TY - JOUR
T1 - Rhythm and Quality Classification from Short ECGs Recorded Using a Mobile Device
AU - Behar, Joachim A.
AU - Rosenberg, Aviv A.
AU - Yaniv, Yael
AU - Oster, Julien
N1 - Publisher Copyright:
© 2017 IEEE Computer Society. All rights reserved.
PY - 2017
Y1 - 2017
N2 - Introduction: Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia. Its prevalence is 1-2% of the general population and it is associated with increased risk of mortality and morbidity. Methods: The AliveCor mobile electrocardiogram (ECG) device was used to collect data. The Physionet Challenge aimed to create an intelligent algorithm for automated rhythm and quality classification. A database of 8528 single lead ECG was used for training and a closed database of 3658 ECG recordings was used for testing the participants algorithms on the Challenge server. The RR interval time-series was first estimated using a R-peak detector. Signal quality was estimated on a second-by-second basis and the continuous sub-segment with the highest quality was selected for further analysis. A number of features were estimated: heart rate variability (time domain based, fragmentation, coefficient of sample entropy etc.), ECG morphology (QRS length, QT interval etc.) and the presence of ectopic beats. The features were used to train support vector machine classifiers in a one-vs.-rest approach. Results: For the final score of the challenge we obtained an overall F1 measure on the test set of 0.80. Conclusion: The feature based machine learning approach showed high performance in distinguishing between the different rhythms represented in the Challenge. This opens the horizon for computer automated interpretation of single lead mobile ECG.
AB - Introduction: Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia. Its prevalence is 1-2% of the general population and it is associated with increased risk of mortality and morbidity. Methods: The AliveCor mobile electrocardiogram (ECG) device was used to collect data. The Physionet Challenge aimed to create an intelligent algorithm for automated rhythm and quality classification. A database of 8528 single lead ECG was used for training and a closed database of 3658 ECG recordings was used for testing the participants algorithms on the Challenge server. The RR interval time-series was first estimated using a R-peak detector. Signal quality was estimated on a second-by-second basis and the continuous sub-segment with the highest quality was selected for further analysis. A number of features were estimated: heart rate variability (time domain based, fragmentation, coefficient of sample entropy etc.), ECG morphology (QRS length, QT interval etc.) and the presence of ectopic beats. The features were used to train support vector machine classifiers in a one-vs.-rest approach. Results: For the final score of the challenge we obtained an overall F1 measure on the test set of 0.80. Conclusion: The feature based machine learning approach showed high performance in distinguishing between the different rhythms represented in the Challenge. This opens the horizon for computer automated interpretation of single lead mobile ECG.
UR - http://www.scopus.com/inward/record.url?scp=85045099483&partnerID=8YFLogxK
U2 - 10.22489/CinC.2017.165-056
DO - 10.22489/CinC.2017.165-056
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
SN - 2325-8861
VL - 44
SP - 1
EP - 4
JO - Computing in Cardiology
JF - Computing in Cardiology
T2 - 44th Computing in Cardiology Conference, CinC 2017
Y2 - 24 September 2017 through 27 September 2017
ER -