An End-to-End Neural Network Model for Blood Pressure Estimation Using PPG Signal

Wang, Cuicui; Yang, Fan; Yuan, Xueguang; Zhang, Yangan; Chang, Kunliang; Li, Zhengyang

doi:10.1007/978-981-15-0187-6_30

Cited by 14 publications

(14 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data preprocessing: This part comprises signal smoothing of raw PPG data and the removal of abnormal data following standard procedures suggested by [23]. [15] and [17]. Both models comprised a convolutional neural network (CNN) and its modification to capture the spatial features of the waveforms.…”

Section: Methodsmentioning

confidence: 99%

“…Using artificial neural network (ANN) architecture for fitting the features to simultaneously estimate the DBP and SBP, this method reduces the error from the other methods used as comparisons, such as linear regression and regression support vector machine (RSVM). On the contrary, the whole PPG waveform segment was extracted and used as the input of deep learning models in [ 15 , 17 ]. Both models comprised a convolutional neural network (CNN) and its modification to capture the spatial features of the waveforms.…”

Section: Literature Reviewmentioning

confidence: 99%

“…They are popular as a low-cost but robust technology with full accessibility. Prior works have emphasized the relevance of a more detailed study of PPG signals only [ 13 , 14 , 15 , 16 , 17 , 18 ]. Hence, a ECG-free BP estimation model is preferable to improve the usability and to reduce the cost since the devices will no longer need additional biosensors for detecting ECG signals.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Generalized Deep Neural Network Model for Cuffless Blood Pressure Estimation with Photoplethysmogram Signal Only

Hsu

Chang

et al. 2020

Sensors

View full text Add to dashboard Cite

Due to the growing public awareness of cardiovascular disease (CVD), blood pressure (BP) estimation models have been developed based on physiological parameters extracted from both electrocardiograms (ECGs) and photoplethysmograms (PPGs). Still, in order to enhance the usability as well as reduce the sensor cost, researchers endeavor to establish a generalized BP estimation model using only PPG signals. In this paper, we propose a deep neural network model capable of extracting 32 features exclusively from PPG signals for BP estimation. The effectiveness and accuracy of our proposed model was evaluated by the root mean square error (RMSE), mean absolute error (MAE), the Association for the Advancement of Medical Instrumentation (AAMI) standard and the British Hypertension Society (BHS) standard. Experimental results showed that the RMSEs in systolic blood pressure (SBP) and diastolic blood pressure (DBP) are 4.643 mmHg and 3.307 mmHg, respectively, across 9000 subjects, with 80.63% of absolute errors among estimated SBP records lower than 5 mmHg and 90.19% of absolute errors among estimated DBP records lower than 5 mmHg. We demonstrated that our proposed model has remarkably high accuracy on the largest BP database found in the literature, which shows its effectiveness compared to some prior works.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Generalized Deep Neural Network Model for Cuffless Blood Pressure Estimation with Photoplethysmogram Signal Only

Hsu

Chang

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…For BP estimation, the output layer of the network often consists of two neurons, one for SBP and the other for DBP [ 7 , 12 , 13 , 14 ]. The metric used for the performance evaluation of the model was mean absolute error (MAE) [ 7 , 12 , 13 , 14 , 15 ]. Based on [ 14 ], the authors proposed a regression model based on the deep belief-network (DBN)-deep neural network (DNN) to learn about the complex nonlinear relationship amidst the generated feature vectors obtained from the oscillometric wave and the observed blood pressures.…”

Section: Introductionmentioning

confidence: 99%

Real-Time Cuffless Continuous Blood Pressure Estimation Using Deep Learning Model

Harfiya

Purwandari

et al. 2020

Sensors

102

View full text Add to dashboard Cite

Blood pressure monitoring is one avenue to monitor people’s health conditions. Early detection of abnormal blood pressure can help patients to get early treatment and reduce mortality associated with cardiovascular diseases. Therefore, it is very valuable to have a mechanism to perform real-time monitoring for blood pressure changes in patients. In this paper, we propose deep learning regression models using an electrocardiogram (ECG) and photoplethysmogram (PPG) for the real-time estimation of systolic blood pressure (SBP) and diastolic blood pressure (DBP) values. We use a bidirectional layer of long short-term memory (LSTM) as the first layer and add a residual connection inside each of the following layers of the LSTMs. We also perform experiments to compare the performance between the traditional machine learning methods, another existing deep learning model, and the proposed deep learning models using the dataset of Physionet’s multiparameter intelligent monitoring in intensive care II (MIMIC II) as the source of ECG and PPG signals as well as the arterial blood pressure (ABP) signal. The results show that the proposed model outperforms the existing methods and is able to achieve accurate estimation which is promising in order to be applied in clinical practice effectively.

show abstract

“…With the expressiveness of deep learning, several recent studies have been proposed to estimate BP with cuffless devices using only a single measurement, such as PPG, without depending on hand-crafted features. In [108], an end-to-end approach is proposed to estimate blood pressure from the pulse wave signal. Without complicated feature extraction, a normalized single pulse wave is fed into a deep neural network, which consists of depth-separable convolutional layers and gated recurrent units in the recurrent layers.…”

Section: Future Directionsmentioning

confidence: 99%

Continuous Non-Invasive Blood Pressure Monitoring: A Methodological Review on Measurement Techniques

Ellington

Lee

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Continuous measurement of blood pressure is crucial to the assessment of many medical conditions. However, the current clinical gold standard involving an arterial catheter, occluding cuff, and other invasive procedures are performed in hospital settings while home-based devices can provide only intermittent measurement and are not as reliable. Therefore, there is a significant need for continuous noninvasive blood pressure (cNIBP) monitoring in the daily life. Pulse transit time (PTT)/pulse arrival time (PAT)-based blood pressure measurement has proven its potential to address this need. In this article, we present state-of-the-art devices and recent literature related to measurement technologies used in PTT/PAT-based methods for cNIBP monitoring. Various physiological signals which could be used to enable cNIBP in the home setting are categorized into two groups (i.e., proximal waveforms and distal waveforms) and are thoroughly discussed and compared. Given insightful analysis of these waveforms, we highlight their combinations to derive PTT/PAT values for BP measurement then discuss challenges presented from the cuffless and PTT/PAT-based nature of these devices. Finally, we conclude with future directions needed for home-based cNIBP adaptation and present societal broader impacts.

show abstract

An End-to-End Neural Network Model for Blood Pressure Estimation Using PPG Signal

Cited by 14 publications

References 6 publications

Generalized Deep Neural Network Model for Cuffless Blood Pressure Estimation with Photoplethysmogram Signal Only

Generalized Deep Neural Network Model for Cuffless Blood Pressure Estimation with Photoplethysmogram Signal Only

Real-Time Cuffless Continuous Blood Pressure Estimation Using Deep Learning Model

Continuous Non-Invasive Blood Pressure Monitoring: A Methodological Review on Measurement Techniques

Contact Info

Product

Resources

About