Blood Pressure Estimation Using Photoplethysmogram Signal and Its Morphological Features

Hasanzadeh, Navid; Ahmadi, Mohammad Mahdi; Mohammadzade, Hoda

doi:10.1109/jsen.2019.2961411

Cited by 82 publications

(53 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An important aspect of model development is the manner in which data are used to train, validate, and independently test a model. Cross validation allows a single data set to be used for both model training and validation, which is convenient for initial development ( 18 , 35 , 66 , 77 ). However, to obtain reliable results, data sets should ideally be divided into training, validation, and testing sets ( 70 ), and models should be tested on external data sets.…”

Section: Resultsmentioning

confidence: 99%

“…Studies have demonstrated the difficulty of estimating BP precisely from pulse wave features. BP estimates obtained from pulse wave features using ML algorithms can exhibit low bias (smaller than 0.68 mmHg), although achieving a low enough SD error of ≤8 mmHg (as required by AAMI standards) remains a challenge ( 35 , 66 ). The required level of precision has been achieved by using a two-step algorithm in which pulse waves are categorized as hypo-, normo-, or hypertensive, and then BP is estimated using a model specifically for that category ( 40 ).…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Assessing hemodynamics from the photoplethysmogram to gain insights into vascular age: a review from VascAgeNet

Charlton

Paliakaitė‬‬‬

Pilt

et al. 2022

American Journal of Physiology-Heart and Circulatory Physiology

View full text Add to dashboard Cite

The photoplethysmogram (PPG) signal is widely measured by clinical and consumer devices, and it is emerging as a potential tool for assessing vascular age. The shape and timing of the PPG pulse wave are both influenced by normal vascular ageing, changes in arterial stiffness and blood pressure, and atherosclerosis. This review summarises research into assessing vascular age from the PPG. Three categories of approaches are described: (i) those which use a single PPG signal (based on pulse wave analysis); (ii) those which use multiple PPG signals (such as pulse transit time measurement); and (iii) those which use PPG and other signals (such as pulse arrival time measurement). Evidence is then presented on the performance, repeatability and reproducibility, and clinical utility of PPG-derived parameters of vascular age. Finally, the review outlines key directions for future research to realise the full potential of photoplethysmography for assessing vascular age.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Assessing hemodynamics from the photoplethysmogram to gain insights into vascular age: a review from VascAgeNet

Charlton

Paliakaitė‬‬‬

Pilt

et al. 2022

American Journal of Physiology-Heart and Circulatory Physiology

View full text Add to dashboard Cite

show abstract

“…To achieve this goal, a tree-based pipeline optimization tool (TPOT) is used in this paper to estimate the blood pressure from PPG. To simplify, TPOT uses genetic programming from the Python package DEAP [59] to pick a series of pre-processing data functions and ML classification or regression algorithms to optimize the model's performance for a dataset of interest. In addition to the ML algorithm, the TPOT model pipeline, as presented in the example illustrated in Figure 1, includes a variety of data transformers implemented in the Scikit-learn Python library, such as various pre-processors (Min-Max Scaler, Standard Scaler, Max Abs Scaler, Normalizer, polynomial features expansion) and feature selectors (Select Percentile, Variance Threshold, recursive feature elimination).…”

Section: Methodsmentioning

confidence: 99%

A Continuous Cuffless Blood Pressure Estimation Using Tree-Based Pipeline Optimization Tool

Fati

Muneer

Akbar³

et al. 2021

Symmetry

View full text Add to dashboard Cite

High blood pressure (BP) may lead to further health complications if not monitored and controlled, especially for critically ill patients. Particularly, there are two types of blood pressure monitoring, invasive measurement, whereby a central line is inserted into the patient’s body, which is associated with infection risks. The second measurement is cuff-based that monitors BP by detecting the blood volume change at the skin surface using a pulse oximeter or wearable devices such as a smartwatch. This paper aims to estimate the blood pressure using machine learning from photoplethysmogram (PPG) signals, which is obtained from cuff-based monitoring. To avoid the issues associated with machine learning such as improperly choosing the classifiers and/or not selecting the best features, this paper utilized the tree-based pipeline optimization tool (TPOT) to automate the machine learning pipeline to select the best regression models for estimating both systolic BP (SBP) and diastolic BP (DBP) separately. As a pre-processing stage, notch filter, band-pass filter, and zero phase filtering were applied by TPOT to eliminate any potential noise inherent in the signal. Then, the automated feature selection was performed to select the best features to estimate the BP, including SBP and DBP features, which are extracted using random forest (RF) and k-nearest neighbors (KNN), respectively. To train and test the model, the PhysioNet global dataset was used, which contains 32.061 million samples for 1000 subjects. Finally, the proposed approach was evaluated and validated using the mean absolute error (MAE). The results obtained were 6.52 mmHg for SBS and 4.19 mmHg for DBP, which show the superiority of the proposed model over the related works.

show abstract

“…However, the prediction was based on a single BP measurement and did not consider the dynamics of BP. In [14] – [18] , PPG signals were used to predict short-term BP with ensemble trees models [14] – [16] and neural-network-based models [17] , [18] . However, PPG-based prediction is only applicable for a very short time horizon (~10 minutes), while our technique aims to predict BP in a longer time horizon, to provide actionable information to users.…”

Section: Related Workmentioning

confidence: 99%

Using Wearables and Machine Learning to Enable Personalized Lifestyle Recommendations to Improve Blood Pressure

Chiang

Wong

Dey

2021

IEEE J. Transl. Eng. Health Med.

View full text Add to dashboard Cite

show abstract

Blood Pressure Estimation Using Photoplethysmogram Signal and Its Morphological Features

Cited by 82 publications

References 42 publications

Assessing hemodynamics from the photoplethysmogram to gain insights into vascular age: a review from VascAgeNet

Assessing hemodynamics from the photoplethysmogram to gain insights into vascular age: a review from VascAgeNet

A Continuous Cuffless Blood Pressure Estimation Using Tree-Based Pipeline Optimization Tool

Using Wearables and Machine Learning to Enable Personalized Lifestyle Recommendations to Improve Blood Pressure

Contact Info

Product

Resources

About