Predicting acute hypotensive episodes from mean arterial pressure

P. Langley; S.T.  King; D. Zheng; E.J. Bowers; K. Wang; J. Allen; A. Murray

Predicting acute hypotensive episodes from mean arterial pressure

P. Langley, S.T. King, D. Zheng, E.J. Bowers, K. Wang, J. Allen, A. Murray

Faculty Research Centre for Intelligent Healthcare

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding › peer-review

11 Citations (Scopus)

1 Downloads (Pure)

Abstract

Acute hypotensive episodes (AHE) are serious clinical events in intensive care units. We present an algorithm for automated computer prediction of AHE in patients using mean arterial pressure (MAP). We defined an AHE index based on the observation that patients with documented AHE experienced more transient reductions in MAP compared to those without AHE. The algorithm was developed and tested using the PhysioNet/Computers in Cardiology Challenge 2009 data sets. The algorithm, which classifies records with at least one occurrence of a reduction in MAP to 65 mmHg for at least 75% of a 30 minute window as AHE positive, correctly classified 8 out
of 10 records in test set A and 28/40 records in test set B.
Using MAP alone the algorithm achieved modest accuracy for prediction of AHE in patients. The algorithm could be improved by taking account of temporal changes in MAP.

Original language	English
Title of host publication	Computers in Cardiology
Pages	553−556
Number of pages	4
Volume	36
ISBN (Electronic)	978-1-4244-7282-6
Publication status	Published - 2009
Event	36th Annual Computers in Cardiology Conference - Park City, United States Duration: 13 Sep 2009 → 16 Sep 2009

Publication series

Name
ISSN (Print)	0276-6574

Conference

Conference	36th Annual Computers in Cardiology Conference
Country	United States
City	Park City
Period	13/09/09 → 16/09/09

Bibliographical note

Licensed under the Creative Commons Attribution
License 3.0 (CCAL).

Since volume 33 (2006), CinC has been an open-access publication, in which copyright in each article is held by its authors, who grant permission to copy and redistribute their work with attribution, under the terms of the Creative Commons Attribution License.

Access to Document

PublishedFinal published version, 474 KBLicence: CC BY

http://www.scopus.com/inward/record.url?eid=2-s2.0-77952677374&partnerID=MN8TOARS

Fingerprint Dive into the research topics of 'Predicting acute hypotensive episodes from mean arterial pressure'. Together they form a unique fingerprint.

Cite this

@inproceedings{2c3ddc8732bd4e599ef4d7f83c3e93ec,

title = "Predicting acute hypotensive episodes from mean arterial pressure",

abstract = "Acute hypotensive episodes (AHE) are serious clinical events in intensive care units. We present an algorithm for automated computer prediction of AHE in patients using mean arterial pressure (MAP). We defined an AHE index based on the observation that patients with documented AHE experienced more transient reductions in MAP compared to those without AHE. The algorithm was developed and tested using the PhysioNet/Computers in Cardiology Challenge 2009 data sets. The algorithm, which classifies records with at least one occurrence of a reduction in MAP to 65 mmHg for at least 75% of a 30 minute window as AHE positive, correctly classified 8 outof 10 records in test set A and 28/40 records in test set B.Using MAP alone the algorithm achieved modest accuracy for prediction of AHE in patients. The algorithm could be improved by taking account of temporal changes in MAP. ",

author = "P. Langley and S.T. King and D. Zheng and E.J. Bowers and K. Wang and J. Allen and A. Murray",

note = "Licensed under the Creative Commons Attribution License 3.0 (CCAL). Since volume 33 (2006), CinC has been an open-access publication, in which copyright in each article is held by its authors, who grant permission to copy and redistribute their work with attribution, under the terms of the Creative Commons Attribution License. ; 36th Annual Computers in Cardiology Conference ; Conference date: 13-09-2009 Through 16-09-2009",

year = "2009",

language = "English",

isbn = "978-1-4244-7281-9",

volume = "36",

pages = "553−556",

booktitle = "Computers in Cardiology",

}

TY - GEN

T1 - Predicting acute hypotensive episodes from mean arterial pressure

AU - Langley, P.

AU - King, S.T.

AU - Zheng, D.

AU - Bowers, E.J.

AU - Wang, K.

AU - Allen, J.

AU - Murray, A.

N1 - Licensed under the Creative Commons Attribution License 3.0 (CCAL). Since volume 33 (2006), CinC has been an open-access publication, in which copyright in each article is held by its authors, who grant permission to copy and redistribute their work with attribution, under the terms of the Creative Commons Attribution License.

PY - 2009

Y1 - 2009

N2 - Acute hypotensive episodes (AHE) are serious clinical events in intensive care units. We present an algorithm for automated computer prediction of AHE in patients using mean arterial pressure (MAP). We defined an AHE index based on the observation that patients with documented AHE experienced more transient reductions in MAP compared to those without AHE. The algorithm was developed and tested using the PhysioNet/Computers in Cardiology Challenge 2009 data sets. The algorithm, which classifies records with at least one occurrence of a reduction in MAP to 65 mmHg for at least 75% of a 30 minute window as AHE positive, correctly classified 8 outof 10 records in test set A and 28/40 records in test set B.Using MAP alone the algorithm achieved modest accuracy for prediction of AHE in patients. The algorithm could be improved by taking account of temporal changes in MAP.

AB - Acute hypotensive episodes (AHE) are serious clinical events in intensive care units. We present an algorithm for automated computer prediction of AHE in patients using mean arterial pressure (MAP). We defined an AHE index based on the observation that patients with documented AHE experienced more transient reductions in MAP compared to those without AHE. The algorithm was developed and tested using the PhysioNet/Computers in Cardiology Challenge 2009 data sets. The algorithm, which classifies records with at least one occurrence of a reduction in MAP to 65 mmHg for at least 75% of a 30 minute window as AHE positive, correctly classified 8 outof 10 records in test set A and 28/40 records in test set B.Using MAP alone the algorithm achieved modest accuracy for prediction of AHE in patients. The algorithm could be improved by taking account of temporal changes in MAP.

UR - http://www.scopus.com/inward/record.url?eid=2-s2.0-77952677374&partnerID=MN8TOARS

M3 - Conference proceeding

SN - 978-1-4244-7281-9

VL - 36

SP - 553−556

BT - Computers in Cardiology

T2 - 36th Annual Computers in Cardiology Conference

Y2 - 13 September 2009 through 16 September 2009

ER -