Assessment of deep learning based blood pressure prediction from PPG and rPPG signals

  title={Assessment of deep learning based blood pressure prediction from PPG and rPPG signals},
  author={Fabian Schrumpf and Patrick Frenzel and Christoph Aust and Georg Osterhoff and Mirco Fuchs},
  journal={2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  • Fabian Schrumpf, P. Frenzel, +2 authors M. Fuchs
  • Published 2021
  • Computer Science, Engineering
  • 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Exploiting photoplethysmography signals (PPG) for non-invasive blood pressure (BP) measurement is interesting for various reasons. First, PPG can easily be measured using fingerclip sensors. Second, camera-based approaches allow to derive remote PPG (rPPG) signals similar to PPG and therefore provide the opportunity for non-invasive measurements of BP. Various methods relying on machine learning techniques have recently been published. Performances are often reported as the mean average error… Expand

Figures and Tables from this paper

Assessment of Non-Invasive Blood Pressure Prediction from PPG and rPPG Signals Using Deep Learning
This work aims to analyze the PPG- and rPPG based BP prediction error with respect to the underlying data distribution and reveals a strong systematic increase of the prediction error towards less frequent BP values across NN architectures. Expand


Blood Pressure Estimation From PPG Signals Using Convolutional Neural Networks And Siamese Network
Two techniques are presented that enable continuous and noninvasive cuff-less BP estimation using photoplethysmography (PPG) signals with Convolutional Neural Networks (CNNs) and are as accurate as the values estimated by many home BP measuring devices. Expand
Blood Pressure Estimation from Photoplethysmogram Using a Spectro-Temporal Deep Neural Network
This study analyzed the MIMIC III database for high-quality PPG and arterial BP waveforms and used the PPG alongside its first and second derivative as inputs into a novel spectro-temporal deep neural network with residual connections, showing that personalization of models is important and substantially improves the results, while deriving a good general predictive model is difficult. Expand
Generalized Deep Neural Network Model for Cuffless Blood Pressure Estimation with Photoplethysmogram Signal Only
A deep neural network model capable of extracting 32 features exclusively from PPG signals for BP estimation has remarkably high accuracy on the largest BP database found in the literature, which shows its effectiveness compared to some prior works. Expand
End-to-End Blood Pressure Prediction via Fully Convolutional Networks
A cuffless BP prediction method based on a deep convolutional neural network (CNN) that can overcome the problems mentioned above and achieves excellent performance in predicting both systolic blood pressure and diastolicBlood pressure over other known approaches. Expand
A multistage deep neural network model for blood pressure estimation using photoplethysmogram signals
A multistage model based on deep neural networks to estimate systolic and diastolic blood pressures using the photoplethysmogram (PPG) signal is proposed and highlights the benefits of the proposed model in terms of appropriate feature extraction as well as estimation consistency. Expand
Combined Deep CNN–LSTM Network-based Multitasking Learning Architecture for Noninvasive Continuous Blood Pressure Estimation using Difference in ECG-PPG Features
A noninvasive continuous algorithm using the difference between the ECG and PPG as a new feature that can include PTT information is proposed, a deep CNN–LSTM-based multitasking machine learning model that outputs simultaneous prediction results of systolic (SBP) and diastolic blood pressures (DBP). Expand
Real-Time Cuffless Continuous Blood Pressure Estimation Using Deep Learning Model
This paper proposes deep learning regression models using an electrocardiogram (ECG) and photoplethysmogram (PPG) for the real-time estimation of systolicBlood pressure (SBP) and diastolic blood pressure (DBP) values and shows that the proposed model outperforms the existing methods and is able to achieve accurate estimation. Expand
End-To-End Deep Learning Architecture for Continuous Blood Pressure Estimation Using Attention Mechanism
An end-to-end deep learning architecture using only raw signals without the process of extracting features to improve the BP estimation performance using the attention mechanism is proposed, showing the applicability of the proposed model as an analytical metric for BP estimation. Expand
Photoplethysmography based stratification of blood pressure using multi information fusion artificial neural network
A new multi information fusion artificial neural network (MIF-ANN) is designed to effectively fuse and exploit multiple input data and play an important role in improving the accuracy of BP detection. Expand
Cuffless and Continuous Blood Pressure Estimation From PPG Signals Using Recurrent Neural Networks
  • Chadi El Hajj, P. Kyriacou
  • Computer Science, Medicine
  • 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
  • 2020
Experimental results show that the accuracy of the proposed methods outperform traditional models applied in the literature and satisfy the American National Standards of the Association for the Advancement of Medical Instrumentation. Expand