TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Detection of atrial fibrillation in ECG hand-held devices using a random forest classifier

Tutkimustuotosvertaisarvioitu

Standard

Detection of atrial fibrillation in ECG hand-held devices using a random forest classifier. / Zabihi, Morteza; Rad, Ali Bahrami; Katsaggelos, Aggelos K.; Kiranyaz, Serkan; Narkilahti, Susanna; Gabbouj, Moncef.

Computing in Cardiology 2017. Vuosikerta 44 2017. s. 1-4 (Computing in Cardiology).

Tutkimustuotosvertaisarvioitu

Harvard

Zabihi, M, Rad, AB, Katsaggelos, AK, Kiranyaz, S, Narkilahti, S & Gabbouj, M 2017, Detection of atrial fibrillation in ECG hand-held devices using a random forest classifier. julkaisussa Computing in Cardiology 2017. Vuosikerta. 44, Computing in Cardiology, Sivut 1-4, COMPUTING IN CARDIOLOGY CONFERENCE, 1/01/00. https://doi.org/10.22489/CinC.2017.069-336

APA

Zabihi, M., Rad, A. B., Katsaggelos, A. K., Kiranyaz, S., Narkilahti, S., & Gabbouj, M. (2017). Detection of atrial fibrillation in ECG hand-held devices using a random forest classifier. teoksessa Computing in Cardiology 2017 (Vuosikerta 44, Sivut 1-4). (Computing in Cardiology). https://doi.org/10.22489/CinC.2017.069-336

Vancouver

Zabihi M, Rad AB, Katsaggelos AK, Kiranyaz S, Narkilahti S, Gabbouj M. Detection of atrial fibrillation in ECG hand-held devices using a random forest classifier. julkaisussa Computing in Cardiology 2017. Vuosikerta 44. 2017. s. 1-4. (Computing in Cardiology). https://doi.org/10.22489/CinC.2017.069-336

Author

Zabihi, Morteza ; Rad, Ali Bahrami ; Katsaggelos, Aggelos K. ; Kiranyaz, Serkan ; Narkilahti, Susanna ; Gabbouj, Moncef. / Detection of atrial fibrillation in ECG hand-held devices using a random forest classifier. Computing in Cardiology 2017. Vuosikerta 44 2017. Sivut 1-4 (Computing in Cardiology).

Bibtex - Lataa

@inproceedings{fc30b9bb81a24f39bdaff17263f1421c,
title = "Detection of atrial fibrillation in ECG hand-held devices using a random forest classifier",
abstract = "Atrial Fibrillation (AF) is characterized by chaotic electrical impulses in the atria, which leads to irregular heartbeats and can develop blood clots and stroke. Therefore, early detection of AF is crucial for increasing the success rate of the treatment. This study is focused on detection of AF rhythm using hand-held ECG monitoring devices, in addition to three other classes: normal or sinus rhythm, other rhythms, and too noisy to analyze. The pipeline of the proposed method consists of three major components: preprocessing and feature extraction, feature selection, and classification. In total, 491 hand-crafted features are extracted. Then, 150 features are selected in a feature ranking procedure. The selected features are from time, frequency, time-frequency domains, and phase space reconstruction of the ECG signals. In the final stage, a random forest classifier is used to classify the selected features into one of the four aforementioned ECG classes. Using the scoring mechanism provided by PhysioNet/Computing in Cardiology (CinC) Challenge 2017, the overall score (mean±std) of 81.9±2.6{\%} is achieved over the training dataset in 10-fold cross-validation. The proposed algorithm tied for the first place in the PhysioNet/CinC Challenge 2017 with an overall score of 82.6{\%} (rounded to 83{\%}) on the unseen test dataset.",
author = "Morteza Zabihi and Rad, {Ali Bahrami} and Katsaggelos, {Aggelos K.} and Serkan Kiranyaz and Susanna Narkilahti and Moncef Gabbouj",
note = "EXT={"}Kiranyaz, Serkan{"}",
year = "2017",
doi = "10.22489/CinC.2017.069-336",
language = "English",
volume = "44",
series = "Computing in Cardiology",
pages = "1--4",
booktitle = "Computing in Cardiology 2017",

}

RIS (suitable for import to EndNote) - Lataa

TY - GEN

T1 - Detection of atrial fibrillation in ECG hand-held devices using a random forest classifier

AU - Zabihi, Morteza

AU - Rad, Ali Bahrami

AU - Katsaggelos, Aggelos K.

AU - Kiranyaz, Serkan

AU - Narkilahti, Susanna

AU - Gabbouj, Moncef

N1 - EXT="Kiranyaz, Serkan"

PY - 2017

Y1 - 2017

N2 - Atrial Fibrillation (AF) is characterized by chaotic electrical impulses in the atria, which leads to irregular heartbeats and can develop blood clots and stroke. Therefore, early detection of AF is crucial for increasing the success rate of the treatment. This study is focused on detection of AF rhythm using hand-held ECG monitoring devices, in addition to three other classes: normal or sinus rhythm, other rhythms, and too noisy to analyze. The pipeline of the proposed method consists of three major components: preprocessing and feature extraction, feature selection, and classification. In total, 491 hand-crafted features are extracted. Then, 150 features are selected in a feature ranking procedure. The selected features are from time, frequency, time-frequency domains, and phase space reconstruction of the ECG signals. In the final stage, a random forest classifier is used to classify the selected features into one of the four aforementioned ECG classes. Using the scoring mechanism provided by PhysioNet/Computing in Cardiology (CinC) Challenge 2017, the overall score (mean±std) of 81.9±2.6% is achieved over the training dataset in 10-fold cross-validation. The proposed algorithm tied for the first place in the PhysioNet/CinC Challenge 2017 with an overall score of 82.6% (rounded to 83%) on the unseen test dataset.

AB - Atrial Fibrillation (AF) is characterized by chaotic electrical impulses in the atria, which leads to irregular heartbeats and can develop blood clots and stroke. Therefore, early detection of AF is crucial for increasing the success rate of the treatment. This study is focused on detection of AF rhythm using hand-held ECG monitoring devices, in addition to three other classes: normal or sinus rhythm, other rhythms, and too noisy to analyze. The pipeline of the proposed method consists of three major components: preprocessing and feature extraction, feature selection, and classification. In total, 491 hand-crafted features are extracted. Then, 150 features are selected in a feature ranking procedure. The selected features are from time, frequency, time-frequency domains, and phase space reconstruction of the ECG signals. In the final stage, a random forest classifier is used to classify the selected features into one of the four aforementioned ECG classes. Using the scoring mechanism provided by PhysioNet/Computing in Cardiology (CinC) Challenge 2017, the overall score (mean±std) of 81.9±2.6% is achieved over the training dataset in 10-fold cross-validation. The proposed algorithm tied for the first place in the PhysioNet/CinC Challenge 2017 with an overall score of 82.6% (rounded to 83%) on the unseen test dataset.

U2 - 10.22489/CinC.2017.069-336

DO - 10.22489/CinC.2017.069-336

M3 - Conference contribution

VL - 44

T3 - Computing in Cardiology

SP - 1

EP - 4

BT - Computing in Cardiology 2017

ER -