Attention-based residual improved U-Net model for continuous blood pressure monitoring by using photoplethysmography signal

Article Engineering, Biomedical

Towards accurate estimation of cuffless and continuous blood pressure using multi-order derivative and multivariate photoplethysmogram features

Wan-Hua Lin et al.

Summary: This study investigated the efficiency and accuracy of using only PPG features for CC-BP estimation, demonstrating that using 65 PPG features resulted in significantly higher accuracy compared to using hybrid PAT and PPG indicators.

BIOMEDICAL SIGNAL PROCESSING AND CONTROL (2021)

Add to Collection

Article Automation & Control Systems

Application of regularized Savitzky-Golay filters to identification of time-varying systems

Maciej Jan Niedzwiecki et al.

Summary: SG filtering is a classical signal smoothing technique that can be successfully applied to the identification of time-varying FIR systems through its regularized version. The preestimation technique converts the identification problem into a smoothing problem, resulting in estimators with excellent parameter tracking capabilities.

AUTOMATICA (2021)

Add to Collection

Article Engineering, Biomedical

Deep learning models for cuffless blood pressure monitoring from PPG signals using attention mechanism

C. El-Hajj et al.

Summary: A study proposed recurrent neural network models utilizing Photoplethysmogram signals with bidirectional connections and attention mechanism to accurately estimate systolic and diastolic blood pressure. Experimental results showed that these models could capture the non-linear relationship and outperformed traditional machine learning methods on datasets, meeting global standards.

BIOMEDICAL SIGNAL PROCESSING AND CONTROL (2021)

Add to Collection

Article Chemistry, Analytical

An Estimation Method of Continuous Non-Invasive Arterial Blood Pressure Waveform Using Photoplethysmography: A U-Net Architecture-Based Approach

Tasbiraha Athaya et al.

Summary: The study proposes a method using deep learning architecture for blood pressure monitoring, estimating non-invasively with fingertip PPG signals. The results demonstrate the effectiveness of directly estimating ABP waveform and achieving blood pressure indicators within acceptable error ranges according to standards.

SENSORS (2021)

Add to Collection

Article Chemistry, Analytical

Continuous Blood Pressure Estimation Using Exclusively Photopletysmography by LSTM-Based Signal-to-Signal Translation

Latifa Nabila Harfiya et al.

Summary: This study introduces a novel deep learning model for signal-to-signal translation from PPG to ABP, achieving continuous blood pressure estimation with high accuracy. The model meets the standards set by AAMI and BHS for SBP and DBP prediction, showcasing the potential for accurate continuous BP estimation without complex feature engineering.

SENSORS (2021)

Add to Collection

Review Engineering, Biomedical

A review of machine learning in hypertension detection and blood pressure estimation based on clinical and physiological data

Erick Martinez-Rios et al.

Summary: The paper reviews the application of machine learning techniques in medicine for detecting hypertension or estimating blood pressure. It suggests an opportunity to improve model performance by combining demographic or clinical data with physiological signals.

BIOMEDICAL SIGNAL PROCESSING AND CONTROL (2021)

Add to Collection

Article Clinical Neurology

Perioperative Continuous Noninvasive Arterial Pressure Monitoring for Neuroendovascular Interventions: Prospective Study for Evaluation of the Vascular Unloading Technique

Alejandro Bugarini et al.

Summary: The study found that the ClearSight system provided accurate measurements of arterial blood pressure compared with invasive methods and within safe clinical parameters. This method may serve as a safe and reliable alternative for invasive blood pressure monitoring during neuroendovascular procedures.

WORLD NEUROSURGERY (2021)

Add to Collection

Review Engineering, Biomedical