Blood Pressure Estimation by Photoplethysmogram Decomposition into Hyperbolic Secant Waves

T, Nagasawa; Iuchi, Kaito; Takahashi, Ryo; Tsunomura, Mari; Souza, Raquel Pantojo de; Ogawa‐Ochiai, Keiko; Tsumura, Norimichi; Cardoso, George C.

doi:10.3390/app12041798

Cited by 13 publications

(8 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… is typically observed during systole, therefore reflects the systolic component. represents the dicrotic wave 10 . represents the additional minor reflections and re-reflections in the systemic vascular structure with lower amplitude than the two main reflected waves 54 .…”

Section: Methodsmentioning

confidence: 99%

“…where |z i | is the number of features in z i . As most models cannot handle missing data, SHAP values are computed by replacing f (•) in equation (10) with f x (•) , a conditional expectation function of the original model. This step equates to replacing each missing feature with a random value representative of the datapoints the original model was trained over.…”

Section: Shap Values Feature Ranking Coefficientmentioning

confidence: 99%

“…The first reflection site is at the junction of the renal arteries resulting in a reflected pressure wave (known as the tidal wave) that is typically present in late systole 9 . The second reflection site is at the junction of the iliac arteries resulting in a reflected pressure wave (known as the dicrotic wave) that is typically present in early diastole 10 . Changes in arterial stiffness are thought to have a significant impact on the timing, amplitude, and morphology of the reflected pressure waves and therefore may significantly impact the shape of the PPG waveform 8 .…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Features from the photoplethysmogram and the electrocardiogram for estimating changes in blood pressure

Finnegan

Davidson

Harford

et al. 2023

Sci Rep

View full text Add to dashboard Cite

There is a growing emphasis being placed on the potential for cuffless blood pressure (BP) estimation through modelling of morphological features from the photoplethysmogram (PPG) and electrocardiogram (ECG). However, the appropriate features and models to use remain unclear. We investigated the best features available from the PPG and ECG for BP estimation using both linear and non-linear machine learning models. We conducted a clinical study in which changes in BP ($$\Delta$$ Δ BP) were induced by an infusion of phenylephrine in 30 healthy volunteers (53.8% female, 28.0 (9.0) years old). We extracted a large and diverse set of features from both the PPG and the ECG and assessed their individual importance for estimating $$\Delta$$ Δ BP through Shapley additive explanation values and a ranking coefficient. We trained, tuned, and evaluated linear (ordinary least squares, OLS) and non-linear (random forest, RF) machine learning models to estimate $$\Delta$$ Δ BP in a nested leave-one-subject-out cross-validation framework. We reported the results as correlation coefficient ($$\rho _p$$ ρ p ), root mean squared error (RMSE), and mean absolute error (MAE). The non-linear RF model significantly ($$p<0.05$$ p < 0.05 ) outperformed the linear OLS model using both the PPG and the ECG signals across all performance metrics. Estimating $$\Delta$$ Δ SBP using the PPG alone ($$\rho _p$$ ρ p = 0.86 (0.23), RMSE = 5.66 (4.76) mmHg, MAE = 4.86 (4.29) mmHg) performed significantly better than using the ECG alone ($$\rho _p$$ ρ p = 0.69 (0.45), RMSE = 6.79 (4.76) mmHg, MAE = 5.28 (4.57) mmHg), all $$p < 0.001$$ p < 0.001 . The highest ranking features from the PPG largely modelled increasing reflected wave interference driven by changes in arterial stiffness. This finding was supported by changes observed in the PPG waveform in response to the phenylephrine infusion. However, a large number of features were required for accurate BP estimation, highlighting the high complexity of the problem. We conclude that the PPG alone may be further explored as a potential single source, cuffless, blood pressure estimator. The use of the ECG alone is not justified. Non-linear models may perform better as they are able to incorporate interactions between feature values and demographics. However, demographics may not adequately account for the unique and individualised relationship between the extracted features and BP.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Shap Values Feature Ranking Coefficientmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Features from the photoplethysmogram and the electrocardiogram for estimating changes in blood pressure

Finnegan

Davidson

Harford

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…The authors of [ 69 ] investigated the propagation of pulses through an elastic tube filled with viscous fluid under initial pressure using Navier–Stokes equations. In addition, the authors of [ 185 ] proposed pulse decomposition analysis using hyperbolic secant (sech) waves and suggested that hyperbolic secant wave decomposition gives more accurate blood pressure values than the Gaussian function.…”

Section: Contact-based Bp Measurement From Ppg Signalsmentioning

confidence: 99%

Blood Pressure Measurement: From Cuff-Based to Contactless Monitoring

et al. 2022

View full text Add to dashboard Cite

Blood pressure (BP) determines whether a person has hypertension and offers implications as to whether he or she could be affected by cardiovascular disease. Cuff-based sphygmomanometers have traditionally provided both accuracy and reliability, but they require bulky equipment and relevant skills to obtain precise measurements. BP measurement from photoplethysmography (PPG) signals has become a promising alternative for convenient and unobtrusive BP monitoring. Moreover, the recent developments in remote photoplethysmography (rPPG) algorithms have enabled new innovations for contactless BP measurement. This paper illustrates the evolution of BP measurement techniques from the biophysical theory, through the development of contact-based BP measurement from PPG signals, and to the modern innovations of contactless BP measurement from rPPG signals. We consolidate knowledge from a diverse background of academic research to highlight the importance of multi-feature analysis for improving measurement accuracy. We conclude with the ongoing challenges, opportunities, and possible future directions in this emerging field of research.

show abstract

“…The photoplethysmography (PPG) waveform is defined by the primary pulse wave resulting from the heartbeat, as well as reflected waves occurring during the pulse propagation 1 . Pulse decomposition analysis (PDA) aims to define these constituent waves, as their parameters are influenced by levels of central systolic BP 2 .…”

Section: Introductionmentioning

confidence: 99%

An experimental study of the photoplethysmography waveform analysis method in estimation of blood pressure and vessel stiffness

Ferdinando¹,

Zienkiewicz²,

Abdelsamie³

et al. 2023

Dynamics and Fluctuations in Biomedical Photonics XX

View full text Add to dashboard Cite

Photoplethysmography (PPG) waveform is primary formed by absorbance and scattering of light caused by blood volume changes in the microvascular bed of tissue. The volume of blood is constantly changing due to cardiac activity and various low frequency physiological components, such as, respiration and sympathetic nervous system. Importantly, elastic property of blood vessels and blood pressure also greatly affects the volume of blood and thus PPG waveform inversely contains information on vessel elasticity and pressure that has been studied using e.g., pulse decomposition analysis (PDA) models. We emulated PPG waveform by using a simplified mock circulatory loop mimicking human circulatory system to study how changing elasticity of 3D printed vessels and blood pressure affects the PPG waveform, aiming to validate presented pulse decomposition analysis model for estimating vessel stiffness and blood pressure. The circulatory system built for the study is controlled via custom-made LabView software. Pumping frequency, pressure and flow of blood mimicking liquid can be controlled and accurately measured for a reference. The main analysis relied on the PDA that extracted five log-normal pulses for further analysis. In particular, we focused on the centre parameter of each log-normal pulse and observed it changes depending on the emulated parameters.

show abstract

Blood Pressure Estimation by Photoplethysmogram Decomposition into Hyperbolic Secant Waves

Cited by 13 publications

References 18 publications

Features from the photoplethysmogram and the electrocardiogram for estimating changes in blood pressure

Features from the photoplethysmogram and the electrocardiogram for estimating changes in blood pressure

Blood Pressure Measurement: From Cuff-Based to Contactless Monitoring

An experimental study of the photoplethysmography waveform analysis method in estimation of blood pressure and vessel stiffness

Contact Info

Product

Resources

About