Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
December 21, 2023

A Machine Learning Approach to Estimate Continuous Blood Pressure From Photoplethysmography

View Full Paper
Ask AI
Bookmark
Share

Key result

Cubic and Gaussian support vector machines accurately estimate BP from PPG signals meeting AAMI standards.

  • n=219

Why the study?

Continuous blood pressure monitoring is needed to mitigate health risks, but traditional methods like sphygmomanometers are unsuitable for continuous monitoring.

Can a machine learning-based method using photoplethysmography (PPG) signal features accurately estimate continuous blood pressure?

Population

657 PPG signals from 219 subjects

Comparison

Linear Regression vs SVM vs GPR vs Decision Tree algorithms

Design

Algorithm development and validation study

Authors

PKPathan Fayaz KhanIndira Gandhi Centre for Atomic ResearchSSS SenthilnathanIndira Gandhi Centre for Atomic Research

Discussion

Loading...

Member takes

Overview

May support cuffless BP monitoring development; leaves open prospective validation before clinical use.

Structured PICO

Can a machine learning-based method using photoplethysmography (PPG) signal features accurately estimate continuous blood pressure?

P
Population
219 subjects providing 657 PPG signals for the evaluation of machine learning algorithms for continuous blood pressure estimation.
E
Exposure
Machine learning-based method (Cubic Support Vector Machine [CSVM] and Gaussian Support Vector Machine [GSVM]) for continuous blood pressure estimation using PPG signal features
C
Comparator
Other machine learning algorithms (Linear Regression, Decision Tree, etc.)
O
Outcome
Accuracy of systolic and diastolic blood pressure estimationsurrogate

A novel machine learning approach using PPG signals accurately estimates continuous systolic and diastolic blood pressure, meeting AAMI standards and offering a cuffless alternative for continuous monitoring.

Cite This Study

Khan et al. (2023) studied Blood pressure estimation (n=219). Machine learning-based blood pressure estimation using PPG signals was evaluated on Systolic and diastolic blood pressure estimation accuracy. Machine learning algorithms, specifically cubic and Gaussian support vector machines, accurately estimated systolic and diastolic blood pressure from PPG signals, conforming to AAMI standards.

synapsesocial.com/papers/6a20dce634bef10fdaeb140dhttps://doi.org/10.1109/icdsaai59313.2023.10452561
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1A Novel Non-Invasive Cuff-Less Method for Continuous Blood Pressure Estimation Using Machine Learning and Photoplethysmography2024
  2. 2Continuous Monitoring of Blood Pressure with Evidential Regression2021 · 1 citations
  3. 3Blood pressure monitoring during anesthesia induction using PPG morphology features and machine learning2023 · 13 citations
  4. 4A continuous cuffless blood pressure measurement from optimal PPG characteristic features using machine learning algorithms2024 · 34 citations
  5. 5Blood Pressure Estimation Using Photoplethysmography Only: Comparison between Different Machine Learning Approaches2018 · 178 citations