A new deep learning framework based on blood pressure range constraint for continuous cuffless BP estimation

Chen, Yongyi; Zhang, Dan; Karimi, Hamid Reza; Deng, Chao; Yin, Wutao

doi:10.1016/j.neunet.2022.04.017

Cited by 30 publications

(17 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fourth, the size of the dataset imposed a limitation on providing a separate and independent test dataset to validate the accuracy of the model. A larger database would provide the flexibility to set aside a portion of the data solely for testing purposes and offer a larger training set for the network that can ultimately increase the accuracy of the estimation, as was found in some previous studies such as the ones in [ 18 ] and [ 19 ], where a larger dataset was used. However, there could be other reasons behind their reported better performance, such as: Reference blood pressure values were taken invasively, whereas, in our study, these values are collected through noninvasive methods.…”

Section: Discussionmentioning

confidence: 99%

“…However, there could be other reasons behind their reported better performance, such as: Reference blood pressure values were taken invasively, whereas, in our study, these values are collected through noninvasive methods. In [ 18 ], because of the large dataset, the authors could afford to apply a BP range constraint, meaning that, whenever the output was beyond a certain threshold, it was eliminated and not considered for performance evaluation. The input in those studies was based on segmented windows of the collected data with overlaps.…”

Section: Discussionmentioning

confidence: 99%

“…In [ 18 ], because of the large dataset, the authors could afford to apply a BP range constraint, meaning that, whenever the output was beyond a certain threshold, it was eliminated and not considered for performance evaluation.…”

Section: Discussionmentioning

confidence: 99%

“…Most such features are generated from pulse morphology within individual beats [ 11 ]. In particular, data from a single PPG sensor have been used in some studies within a deep learning framework [ 18 , 19 ]. A detailed review of different PPG-based methods can be found in [ 20 ].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Cuffless Blood Pressure Estimation Using Calibrated Cardiovascular Dynamics in the Photoplethysmogram

Samimi

Dajani

2022

Bioengineering

View full text Add to dashboard Cite

An important means for preventing and managing cardiovascular disease is the non-invasive estimation of blood pressure. There is particular interest in developing approaches that provide accurate cuffless and continuous estimation of this important vital sign. This paper proposes a method that uses dynamic changes of the pulse waveform over short time intervals and calibrates the system based on a mathematical model that relates reflective PTT (R-PTT) to blood pressure. An advantage of the method is that it only requires collecting the photoplethysmogram (PPG) using one optical sensor, in addition to initial non-invasive measurements of blood pressure that are used for calibration. This method was applied to data from 30 patients, resulting in a mean error (ME) of 0.59 mmHg, a standard deviation of error (SDE) of 7.07 mmHg, and a mean absolute error (MAE) of 4.92 mmHg for diastolic blood pressure (DBP) and an ME of 2.52 mmHg, an SDE of 12.15 mmHg, and an MAE of 8.89 mmHg for systolic blood pressure (SBP). These results demonstrate the possibility of using the PPG signal for the cuffless continuous estimation of blood pressure based on the analysis of calibrated changes in cardiovascular dynamics, possibly in conjunction with other methods that are currently being researched.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Cuffless Blood Pressure Estimation Using Calibrated Cardiovascular Dynamics in the Photoplethysmogram

Samimi

Dajani

2022

Bioengineering

View full text Add to dashboard Cite

show abstract

“…A BP estimation model was developed using the receptive field parallel attention shrinkage network to increase the effectiveness of feature extraction from PPG signals. The mean absolute errors (MAEs) ± SDs for the estimated SBP and DBP were 1.63 ± 2.43 and 2.26 ± 4.04 mmHg, respectively [13]. Li et al proposed a blood pressure estimation method, which can be calibrated with reference inputs rather than with retraining.…”

Section: Introductionmentioning

confidence: 99%

Estimation of Beat-by-Beat Blood Pressure and Heart Rate From ECG and PPG Using a Fine-Tuned Deep CNN Model

2022

View full text Add to dashboard Cite

Given that current cuffless blood pressure (BP) measurement technologies feature acceptable overall accuracy, this paper proposed a sufficiently accurate cuffless BP estimation method based on photoplethysmography (PPG) and electrocardiography (ECG) signals. This study used single-channel PPG and ECG signals to estimate heart rate (HR), diastolic BP (DBP), and systolic BP (SBP). A modified long-term recurrent convolutional network comprising a multi-scale convolution network and a long short-term memory (LSTM) network was used to develop a deep learning model for accurately estimating BP and HR. The PPG and ECG signal data of 1551 patients were obtained from the Data Sets-UCI Machine Learning Repository of the University of California, Irvine. The study dataset comprised ECG, PPG, and arterial BP (ABP) signals from the PhysioNet MIMIC II dataset. The original signals were processed by removing noise and artifacts. The aforementioned dataset contains 12,000 records in a hierarchical data format, with each record containing three signals, namely 125-Hz ECG signals from channel II (ECG lead II), 125-Hz PPG signals from the fingertip, and 125-Hz invasive ABP signals. To validate the stability and performance of the developed model, ten-fold cross-validation was conducted. The mean absolute error (MAE) (standard deviation (SD)) values of the developed model for predicting SBP, DBP, and HR were 2.24 mmHg (3.59 mmHg), 1.40 mmHg (2.56 mmHg), and 0.84 bpm (2.23 bpm), respectively. In addition, the estimated SBP and DBP values satisfied the standards of the British Hypertension Society and the Association for the Advancement of Medical Instrumentation. Compared with the methods proposed in other studies, the deep learning model developed in this study required a lower number of layers to provide accurate SBP, DBP, and HR estimations. The results of this study confirmed the effectiveness of the proposed deep learning architecture.

show abstract

Policy-Based Hypertension Monitoring Using Formal Runtime Verification Monitors

Panda

Pinisetty

Roop

2022

Bioinformatics Research and Applications

View full text Add to dashboard Cite

A new deep learning framework based on blood pressure range constraint for continuous cuffless BP estimation

Cited by 30 publications

References 34 publications

Cuffless Blood Pressure Estimation Using Calibrated Cardiovascular Dynamics in the Photoplethysmogram

Cuffless Blood Pressure Estimation Using Calibrated Cardiovascular Dynamics in the Photoplethysmogram

Estimation of Beat-by-Beat Blood Pressure and Heart Rate From ECG and PPG Using a Fine-Tuned Deep CNN Model

Policy-Based Hypertension Monitoring Using Formal Runtime Verification Monitors

Contact Info

Product

Resources

About