5] 陈晓, 杨瑶. 基于长期递归卷积网络的无创血压测量[J]. 电子测量技术, 2022, 45(4): 139-146.
CHEN X, YANG Y. Noninvasive blood pressure measurement based on long-term recursive convolution network[J]. Electronic Measurement Technology, 2022, 45(4): 139-146.
[6] SIARON K B, CORTES M X, STUTZMAN S E, et al. Blood pressure measurements are site dependent in a cohort of patients with neurological illness[J]. Scientific Reports, 2020, 10(1): 1-7.
[7] LI Y H, HARFIYA L N, PURWANDARI K, et al. Real-time cuffless continuous blood pressure estimation using deep learning model[J]. Sensors, 2020, 20(19): 5606.
[8] KACHUEE M, KIANI M M, MOHAMMADZADE H, et al. Cuffless blood pressure estimation algorithms for continuous health-care monitoring[J]. IEEE Transactions on Biomedical Engineering, 2016, 64(4): 859-869.
[9] MARTíNEZ G, HOWARD N, ABBOTT D, et al. Can photoplethysmography replace arterial blood pressure in the assessment of blood pressure?[J]. Journal of Clinical Medicine, 2018, 7(10): 316.
[10] KACHUEE M, KIANI M M, MOHAMMADZADE H, et al. Cuffless high-accuracy calibration-free blood pressure estimation using pulse transit time[C]//Proceedings of the 2015 IEEE International Symposium on Circuits and Systems, 2015: 1006-1009.
[11] 吴丹. 基于深度神经网络的连续无创血压检测及其应用研究[D]. 北京: 中国科学院大学 (中国科学院深圳先进技术研究院), 2017.
WU D. Continuous and noninvasive blood pressure measurement based on deep network and its applications[D]. Beijing: University of Chinese Academy of Sciences (Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences), 2017.
[12] ATHAYA T, CHOI S. An estimation method of continuous non-invasive arterial blood pressure waveform using photoplethysmography: a U-net architecture-based approach[J]. Sensors, 2021, 21(5): 1867.
[13] IBTEHAZ N, RAHMAN M S. MultiResUNet: rethinking the U-net architecture for multimodal biomedical image segmentation[J]. Neural Networks, 2020, 121: 74-87.
[14] SLAPNI?AR G, MLAKAR N, LU?TREK M. Blood pressure estimation from photoplethysmogram using a spectro-temporal deep neural network[J]. Sensors, 2019, 19(15): 3420.
[15] O’BRIEN E, PETRIE J, LITTLER W A, et al. The British hypertension society protocol for the evaluation of blood pressure measuring devices[J]. Journal of Hypertension, 1993, 11(S2): 43-62.
[16] Association for the Advancement of Medical Instrumentation. Manual, electronic or automated sphygmomanometers: ANSI/AAMI SP10-2002/A1[S]. American National Standards Institute, Inc, 2003.
[17] MOUSAVI S S, FIROUZMAND M, CHARMI M, et al. Blood pressure estimation from appropriate and inappropriate PPG signals using a whole-based method[J]. Biomedical Signal Processing and Control, 2019, 47: 196-206.
[18] WANG L, ZHOU W, XING Y, et al. A novel neural network model for blood pressure estimation using photoplethesmography without electrocardiogram[J]. Journal of Healthcare Engineering, 2018. DOI:10.1155/2018/7804243.
[19] HARFIYA L N, CHANG C C, LI Y H. Continuous blood pressure estimation using exclusively photopletysmography by LSTM-based signal-to-signal translation[J]. Sensors, 2021, 21(9): 2952.
[20] CHUANG C C, LEE C C, YENG C H, et al. Attention mechanism-based convolutional long short-term memory neural networks to electrocardiogram-based blood pressure estimation[J]. Applied Sciences, 2021, 11(24): 12019.