An algorithm for assessment of quality of ECGs acquired via mobile telephones

Philip Langley; Luigi Yuri  Di Marco; Susan  King; David Duncan; C. Di Maria; Wenfeng Duan; Marjan  Bojarnejad; D. Zheng; J. Allen; Alan Murray

An algorithm for assessment of quality of ECGs acquired via mobile telephones

Philip Langley, Luigi Yuri Di Marco, Susan King, David Duncan, C. Di Maria, Wenfeng Duan, Marjan Bojarnejad, D. Zheng, J. Allen, Alan Murray

Research output: Contribution to journal › Article › peer-review

41 Citations (Scopus)

Abstract

For the application of acquiring ECGs from mobile telephones by unskilled users it would be beneficial if the mobile device could assess ECG quality and inform the user if the quality was acceptable. Using the PhysioNet/Computing in Cardiology Challenge 2011 dataset we identified several ECG features that were commonly observed in the training set `unacceptable' category for algorithmic development: flat baseline (FB), saturation (SA), baseline drift (BD), low amplitude (LA), high amplitude (HA) and steep slope (SS). For the training set with each feature detection applied separately the following scores were achieved: FB 76.2%, SA 80.9%, BD 61.3%, LA 75.6%, HA 74.1% and SS 77.5%. With all features combined a score of 91.4% was achieved. For the test set the algorithm classified 181 records as unacceptable and 319 records as acceptable and the score was 85.7%.

Original language	English
Pages (from-to)	281-284
Number of pages	4
Journal	Computing in Cardiology
Volume	38
Publication status	Published - 2011
Externally published	Yes
Event	Computing in Cardiology Conference - Zhejiang University, Hangzhou, China Duration: 18 Sept 2011 → 21 Sept 2011

Access to Document

https://www.cinc.org/archives/2011/pdf/0281.pdf

Cite this

@article{a74b9a50980547839478ed98d94ca13e,

title = "An algorithm for assessment of quality of ECGs acquired via mobile telephones",

abstract = "For the application of acquiring ECGs from mobile telephones by unskilled users it would be beneficial if the mobile device could assess ECG quality and inform the user if the quality was acceptable. Using the PhysioNet/Computing in Cardiology Challenge 2011 dataset we identified several ECG features that were commonly observed in the training set `unacceptable' category for algorithmic development: flat baseline (FB), saturation (SA), baseline drift (BD), low amplitude (LA), high amplitude (HA) and steep slope (SS). For the training set with each feature detection applied separately the following scores were achieved: FB 76.2%, SA 80.9%, BD 61.3%, LA 75.6%, HA 74.1% and SS 77.5%. With all features combined a score of 91.4% was achieved. For the test set the algorithm classified 181 records as unacceptable and 319 records as acceptable and the score was 85.7%.",

author = "Philip Langley and {Di Marco}, {Luigi Yuri} and Susan King and David Duncan and {Di Maria}, C. and Wenfeng Duan and Marjan Bojarnejad and D. Zheng and J. Allen and Alan Murray",

year = "2011",

language = "English",

volume = "38",

pages = "281--284",

journal = "Computing in Cardiology",

issn = "2325-887X",

publisher = "IEEE Computer Society",

note = "Computing in Cardiology Conference ; Conference date: 18-09-2011 Through 21-09-2011",

}

TY - JOUR

T1 - An algorithm for assessment of quality of ECGs acquired via mobile telephones

AU - Langley, Philip

AU - Di Marco, Luigi Yuri

AU - King, Susan

AU - Duncan, David

AU - Di Maria, C.

AU - Duan, Wenfeng

AU - Bojarnejad, Marjan

AU - Zheng, D.

AU - Allen, J.

AU - Murray, Alan

PY - 2011

Y1 - 2011

N2 - For the application of acquiring ECGs from mobile telephones by unskilled users it would be beneficial if the mobile device could assess ECG quality and inform the user if the quality was acceptable. Using the PhysioNet/Computing in Cardiology Challenge 2011 dataset we identified several ECG features that were commonly observed in the training set `unacceptable' category for algorithmic development: flat baseline (FB), saturation (SA), baseline drift (BD), low amplitude (LA), high amplitude (HA) and steep slope (SS). For the training set with each feature detection applied separately the following scores were achieved: FB 76.2%, SA 80.9%, BD 61.3%, LA 75.6%, HA 74.1% and SS 77.5%. With all features combined a score of 91.4% was achieved. For the test set the algorithm classified 181 records as unacceptable and 319 records as acceptable and the score was 85.7%.

AB - For the application of acquiring ECGs from mobile telephones by unskilled users it would be beneficial if the mobile device could assess ECG quality and inform the user if the quality was acceptable. Using the PhysioNet/Computing in Cardiology Challenge 2011 dataset we identified several ECG features that were commonly observed in the training set `unacceptable' category for algorithmic development: flat baseline (FB), saturation (SA), baseline drift (BD), low amplitude (LA), high amplitude (HA) and steep slope (SS). For the training set with each feature detection applied separately the following scores were achieved: FB 76.2%, SA 80.9%, BD 61.3%, LA 75.6%, HA 74.1% and SS 77.5%. With all features combined a score of 91.4% was achieved. For the test set the algorithm classified 181 records as unacceptable and 319 records as acceptable and the score was 85.7%.

M3 - Article

SN - 2325-887X

VL - 38

SP - 281

EP - 284

JO - Computing in Cardiology

JF - Computing in Cardiology

T2 - Computing in Cardiology Conference

Y2 - 18 September 2011 through 21 September 2011

ER -

An algorithm for assessment of quality of ECGs acquired via mobile telephones

Abstract

Access to Document

Fingerprint

Cite this