PPG2ABP: Translating Photoplethysmogram (PPG) Signals to Arterial Blood Pressure (ABP) Waveforms

Cardiovascular diseases are one of the most severe causes of mortality, taking a heavy toll of lives annually throughout the world. The continuous monitoring of blood pressure seems to be the most viable option, but this demands an invasive process, bringing about several layers of complexities. This motivates us to develop a method to predict the continuous arterial blood pressure (ABP) waveform through a non-invasive approach using photoplethysmogram (PPG) signals. In addition we explore the advantage of deep learning as it would free us from sticking to ideally shaped PPG signals only, by making handcrafted feature computation irrelevant, which is a shortcoming of the existing approaches. Thus, we present, PPG2ABP, a deep learning based method, that manages to predict the continuous ABP waveform from the input PPG signal, with a mean absolute error of 4.604 mmHg, preserving the shape, magnitude and phase in unison. However, the more astounding success of PPG2ABP turns out to be that the computed values of DBP, MAP and SBP from the predicted ABP waveform outperforms the existing works under several metrics, despite that PPG2ABP is not explicitly trained to do so.

[1]  Boreom Lee,et al.  Enhancing the estimation of blood pressure using pulse arrival time and two confounding factors , 2010, Physiological measurement.

[2]  Steve Warren,et al.  Two-Stage Approach for Detection and Reduction of Motion Artifacts in Photoplethysmographic Data , 2010, IEEE Transactions on Biomedical Engineering.

[3]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[4]  A. Hill,et al.  The Velocity of the Pulse Wave in Man , 1922 .

[5]  M. Elgendi,et al.  Can Photoplethysmography Replace Arterial Blood Pressure in the Assessment of Blood Pressure? , 2018, Journal of clinical medicine.

[6]  Mohamed Elgendi,et al.  Optimal Signal Quality Index for Photoplethysmogram Signals , 2016, Bioengineering.

[7]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[8]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[9]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[10]  I. Johnstone,et al.  Ideal spatial adaptation by wavelet shrinkage , 1994 .

[11]  D. Giavarina.  Understanding Bland Altman analysis , 2015, Biochemia medica.

[12]  David L. Donoho,et al.  De-noising by soft-thresholding , 1995, IEEE Trans. Inf. Theory.

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

[14]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[15]  Guido van Rossum,et al.  Python Programming Language , 2007, USENIX Annual Technical Conference.

[16]  Brij N. Singh,et al.  Optimal selection of wavelet basis function applied to ECG signal denoising , 2006, Digit. Signal Process..

[17]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Sun K. Yoo,et al.  Motion artifact reduction in photoplethysmography using independent component analysis , 2006, IEEE Transactions on Biomedical Engineering.

[19]  Cheng Wang,et al.  Monitoring heart and respiratory rates at radial artery based on PPG , 2013 .

[20]  T. H. Kyaw,et al.  Multiparameter Intelligent Monitoring in Intensive Care II: A public-access intensive care unit database* , 2011, Critical care medicine.

[21]  L A Geddes,et al.  Pulse transit time as an indicator of arterial blood pressure. , 1981, Psychophysiology.

[22]  X. Aubert,et al.  Is pulse transit time a good indicator of blood pressure changes during short physical exercise in a young population? , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[23]  Mohammad Sohel Rahman,et al.  MultiResUNet : Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation , 2019, Neural Networks.

[24]  Kemal Polat,et al.  Non-invasive prediction of hemoglobin level using machine learning techniques with the PPG signal's characteristics features , 2015, Appl. Soft Comput..