A machine learning approach to objective cardiac event detection

N. Twomey; P. A. Flach

doi:10.1109/CISIS.2014.75

A machine learning approach to objective cardiac event detection

N. Twomey^*, P. A. Flach

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

2 Citations (Scopus)

359 Downloads (Pure)

Abstract

This paper presents an automated framework for the detection of the QRS complex from Electrocardiogram (ECG) signals. We introduce an artefact-tolerant pre-processing algorithm which emphasises a number of characteristics of the ECG that are representative of the QRS complex. With this processed ECG signal we train Logistic Regression and Support Vector Machine classification models. With our approach we obtain over 99.7% detection sensitivity and precision on the MIT-BIH database without using supplementary de-noising or pre-emphasis filters.

Original language	English
Title of host publication	2014 8th International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2014
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	519-524
Number of pages	6
ISBN (Print)	9781479943258
DOIs	https://doi.org/10.1109/CISIS.2014.75
Publication status	Published - 1 Jan 2014
Event	2014 8th International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2014 - Birmingham, United Kingdom Duration: 2 Jul 2014 → 4 Jul 2014

Conference

Conference	2014 8th International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2014
Country/Territory	United Kingdom
City	Birmingham
Period	2/07/14 → 4/07/14

Research Groups and Themes

Jean Golding
SPHERE

Keywords

Pattern recognition
QRS detection

Access to Document

10.1109/CISIS.2014.75

2014_iibm
This is the author accepted manuscript (AAM). The final published version (version of record) is available online via IEEE at 10.1109/CISIS.2014.75. Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 418 KB

Handle.net

Persistent link

Cite this

@inproceedings{322cc790bc9c4ce9a1d72e4d9d1c3e29,

title = "A machine learning approach to objective cardiac event detection",

abstract = "This paper presents an automated framework for the detection of the QRS complex from Electrocardiogram (ECG) signals. We introduce an artefact-tolerant pre-processing algorithm which emphasises a number of characteristics of the ECG that are representative of the QRS complex. With this processed ECG signal we train Logistic Regression and Support Vector Machine classification models. With our approach we obtain over 99.7% detection sensitivity and precision on the MIT-BIH database without using supplementary de-noising or pre-emphasis filters.",

keywords = "Pattern recognition, QRS detection",

author = "N. Twomey and Flach, {P. A.}",

year = "2014",

month = jan,

day = "1",

doi = "10.1109/CISIS.2014.75",

language = "English",

isbn = "9781479943258",

pages = "519--524",

booktitle = "2014 8th International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2014",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

note = "2014 8th International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2014 ; Conference date: 02-07-2014 Through 04-07-2014",

}

Twomey, N & Flach, PA 2014, A machine learning approach to objective cardiac event detection. in 2014 8th International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2014., 6915567, Institute of Electrical and Electronics Engineers (IEEE), pp. 519-524, 2014 8th International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2014, Birmingham, United Kingdom, 2/07/14. https://doi.org/10.1109/CISIS.2014.75

A machine learning approach to objective cardiac event detection. / Twomey, N.; Flach, P. A.
2014 8th International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2014. Institute of Electrical and Electronics Engineers (IEEE), 2014. p. 519-524 6915567.

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - A machine learning approach to objective cardiac event detection

AU - Twomey, N.

AU - Flach, P. A.

PY - 2014/1/1

Y1 - 2014/1/1

N2 - This paper presents an automated framework for the detection of the QRS complex from Electrocardiogram (ECG) signals. We introduce an artefact-tolerant pre-processing algorithm which emphasises a number of characteristics of the ECG that are representative of the QRS complex. With this processed ECG signal we train Logistic Regression and Support Vector Machine classification models. With our approach we obtain over 99.7% detection sensitivity and precision on the MIT-BIH database without using supplementary de-noising or pre-emphasis filters.

AB - This paper presents an automated framework for the detection of the QRS complex from Electrocardiogram (ECG) signals. We introduce an artefact-tolerant pre-processing algorithm which emphasises a number of characteristics of the ECG that are representative of the QRS complex. With this processed ECG signal we train Logistic Regression and Support Vector Machine classification models. With our approach we obtain over 99.7% detection sensitivity and precision on the MIT-BIH database without using supplementary de-noising or pre-emphasis filters.

KW - Pattern recognition

KW - QRS detection

UR - http://www.scopus.com/inward/record.url?scp=84908868678&partnerID=8YFLogxK

U2 - 10.1109/CISIS.2014.75

DO - 10.1109/CISIS.2014.75

M3 - Conference Contribution (Conference Proceeding)

AN - SCOPUS:84908868678

SN - 9781479943258

SP - 519

EP - 524

BT - 2014 8th International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2014

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 2014 8th International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2014

Y2 - 2 July 2014 through 4 July 2014

ER -

A machine learning approach to objective cardiac event detection

Abstract

Conference

Research Groups and Themes

Keywords

Access to Document

Handle.net

Other files and links

Fingerprint

SPHERE (EPSRC IRC)

Cite this

A machine learning approach to objective cardiac event detection

Abstract

Conference

Research Groups and Themes

Keywords

Access to Document

Handle.net

Other files and links

Fingerprint

Projects

SPHERE (EPSRC IRC)

Cite this