An automatic beat detection algorithm for pressure signals

Mateo Aboy, James McNames, Tran Thong, Daniel Tsunami, Miles Ellenby, Brahm Goldstein

Research output: Contribution to journalArticle

129 Citations (Scopus)

Abstract

Beat detection algorithms have many clinical applications including pulse oximetry, cardiac arrhythmia detection, and cardiac output monitoring. Most of these algorithms have been developed by medical device companies and are proprietary. Thus, researchers who wish to investigate pulse contour analysis must rely on manual annotations or develop their own algorithms. We designed an automatic detection algorithm for pressure signals that locates the first peak following each heart beat. This is called the percussion peak in intracranial pressure (ICP) signals and the systolic peak in arterial blood pressure (ABP) and pulse oximetry (SpO 2) signals. The algorithm incorporates a filter bank with variable cutoff frequencies, spectral estimates of the heart rate, rank-order nonlinear filters, and decision logic. We prospectively measured the performance of the algorithm compared to expert annotations of ICP, ABP, and SpO 2 signals acquired from pediatric intensive care unit patients. The algorithm achieved a sensitivity of 99.36% and positive predictivity of 98.43% on a dataset consisting of 42,539 beats.

Original languageEnglish (US)
Pages (from-to)1662-1670
Number of pages9
JournalIEEE Transactions on Biomedical Engineering
Volume52
Issue number10
DOIs
StatePublished - Oct 2005

Fingerprint

Blood pressure
Intensive care units
Pediatrics
Filter banks
Cutoff frequency
Monitoring
Industry

Keywords

  • Arterial blood pressure (ABP)
  • Component detection
  • Intracranial pressure (ICP)
  • Pressure beat detection
  • Pulse contour analysis
  • Pulse oximetry (SpO )

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

An automatic beat detection algorithm for pressure signals. / Aboy, Mateo; McNames, James; Thong, Tran; Tsunami, Daniel; Ellenby, Miles; Goldstein, Brahm.

In: IEEE Transactions on Biomedical Engineering, Vol. 52, No. 10, 10.2005, p. 1662-1670.

Research output: Contribution to journalArticle

Aboy, Mateo ; McNames, James ; Thong, Tran ; Tsunami, Daniel ; Ellenby, Miles ; Goldstein, Brahm. / An automatic beat detection algorithm for pressure signals. In: IEEE Transactions on Biomedical Engineering. 2005 ; Vol. 52, No. 10. pp. 1662-1670.
@article{4828e130518f4aa7a2f13c5630f5bed3,
title = "An automatic beat detection algorithm for pressure signals",
abstract = "Beat detection algorithms have many clinical applications including pulse oximetry, cardiac arrhythmia detection, and cardiac output monitoring. Most of these algorithms have been developed by medical device companies and are proprietary. Thus, researchers who wish to investigate pulse contour analysis must rely on manual annotations or develop their own algorithms. We designed an automatic detection algorithm for pressure signals that locates the first peak following each heart beat. This is called the percussion peak in intracranial pressure (ICP) signals and the systolic peak in arterial blood pressure (ABP) and pulse oximetry (SpO 2) signals. The algorithm incorporates a filter bank with variable cutoff frequencies, spectral estimates of the heart rate, rank-order nonlinear filters, and decision logic. We prospectively measured the performance of the algorithm compared to expert annotations of ICP, ABP, and SpO 2 signals acquired from pediatric intensive care unit patients. The algorithm achieved a sensitivity of 99.36{\%} and positive predictivity of 98.43{\%} on a dataset consisting of 42,539 beats.",
keywords = "Arterial blood pressure (ABP), Component detection, Intracranial pressure (ICP), Pressure beat detection, Pulse contour analysis, Pulse oximetry (SpO )",
author = "Mateo Aboy and James McNames and Tran Thong and Daniel Tsunami and Miles Ellenby and Brahm Goldstein",
year = "2005",
month = "10",
doi = "10.1109/TBME.2005.855725",
language = "English (US)",
volume = "52",
pages = "1662--1670",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "10",

}

TY - JOUR

T1 - An automatic beat detection algorithm for pressure signals

AU - Aboy, Mateo

AU - McNames, James

AU - Thong, Tran

AU - Tsunami, Daniel

AU - Ellenby, Miles

AU - Goldstein, Brahm

PY - 2005/10

Y1 - 2005/10

N2 - Beat detection algorithms have many clinical applications including pulse oximetry, cardiac arrhythmia detection, and cardiac output monitoring. Most of these algorithms have been developed by medical device companies and are proprietary. Thus, researchers who wish to investigate pulse contour analysis must rely on manual annotations or develop their own algorithms. We designed an automatic detection algorithm for pressure signals that locates the first peak following each heart beat. This is called the percussion peak in intracranial pressure (ICP) signals and the systolic peak in arterial blood pressure (ABP) and pulse oximetry (SpO 2) signals. The algorithm incorporates a filter bank with variable cutoff frequencies, spectral estimates of the heart rate, rank-order nonlinear filters, and decision logic. We prospectively measured the performance of the algorithm compared to expert annotations of ICP, ABP, and SpO 2 signals acquired from pediatric intensive care unit patients. The algorithm achieved a sensitivity of 99.36% and positive predictivity of 98.43% on a dataset consisting of 42,539 beats.

AB - Beat detection algorithms have many clinical applications including pulse oximetry, cardiac arrhythmia detection, and cardiac output monitoring. Most of these algorithms have been developed by medical device companies and are proprietary. Thus, researchers who wish to investigate pulse contour analysis must rely on manual annotations or develop their own algorithms. We designed an automatic detection algorithm for pressure signals that locates the first peak following each heart beat. This is called the percussion peak in intracranial pressure (ICP) signals and the systolic peak in arterial blood pressure (ABP) and pulse oximetry (SpO 2) signals. The algorithm incorporates a filter bank with variable cutoff frequencies, spectral estimates of the heart rate, rank-order nonlinear filters, and decision logic. We prospectively measured the performance of the algorithm compared to expert annotations of ICP, ABP, and SpO 2 signals acquired from pediatric intensive care unit patients. The algorithm achieved a sensitivity of 99.36% and positive predictivity of 98.43% on a dataset consisting of 42,539 beats.

KW - Arterial blood pressure (ABP)

KW - Component detection

KW - Intracranial pressure (ICP)

KW - Pressure beat detection

KW - Pulse contour analysis

KW - Pulse oximetry (SpO )

UR - http://www.scopus.com/inward/record.url?scp=26444594252&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=26444594252&partnerID=8YFLogxK

U2 - 10.1109/TBME.2005.855725

DO - 10.1109/TBME.2005.855725

M3 - Article

VL - 52

SP - 1662

EP - 1670

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 10

ER -