Novel Blood Pressure Waveform Reconstruction from Photoplethysmography using Cycle Generative Adversarial Networks

Continuous monitoring of blood pressure (BP) can help individuals manage their chronic diseases such as hypertension, requiring non-invasive measurement methods in free-living conditions. Recent approaches fuse Photoplethysmograph (PPG) and electrocardiographic (ECG) signals using different machine and deep learning approaches to noninvasively estimate BP; however, they fail to reconstruct the complete signal, leading to less accurate models. In this paper, we propose a cycle generative adversarial network (CycleGAN) based approach to extract a BP signal known as ambulatory blood pressure (ABP) from a clean PPG signal. Our approach uses a cycle generative adversarial network that extends the GAN architecture for domain translation, and outperforms state-of-the-art approaches by up to 2× in BP estimation.

[1]  S. Anderson,et al.  Blood pressure lowering for prevention of cardiovascular disease and death: a systematic review and meta-analysis , 2016, The Lancet.

[2]  Mohammad Abdullah Al Faruque,et al.  Energy-efficient Blood Pressure Monitoring based on Single-site Photoplethysmogram on Wearable Devices , 2021, 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC).

[3]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Md. Kamrul Hasan,et al.  Cuffless blood pressure estimation from electrocardiogram and photoplethysmogram using waveform based ANN-LSTM network , 2018, Biomed. Signal Process. Control..

[5]  Marco Levorato,et al.  A Deep Learning Approach to Predict Blood Pressure from PPG Signals , 2021, 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC).

[6]  Li Fei-Fei,et al.  Perceptual Losses for Real-Time Style Transfer and Super-Resolution , 2016, ECCV.

[7]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Kaiyang Li,et al.  A multi-type features fusion neural network for blood pressure prediction based on photoplethysmography , 2021, Biomed. Signal Process. Control..

[9]  Ming Liu,et al.  Novel wavelet neural network algorithm for continuous and noninvasive dynamic estimation of blood pressure from photoplethysmography , 2016, Science China Information Sciences.

[10]  Mostafa Charmi,et al.  Blood pressure estimation from appropriate and inappropriate PPG signals using A whole-based method , 2019, Biomed. Signal Process. Control..

[11]  R. Velik.  An objective review of the technological developments for radial pulse diagnosis in Traditional Chinese Medicine , 2015 .

[12]  Domenico Grimaldi,et al.  A Neural Network-based method for continuous blood pressure estimation from a PPG signal , 2013, 2013 IEEE International Instrumentation and Measurement Technology Conference (I2MTC).

[13]  Harshad Rai,et al.  Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks , 2018 .

[14]  R. Mrowka.  Arterial hypertension , 2017, Acta physiologica.

[15]  Arash Arami,et al.  Nonlinear Dynamic Modeling of Blood Pressure Waveform: Towards an Accurate Cuffless Monitoring System , 2020, IEEE Sensors Journal.

[16]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[17]  Amir M. Rahmani,et al.  An End-to-End and Accurate PPG-based Respiratory Rate Estimation Approach Using Cycle Generative Adversarial Networks , 2021, 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC).

[18]  Chia-Feng Juang,et al.  MLP-BP: A novel framework for cuffless blood pressure measurement with PPG and ECG signals based on MLP-Mixer neural networks , 2022, Biomed. Signal Process. Control..

[19]  V. Jeya Maria Jose,et al.  Investigation on the effect of Womersley number, ECG and PPG features for cuff less blood pressure estimation using machine learning , 2020, Biomed. Signal Process. Control..

[20]  Amir M. Rahmani,et al.  An Accurate Non-accelerometer-based PPG Motion Artifact Removal Technique using CycleGAN , 2021, ACM Trans. Comput. Heal..

[21]  Mehmet Rasit Yuce,et al.  A chest-based continuous cuffless blood pressure method: Estimation and evaluation using multiple body sensors , 2020, Inf. Fusion.

[22]  G Parati,et al.  Blood pressure measuring devices: recommendations of the European Society of Hypertension , 2001, BMJ : British Medical Journal.

[23]  Roger G. Mark,et al.  Continuous cardiac output monitoring by peripheral blood pressure waveform analysis , 2006, IEEE Transactions on Biomedical Engineering.