A Neural Network-based method for continuous blood pressure estimation from a PPG signal

Kurylyak, Yuriy; Lamonaca, Francesco; Grimaldi, D.

doi:10.1109/i2mtc.2013.6555424

Cited by 229 publications

(177 citation statements)

References 15 publications

Supporting

Mentioning

170

Contrasting

Unclassified

Order By: Relevance

“…The MAE and RMSD are defined as: where the means the prediction result of t th sample and is the true value of that sample. Table I shows the MAE and RMSD in form of (MAE±RMSD) on SBP and DBP estimations using conventional method [15] and the proposed method for the testing set. Lower MAE means that average error between the estimated BP and true value is small.…”

mentioning

confidence: 99%

“…Moreover, Jeong et al [20] investigated the applicability of SDPPG for blood pressure measurement through analysis of the relationship between blood pressure and SDPPG features. They find that diastolic blood pressure (DBP) has a good relationship with the amplitude ratios of peak "b" to peak "a" and peak "e" to peak "a".Based on these recent findings, we combine SDPPG features with the conventional 21 time-scale PPG features [15] to develop a better BP estimator. We assume that the ratio of amplitudes and the amplitudes of corresponding PPG points (A_a, A_b, A_c, A_d, A_e, AP_a, AP_b, AP_c, AP_d, and AP_e), as shown in lower part of Fig.…”

mentioning

confidence: 99%

“…Therefore, PPG waveform analysis approach using a single PPG signal is very attractive for continuous and noninvasive BP measurement. However, several reported PPG waveform analysis based BP estimation methods [14], [15] From the recent studies [17], [18] of vascular aging through the second derivative of PPG (SDPPG), Pulse Wave Velocity (PWV) and SDPPG contain the information about aortic compliance and stiffness. These factors highly correlated with blood pressure.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Cuffless Blood Pressure Estimation Based on Photoplethysmography Signal and Its Second Derivative

Li¹,

Po²,

Fu³

2017

IJCTE

117

View full text Add to dashboard Cite

I. INTRODUCTIONBlood pressure (BP) is one of the four vital signs of human body besides heart rate, respiratory rate, and body temperature. Recently, the risk of having hypertension is extending from older to younger groups of the population. This trend making the number of people who need daily monitoring of BP is significantly increased. In addition, the demand for public resources in the hospital is becoming more and more serious and the type of healthcare is tending to individual-centered rather than hospital-centered. The need of self-monitoring BP devices dramatically increases in the recent decades. However, most of the commercial BP measuring devices require to inflate and deflate a cuff for determining the BP values. This measurement has a high demand for the medical practitioner"s operation skills.Self-monitoring BP devices using cuffless and noninvasive detective methods are very attractive for personal healthcare applications. It was reported that Manuscript received August 4, 2016; revised December 9, 2016 cuff-less, noninvasive, and continuous measurement of BP could be achieved by photoplethysmography (PPG) [1]- [7]. PPG [8] is a simple, portable and low-cost optical pulse that can be used to detect blood volume changes. The waveform of PPG is formed by heartbeat and affected by the condition of cardiovascular system [9]. When BP increases, the volumetric elasticity of blood vessel increases. This makes vessel wall stiff and the pulse wave propagation velocity is increased. The pulse wave propagation velocity (PWV) is represented as the pulse wave propagation distance divided by Pulse transit time (PTT). PTT is the time for the pulse wave to travel between two arterial sites, which is highly related with PWV. Normally, PTT is calculated from the time distance between R wave of ECG signal and following peak of fingertip PPG signal [10]. PTT based methods [5]-[7], [11]- [13] have been demonstrated to achieve relatively high accuracy on BP estimation, but two devices are required for the measurement. This is inconvenient and requires high operation skill in practical usage. Moreover, synchronization between two devices is also a big challenge of PTT approach. Therefore, PPG waveform analysis approach using a single PPG signal is very attractive for continuous and noninvasive BP measurement. However, several reported PPG waveform analysis based BP estimation methods [14], [15] From the recent studies [17], [18] of vascular aging through the second derivative of PPG (SDPPG), Pulse Wave Velocity (PWV) and SDPPG contain the information about aortic compliance and stiffness. These factors highly correlated with blood pressure. Basically, SDPPG is the acceleration of PPG and its waveform is in "W" shape with five sequential waves normally, as shown in the lower part of Fig. 1. These five waves are named as Initial Positive Wave (IPW), Early Negative Wave (ENW), Late Upsloping Wave (LUW), Late Downsloping Wave (LDW), and Diastolic Positive Wave (DPW). The positions of "a", "b", "c", "d", and "e" are peaks...

show abstract

mentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Cuffless Blood Pressure Estimation Based on Photoplethysmography Signal and Its Second Derivative

Li¹,

Po²,

Fu³

2017

IJCTE

117

View full text Add to dashboard Cite

show abstract

“…Time intervals between respectively 10, 25, 32, 50, 66, and 75 percent of the PPG amplitude -upward slope from diastolic to systolic points -are nominated by -diastolic width (DW) -DW10, DW25, DW32, DW50, DW66, and DW75, while for the PPG downward slope they are nominated by -systolic width (SW) -SW10, SW25, SW32, SW50, SW66, and SW75 [9]. We did not consider features related to the dicrotic notch because this peak is imperceptible in some cases, specifically elderly subjects, may fully be disappeared during exercise.…”

Section: Feature Extractionmentioning

confidence: 99%

Design and Implementation of a Non-invasive and Cuff-less Arterial Blood Pressure Monitoring System

Anvari

Yazdchi

Kayvanpour

et al. 2017

Computing in Cardiology Conference (CinC)

View full text Add to dashboard Cite

Hypertension or high blood pressure (BP) is one of the most common worldwide disease leading to heart attack or stroke. Continuous assessment of blood pressure level is key to diagnosing hypertension. In this study, we designed and tested a dedicated cuff-less monitoring system which estimates BP level without need for calibration. We obtained continuous measurements from 40 healthy subjects (30 males and 10 females) ranging from 20-30 years old. Our measurement protocol consisted of 15 minutes simultaneous electrocardiography (ECG) and photoplethysmography (PPG) within three sessions, i.e. rest, bicycle exercise, and recovery. From ECG and PPG signals, we obtained 34 candidate features from which up to 9 features were selected to estimate systolic and diastolic BP levels. We validate our results with three regression models such as linear regression, support vector machines (SVM) regression, and multilayer perceptron (MLP) to obtain the best results. The study provides a promising approach for modern cuff-less BP monitoring devices.

show abstract

“…The branch width features are chosen according to [11], while the AmBE feature is chosen according to patent [12].…”

Section: Introductionmentioning

confidence: 99%

Beat-to-beat ambulatory blood pressure estimation based on random forest

Huang

et al. 2016

2016 IEEE 13th International Conference on Wearable and Implantable Body Sensor Networks (BSN)

View full text Add to dashboard Cite

A Neural Network-based method for continuous blood pressure estimation from a PPG signal

Cited by 229 publications

References 15 publications

Cuffless Blood Pressure Estimation Based on Photoplethysmography Signal and Its Second Derivative

Cuffless Blood Pressure Estimation Based on Photoplethysmography Signal and Its Second Derivative

Design and Implementation of a Non-invasive and Cuff-less Arterial Blood Pressure Monitoring System

Beat-to-beat ambulatory blood pressure estimation based on random forest

Contact Info

Product

Resources

About