Article
Computer Science, Information Systems
Chenbin Ma, Peng Zhang, Fan Song, Yangyang Sun, Guangda Fan, Tianyi Zhang, Youdan Feng, Guanglei Zhang
Summary: In this study, a Transformer-based method with knowledge distillation (KD-Informer) is proposed for continuous blood pressure (BP) monitoring using only photoplethysmography (PPG) signals. Experimental results showed that the KD-Informer can accurately estimate systolic BP (SBP) and diastolic BP (DBP) with high reliability and robustness.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Engineering, Electrical & Electronic
Bing-Jhang Wu, Bing-Fei Wu, Chi-Po Hsu
Summary: Blood pressure is a vital sign strongly correlated with human health, but current measurement methods are inconvenient and carry infection risks. This study presents an algorithm for estimating blood pressure based on remote photoplethysmography, leveraging the Windkessel model and hand-crafted waveform characteristics. The proposed method outperforms benchmark algorithms, achieving mean absolute errors of 6.48mmHg and 5.06mmHg for systolic and diastolic blood pressure, respectively, meeting the validation protocol of the British Hypertension Society.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Health Care Sciences & Services
Yan Degiorgis, Martin Proenca, Yassine Ghamri, Gregory Hofmann, Mathieu Lemay, Patrick Schoettker
Summary: During anesthesia, using a photoplethysmography (PPG)-based continuous blood pressure (BP) measurement device in addition to the standard cuff-based monitor can reduce the error of BP measurement and improve patient safety.
JOURNAL OF PERSONALIZED MEDICINE
(2022)
Article
Computer Science, Information Systems
Thiago Bulhoes Da Silva Costa, Felipe Meneguitti Dias, Diego Armando Cardona Cardenas, Marcelo Arruda Fiuza De Toledo, Daniel Mario De Lima, Jose Eduardo Krieger, Marco Antonio Gutierrez
Summary: Cardiovascular diseases are the leading causes of death, and blood pressure monitoring plays a crucial role in prevention, diagnosis, assessment, and treatment. Previous studies on photoplethysmography (PPG) for blood pressure measurement showed overly optimistic results due to limitations in their train/test split configuration. Our study demonstrates that intra-subject data arrangements outperform inter-subject arrangements regardless of the algorithm used, and using only demographic attributes can achieve comparable results to intra-subject scenarios. These findings suggest that algorithms without a calibration strategy in an intra-subject setting may be identifying patients rather than predicting blood pressure.
Article
Physiology
Dean Nachman, Arik Eisenkraft, Nir Goldstein, Arik Ben-Ishay, Meir Fons, Roei Merin, Yftach Gepner
Summary: This observational comparison study found that a photoplethysmography-based non-invasive cuffless BP device showed similar and high agreement with a cuff-based BP device in BP measurements across sex, BMI, and skin color groups.
FRONTIERS IN PHYSIOLOGY
(2022)
Article
Biophysics
Artur Polinski
Summary: The objective of the study is to investigate the effect of signal sampling frequency and low-pass filtering on the accuracy of localizing fiducial points in the photoplethysmographic signal (PPG) and the estimation of blood pressure. Statistical analysis was performed on 3,799 data samples from a publicly available database. Results show that for noise-free data, cubic spline interpolation has limited influence on the localization of fiducial points within the considered sampling frequency range of 62.5-500 Hz. The pulse transit time (PTT) approach yields better results than the pulse arrival time (PAT) approach, with the tangent fiducial point producing the best results. The findings have significance in determining the minimum requirements for sampling frequency and filtering of PPG signals for reliable blood pressure estimation.
PHYSIOLOGICAL MEASUREMENT
(2023)
Article
Chemistry, Analytical
Rafal Siemasz, Krzysztof Tomczuk, Ziemowit Malecha, Piotr Andrzej Felisiak, Artur Weiser
Summary: This article presents a prototype of a new, non-invasive, cuffless, self-calibrating blood pressure measuring device equipped with a pneumatic pressure sensor. The developed device does not require a cuff and can be used on arteries where cuff placement would be impossible. The obtained results showed that the systolic and diastolic pressure measurement errors of the proposed device were within acceptable limits.
Article
Engineering, Biomedical
C. El-Hajj, P. A. Kyriacou
Summary: The research explores the use of deep learning models for continuous cuffless blood pressure monitoring, which performs well and meets international standards.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Chemistry, Analytical
Gizem Yilmaz, Xingyu Lyu, Ju Lynn Ong, Lieng Hsi Ling, Thomas Penzel, B. T. Thomas Yeo, Michael W. L. Chee
Summary: This study utilized machine learning to predict nocturnal blood pressure using single-channel fingertip plethysmography. The results demonstrated the accuracy of the predictions, highlighting the potential for a cuffless method to continuously monitor blood pressure during sleep.
Article
Engineering, Electrical & Electronic
Jukka-Pekka Sirkia, Tuukka Panula, Matti Kaisti
Summary: This work presents a method for extracting information from different depths of the cutaneous vasculature using an optical sensor with controllable external compression force. The experiments show that the optical channels can estimate blood pressure at different depths, including microvascular blood vessels. The results indicate that the method can obtain signals from large arteries deep in the skin to arterioles and capillaries close to the surface.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Computer Science, Information Systems
Rebecca Mieloszyk, Hope Twede, Jonathan Lester, Jeremiah Wander, Sumit Basu, Gabe Cohn, Greg Smith, Dan Morris, Sidhant Gupta, Desney Tan, Nicolas Villar, Moni Wolf, Sailaja Malladi, Matt Mickelson, Lauren Ryan, Lindsey Kim, Jeffrey Kepple, Susanne Kirchner, Emma Wampler, Riena Terada, Joel Robinson, Ron Paulsen, T. Scott Saponas
Summary: This study demonstrated the results of blood pressure estimation in both lab and daily life using different feature groups, with superior performance shown by the radial tonometry-derived feature group. The study emphasizes the need for diverse populations and challenging evaluation settings in blood pressure estimation research.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2022)
Article
Chemistry, Analytical
Treesukon Treebupachatsakul, Apivitch Boosamalee, Siratchakrit Shinnakerdchoke, Suejit Pechprasarn, Nuntachai Thongpance
Summary: This research proposes an algorithm to preprocess photoplethysmography (PPG) and electrocardiogram (ECG) signals and apply them to deep learning for accurate continuous blood pressure monitoring. The algorithm includes several steps such as signal separation, randomization, Fourier transform, and normalization. The neural network trained with this algorithm achieves high accuracy in predicting continuous blood pressure.
Article
Computer Science, Interdisciplinary Applications
Elisa Mejia-Mejia, James M. May, Mohamed Elgendi, Panayiotis A. Kyriacou
Summary: Features extracted from photoplethysmography (PPG) based Pulse Rate Variability (PRV) can effectively classify hypertensive, hypotensive, and normotensive events, as well as estimate blood pressure values in critically ill patients. 5-minute segments show improved performance compared to 1-minute segments in classification and estimation tasks.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2021)
Article
Engineering, Biomedical
Naimahmed Nesaragi, Lars Oivind Hoiseth, Hemin Ali Qadir, Leiv Arne Rosseland, Per Steinar Halvorsen, Ilangko Balasingham
Summary: This article aims to capture the complex interplay in physiological responses related to both bleeding and fluid resuscitation using a challenging LBNP setup.
BIOCYBERNETICS AND BIOMEDICAL ENGINEERING
(2023)
Review
Chemistry, Analytical
Tasbiraha Athaya, Sunwoong Choi
Summary: Accurate estimation of blood pressure waveforms is crucial for patient safety and care in ICUs. This review summarizes the current knowledge about BP waveforms, discusses three noninvasive methodologies for BP waveform estimation, and examines the feasibility of using these strategies at home and in ICUs.