Spectro-Temporal ECG Analysis for Atrial Fibrillation Detection

Zheng Zhao; Simo Särkkä; Ali Bahrami Rad

doi:10.1109/MLSP.2018.8517085

Spectro-Temporal ECG Analysis for Atrial Fibrillation Detection

Zheng Zhao, Simo Särkkä, Ali Bahrami Rad

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

21 Citations (Scopus)

301 Downloads (Pure)

Abstract

This article is concerned with spectro-temporal (i.e., time varying spectrum) analysis of ECG signals for application in atrial fibrillation (AF) detection. We propose a Bayesian spectro-temporal representation of ECG signal using state-space model and Kalman filter. The 2D spectro-temporal data are then classified by a densely connected convolutional networks (DenseNet) into four different classes: AF, non-AF normal rhythms (Normal), non-AF abnormal rhythms (Others), and noisy segments (Noisy). The performance of the proposed algorithm is evaluated and scored with the PhysioNet/Computing in Cardiology (CinC) 2017 dataset. The experiment results shows that the proposed method achieves the overall F1 score of 80.2%, which is in line with the state-of-the-art algorithms. In addition, the proposed spectro-temporal estimation approach outperforms standard time-frequency analysis methods, that is, short-time Fourier transform, continuous wavelet transform, and autoregressive spectral estimation for AF detection.

Original language	English
Title of host publication	2018 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2018
Editors	Nelly Pustelnik, Zheng-Hua Tan, Zhanyu Ma, Jan Larsen
Publisher	IEEE
Number of pages	6
ISBN (Electronic)	978-1-5386-5477-4
DOIs	https://doi.org/10.1109/MLSP.2018.8517085
Publication status	Published - 2018
MoE publication type	A4 Article in a conference publication
Event	IEEE International Workshop on Machine Learning for Signal Processing - Aalborg, Denmark Duration: 17 Sept 2018 → 20 Sept 2018 Conference number: 28

Publication series

Name	IEEE International Workshop on Machine Learning for Signal Processing
Publisher	IEEE
ISSN (Print)	2161-0363
ISSN (Electronic)	2161-0371

Workshop

Workshop	IEEE International Workshop on Machine Learning for Signal Processing
Abbreviated title	MLSP
Country/Territory	Denmark
City	Aalborg
Period	17/09/2018 → 20/09/2018

Keywords

atrial fibrillation
deep learning
Kalman filter
state-space model
spectrogram estimation

Access to Document

10.1109/MLSP.2018.8517085

ELEC_Zhao_etal_Spectro-Temporal-ECG-Analysis_MLSP_2018Accepted author manuscript, 3.99 MB

OpenUrl availability

Full text

Robust Computational ECG Methods for Automated Diagnosis of Cardiac Diseases from Long-Term Recordings
Palva, L., Suotsalo, K., Särkkä, S., Bahrami Rad, A., Hostettler, R., Tronarp, F., Sarmavuori, J., Zhao, Z. & Karvonen, T.
01/06/2016 → 31/12/2018
Project: Business Finland: Other research funding

Science-IT
Mikko Hakala (Manager)
School of Science
Facility/equipment: Facility

Cite this

Zhao, Z., Särkkä, S., & Bahrami Rad, A. (2018). Spectro-Temporal ECG Analysis for Atrial Fibrillation Detection. In N. Pustelnik, Z-H. Tan, Z. Ma, & J. Larsen (Eds.), 2018 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2018 (IEEE International Workshop on Machine Learning for Signal Processing). IEEE. https://doi.org/10.1109/MLSP.2018.8517085

@inproceedings{1f9fec415ee74520b8d8a6ab103fd94d,

title = "Spectro-Temporal ECG Analysis for Atrial Fibrillation Detection",

abstract = "This article is concerned with spectro-temporal (i.e., time varying spectrum) analysis of ECG signals for application in atrial fibrillation (AF) detection. We propose a Bayesian spectro-temporal representation of ECG signal using state-space model and Kalman filter. The 2D spectro-temporal data are then classified by a densely connected convolutional networks (DenseNet) into four different classes: AF, non-AF normal rhythms (Normal), non-AF abnormal rhythms (Others), and noisy segments (Noisy). The performance of the proposed algorithm is evaluated and scored with the PhysioNet/Computing in Cardiology (CinC) 2017 dataset. The experiment results shows that the proposed method achieves the overall F1 score of 80.2%, which is in line with the state-of-the-art algorithms. In addition, the proposed spectro-temporal estimation approach outperforms standard time-frequency analysis methods, that is, short-time Fourier transform, continuous wavelet transform, and autoregressive spectral estimation for AF detection.",

keywords = "atrial fibrillation, deep learning, Kalman filter, state-space model, spectrogram estimation",

author = "Zheng Zhao and Simo S{\"a}rkk{\"a} and {Bahrami Rad}, Ali",

year = "2018",

doi = "10.1109/MLSP.2018.8517085",

language = "English",

series = "IEEE International Workshop on Machine Learning for Signal Processing",

publisher = "IEEE",

editor = "Nelly Pustelnik and Zheng-Hua Tan and Zhanyu Ma and Larsen, {Jan }",

booktitle = "2018 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2018",

address = "United States",

note = "IEEE International Workshop on Machine Learning for Signal Processing, MLSP ; Conference date: 17-09-2018 Through 20-09-2018",

}

Zhao, Z, Särkkä, S & Bahrami Rad, A 2018, Spectro-Temporal ECG Analysis for Atrial Fibrillation Detection. in N Pustelnik, Z-H Tan, Z Ma & J Larsen (eds), 2018 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2018. IEEE International Workshop on Machine Learning for Signal Processing, IEEE, IEEE International Workshop on Machine Learning for Signal Processing, Aalborg, Denmark, 17/09/2018. https://doi.org/10.1109/MLSP.2018.8517085

Spectro-Temporal ECG Analysis for Atrial Fibrillation Detection. / Zhao, Zheng; Särkkä, Simo; Bahrami Rad, Ali.
2018 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2018. ed. / Nelly Pustelnik; Zheng-Hua Tan; Zhanyu Ma; Jan Larsen. IEEE, 2018. (IEEE International Workshop on Machine Learning for Signal Processing).

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

TY - GEN

T1 - Spectro-Temporal ECG Analysis for Atrial Fibrillation Detection

AU - Zhao, Zheng

AU - Särkkä, Simo

AU - Bahrami Rad, Ali

N1 - Conference code: 28

PY - 2018

Y1 - 2018

N2 - This article is concerned with spectro-temporal (i.e., time varying spectrum) analysis of ECG signals for application in atrial fibrillation (AF) detection. We propose a Bayesian spectro-temporal representation of ECG signal using state-space model and Kalman filter. The 2D spectro-temporal data are then classified by a densely connected convolutional networks (DenseNet) into four different classes: AF, non-AF normal rhythms (Normal), non-AF abnormal rhythms (Others), and noisy segments (Noisy). The performance of the proposed algorithm is evaluated and scored with the PhysioNet/Computing in Cardiology (CinC) 2017 dataset. The experiment results shows that the proposed method achieves the overall F1 score of 80.2%, which is in line with the state-of-the-art algorithms. In addition, the proposed spectro-temporal estimation approach outperforms standard time-frequency analysis methods, that is, short-time Fourier transform, continuous wavelet transform, and autoregressive spectral estimation for AF detection.

AB - This article is concerned with spectro-temporal (i.e., time varying spectrum) analysis of ECG signals for application in atrial fibrillation (AF) detection. We propose a Bayesian spectro-temporal representation of ECG signal using state-space model and Kalman filter. The 2D spectro-temporal data are then classified by a densely connected convolutional networks (DenseNet) into four different classes: AF, non-AF normal rhythms (Normal), non-AF abnormal rhythms (Others), and noisy segments (Noisy). The performance of the proposed algorithm is evaluated and scored with the PhysioNet/Computing in Cardiology (CinC) 2017 dataset. The experiment results shows that the proposed method achieves the overall F1 score of 80.2%, which is in line with the state-of-the-art algorithms. In addition, the proposed spectro-temporal estimation approach outperforms standard time-frequency analysis methods, that is, short-time Fourier transform, continuous wavelet transform, and autoregressive spectral estimation for AF detection.

KW - atrial fibrillation

KW - deep learning

KW - Kalman filter

KW - state-space model

KW - spectrogram estimation

U2 - 10.1109/MLSP.2018.8517085

DO - 10.1109/MLSP.2018.8517085

M3 - Conference contribution

T3 - IEEE International Workshop on Machine Learning for Signal Processing

BT - 2018 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2018

A2 - Pustelnik, Nelly

A2 - Tan, Zheng-Hua

A2 - Ma, Zhanyu

A2 - Larsen, Jan

PB - IEEE

T2 - IEEE International Workshop on Machine Learning for Signal Processing

Y2 - 17 September 2018 through 20 September 2018

ER -

Spectro-Temporal ECG Analysis for Atrial Fibrillation Detection

Abstract

Publication series

Workshop

Keywords

Access to Document

OpenUrl availability

Fingerprint

Projects

Robust Computational ECG Methods for Automated Diagnosis of Cardiac Diseases from Long-Term Recordings

Equipment

Science-IT

Cite this