Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
July 23, 2024

PPG-based neural network estimates systolic blood pressure with ~5 mmHg mean absolute error.

View Full Paper
Ask AI
Bookmark
Share

Why the study?

Continuous blood pressure monitoring is important for managing cardiovascular diseases, and PPG offers non-invasive monitoring based on blood volume changes.

Can a PPG-based electronic sensing system using a Feed-Forward Artificial Neural Network accurately estimate systolic and diastolic blood pressure without a cuff?

Population

Dataset of multi-wavelength PPG signals and reference blood pressure values

Comparison

PPG-based ANN algorithm vs reference device measurements

Design

Algorithm development and validation study

Key result

A PPG-based electronic sensing system using an artificial neural network estimated blood pressure with a mean absolute error of 5.08 ± 8.83 mmHg (systolic) and 4.37 ± 7.08 mmHg (diastolic).

Authors

CBChiara BotrugnoFDFrancesco Dell’Olio

Discussion

Loading...

Member takes

Overview

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

Structured PICO

Can a PPG-based electronic sensing system using a Feed-Forward Artificial Neural Network accurately estimate systolic and diastolic blood pressure without a cuff?

P
Population
Dataset of multi-wavelength photoplethysmographic (PPG) signals and reference blood pressure values
I
Intervention
Cuff-less blood pressure prediction system using Feed-Forward Artificial Neural Network (ANN) on PPG signals
C
Comparator
Blood pressure values derived from a reference device
O
Outcome
Mean Absolute Error of systolic and diastolic blood pressure estimationsurrogate

Main Result

Effect estimate: MAE 5.08 ± 8.83 mmHg (systolic), 4.37 ± 7.08 mmHg (diastolic)

A novel PPG-based machine learning algorithm demonstrates promising accuracy for cuff-less, calibration-free continuous blood pressure monitoring.

Cite This Study

Botrugno et al. (2024) studied Blood pressure estimation. PPG-based electronic sensing system with Artificial Neural Network vs. Reference device was evaluated on Mean Absolute Error for systolic and diastolic blood pressure (MAE 5.08 ± 8.83 mmHg (systolic), 4.37 ± 7.08 mmHg (diastolic)). A PPG-based electronic sensing system using an artificial neural network estimated blood pressure with a mean absolute error of 5.08 ± 8.83 mmHg (systolic) and 4.37 ± 7.08 mmHg (diastolic).

synapsesocial.com/papers/6a1d7d911c2cbcb15c5e63echttps://doi.org/10.1109/sas60918.2024.10636647
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 Machine Learning Approach to Estimate Continuous Blood Pressure From Photoplethysmography2023
  2. 2A Novel Non-Invasive Cuff-Less Method for Continuous Blood Pressure Estimation Using Machine Learning and Photoplethysmography2024
  3. 3Cuffless Blood Pressure Estimation Using Calibrated Cardiovascular Dynamics in the Photoplethysmogram2022 · 17 citations
  4. 4Systolic Blood Pressure Estimation from PPG Signal Using ANN2022 · 16 citations
  5. 5Advanced Bio-Inspired System for Noninvasive Cuff-Less Blood Pressure Estimation from Physiological Signal Analysis2018 · 51 citations