In this study, we aimed to detect paroxysmal atrial fibrillation episodes before they occur so that patients can take precautions before putting their and others’ lives in potentially life-threatening danger. We used the atrial fibrillation prediction database, open data from PhysioNet, and assembled our process based on convolutional neural networks. Conventional heart rate variability features are calculated from time-domain measures, frequency-domain measures using power spectral density estimations, time-frequency-domain measures using wavelet transform, and nonlinear Poincaré plot measures. In addition, we also applied an alternative heart rate normalization, which gave promising results only in a few studies, before calculating these heart rate variability features. We used these features directly and their normalized versions using min–max normalization and z-score normalization methods. Thus, heart rate variability features extracted from six different combinations of these normalizations, in addition to no normalization cases, were applied to the convolutional neural network classifier. We tuned the classifiers’ hyperparameters using 90% of feature sets and tested the classifiers’ performances using 10% of feature sets. The proposed approach resulted in 87.76% accuracy, 91.30% precision, 80.04% recall, and 87.50% f1-score in heart rate variability with z-score feature normalization. When the heart rate normalization was also utilized, the suggested method gave 100% accuracy, 100% precision, 100% recall, and 100% f1-score in heart rate variability with z-score feature normalization. The proposed method with heart rate normalization and z-score normalization methods resulted in better classification performance than similar studies in the literature. By comparing the existing studies, we conclude that our approach provides a much better tool to determine a near-future paroxysmal atrial fibrillation episode. However, although the achieved benchmarks are impressive, we note that the approach needs to be supported by other studies and on other datasets before clinical trials.
REFERENCES
1
K. M.
Ryder
and E. J.
Benjamin
, “Epidemiology and significance of atrial fibrillation
,” Am. J. Cardiol.
84
, 131
–138
(1999
). 2
X.
Du
, L.
Guo
, S.
Xia
, J.
Du
, C.
Anderson
, H.
Arima
, M.
Huffman
, Y.
Yuan
, Y.
Zheng
, S.
Wu
, X.
Guang
, X.
Zhou
, H.
Lin
, X.
Cheng
, J.
Dong
, and C.
Ma
, “Atrial fibrillation prevalence, awareness and management in a nationwide survey of adults in China
,” Heart
107
, 535
–541
(2021
). 3
G. B.
Moody
, 2001, PAF Prediction Challenge Database
, published in PhysioNet, Version: 1.0.0, 4
G.
Hindricks
, T.
Potpara
, N.
Dagres
, E.
Arbelo
, J. J.
Bax
, C.
Blomstrom-Lundqvist
, G.
Boriani
, M.
Castella
, G.-A.
Dan
, P. E.
Dilaveris
, L.
Fauchier
, G.
Filippatos
, J. M.
Kalman
, M.
La Meir
, D. A.
Lane
, J.-P.
Lebeau
, M.
Lettino
, G. Y. H.
Lip
, F. J.
Pinto
, G. N.
Thomas
, M.
Valgimigli
, I. C.
Van Gelder
, B. P.
Van Putte
, C. L.
Watkins
, and ESC Scientific Document Group
, “2020 ESC guidelines for the diagnosis and management of atrial fibrillation developed in collaboration with the European Association for Cardio-Thoracic Surgery (EACTS)
,” Eur. Heart J.
42
, 373
–498
(2020
). 5
M.
Mohebbi
and H.
Ghassemian
, “Prediction of paroxysmal atrial fibrillation based on non-linear analysis and spectrum and bispectrum features of the heart rate variability signal
,” Comput. Methods Programs Biomed.
105
, 40
–49
(2012
). 6
Y.
Isler
and M.
Kuntalp
, “Combining classical HRV indices with wavelet entropy measures improves to performance in diagnosing congestive heart failure
,” Comput. Biol. Med.
37
, 1502
–1510
(2007
). 7
A.
Soudani
and M.
Almusallam
, “Atrial fibrillation detection based on ECG-features extraction in WBSN
,” Procedia Comput. Sci.
130
, 472
–479
(2018
). 8
U. R.
Acharya
, H.
Fujita
, O. S.
Lih
, M.
Adam
, J. H.
Tan
, and C. K.
Chua
, “Automated detection of coronary artery disease using different durations of ECG segments with convolutional neural network
,” Knowl. Based Syst.
132
, 62
–71
(2017
). 9
H.
Guruler
, M.
Sahin
, and A.
Ferikoglu
, “Feature selection on single-lead ECG for obstructive sleep apnea diagnosis
,” Turk. J. Electr. Eng. Comput. Sci.
22
, 465
–478
(2014
). 10
Task Force of the European Society of Cardiology the North American Society of Pacing Electrophysiology
, “Heart rate variability
,” Circulation
93
, 1043
–1065
(1996
). 11
M. G.
Tsipouras
and D. I.
Fotiadis
, “Automatic arrhythmia detection based on time and time–frequency analysis of heart rate variability
,” Comput. Methods Programs Biomed.
74
, 95
–108
(2004
). 12
M.-Y.
Lee
and S.-N.
Yu
, “Multiscale sample entropy based on discrete wavelet transform for clinical heart rate variability recognition,” in 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE, 2012).13
J.
Park
, S.
Lee
, and M.
Jeon
, “Atrial fibrillation detection by heart rate variability in Poincaré plot
,” Biomed. Eng. Online
8
, 38
(2009
). 14
Y.
Isler
, “Discrimination of systolic and diastolic dysfunctions using multi-layer perceptron in heart rate variability analysis
,” Comput. Biol. Med.
76
, 113
–119
(2016
). 15
A.
Narin
, Y.
Isler
, M.
Ozer
, and M.
Perc
, “Early prediction of paroxysmal atrial fibrillation based on short-term heart rate variability
,” Physica A
509
, 56
–65
(2018
). 16
Y.
Isler
and M.
Kuntalp
, “Heart rate normalization in the analysis of heart rate variability in congestive heart failure
,” Proc. Inst. Mech. Eng., Part H: J. Eng. Med.
224
, 453
–463
(2009
). 17
C.
Maier
, M.
Bauch
, and H.
Dickhaus
, “Screening and prediction of paroxysmal atrial fibrillation by analysis of heart rate variability parameters,” in Computers in Cardiology 2001. Vol. 28 (Cat. No. 01CH37287) (IEEE, 2001).18
G.
Schreier
, P.
Kastner
, and W.
Marko
, “An automatic ECG processing algorithm to identify patients prone to paroxysmal atrial fibrillation,” in Computers in Cardiology 2001. Vol. 28 (Cat. No. 01CH37287) (IEEE, 2001).19
K. H.
Boon
, M.
Khalil-Hani
, M. B.
Malarvili
, and C. W.
Sia
, “Paroxysmal atrial fibrillation prediction method with shorter HRV sequences
,” Comput. Methods Programs Biomed.
134
, 187
–196
(2016
). 20
M.
Surucu
, Y.
Isler
, and R.
Kara
, “Investigation of the effect of normalization techniques on discriminating patients with paroxysmal atrial fibrillation,” in 2nd International Conference of Applied Sciences, Engineering and Mathematics (IBU-ICASEM 2020, Skopje/North Macedonia, 2020).21
T.
Thong
, J.
McNames
, M.
Aboy
, and B.
Goldstein
, “Prediction of paroxysmal atrial fibrillation by analysis of atrial premature complexes
,” IEEE Trans. Biomed. Eng.
51
, 561
–569
(2004
). 22
E.
Ros
, S.
Mota
, F. J.
Fernández
, F. J.
Toro
, and J. L.
Bernier
, “ECG characterization of paroxysmal atrial fibrillation: Parameter extraction and automatic diagnosis algorithm
,” Comput. Biol. Med.
34
, 679
–696
(2004
). 23
N.
Ozcan
and M.
Kuntalp
, “Determining best hrv indices for paf screening using genetic algorithm,” in 10th International Conference on Electrical and Electronics Engineering (ELECO) (ELECO, 2017), pp. 1385–1388.24
Y. V.
Chesnokov
, A. V.
Holden
, and H.
Zhang
, “Screening patients with paroxysmal atrial fibrillation (PAF) from non-PAF heart rhythm using HRV data analysis,” in 2007 Computers in Cardiology (IEEE, 2007).25
A.
Martínez
, R.
Alcaraz
, and J. J.
Rieta
, “Study on the p-wave feature time course as early predictors of paroxysmal atrial fibrillation
,” Physiol. Meas.
33
, 1959
–1974
(2012
). 26
B.
Pourbabaee
, M. J.
Roshtkhari
, and K.
Khorasani
, “Deep convolutional neural networks and learning ECG features for screening paroxysmal atrial fibrillation patients
,” IEEE Trans. Syst., Man, Cybern.: Syst.
48
, 2095
–2104
(2018
). 27
M.
Surucu
, Y.
Isler
, and R.
Kara
, “Diagnosis of paroxysmal atrial fibrillation from thirty-minute heart rate variability data using convolutional neural networks
,” Turk. J. Electr. Eng. Comput. Sci.
29
, 2986
–2900
(2021
). 28
K. S.
Lynn
and H. D.
Chiang
, “A two-stage solution algorithm for paroxysmal atrial fibrillation prediction,” in Computers in Cardiology 2001. Vol. 28 (Cat. No. 01CH37287) (IEEE, 2001).29
M.
Surucu
, Y.
Isler
, and R.
Kara
, “Heart rate normalization on determining a paroxysmal atrial fibrillation attack,” in 3rd International Conference of Applied Sciences, Engineering and Mathematics, IBU-ICASEM 2021, Skopje/North Macedonia (IBU, 2021).30
Y. V.
Chesnokov
, “Complexity and spectral analysis of the heart rate variability dynamics for distant prediction of paroxysmal atrial fibrillation with artificial intelligence methods
,” Artif. Intell. Med.
43
, 151
–165
(2008
). 31
K. H.
Boon
, M.
Khalil-Hani
, and M. B.
Malarvili
, “Paroxysmal atrial fibrillation prediction based on HRV analysis and non-dominated sorting genetic algorithm III
,” Comput. Methods Programs Biomed.
153
, 171
–184
(2018
). 32
K. H.
Boon
, M.
Khalil-Hani
, and C. W.
Sia
, “Paroxysmal atrial fibrillation onset prediction using heart rate variability analysis and genetic algorithm for optimization,” in Proceedings of the International Conference on Data Engineering 2015 (DaEng-2015) (Springer, Singapore, 2019), pp. 609–617.33
O.
Balli
and Y.
Kutlu
, “Effect of deep learning feature inference techniques on respiratory sounds
,” J. Intell. Syst. Appl.
3
, 134
–137
(2020
).34
Y.
Camgozlu
and Y.
Kutlu
, “Examining the difference between image size, background color, gray picture and color picture in leave classification with deep learning
,” J. Intell. Syst. Appl.
3
, 130
–133
(2020
).35
G.
Altan
, Y.
Kutlu
, A. O.
Pekmezci
, and S.
Nural
, “Deep learning with 3D-second order difference plot on respiratory sounds
,” Biomed. Signal Process. Control
45
, 58
–69
(2018
). 36
G.
Altan
, Y.
Kutlu
, and N.
Allahverdi
, “Deep learning on computerized analysis of chronic obstructive pulmonary disease
,” IEEE J. Biomed. Health Inform.
24
, 1344
–1350
(2020
). 37
G.
Moody
, A.
Goldberger
, S.
McClennen
, and S.
Swiryn
, “Predicting the onset of paroxysmal atrial fibrillation: The computers in cardiology challenge 2001,” in Computers in Cardiology 2001. Vol.28 (Cat. No. 01CH37287) (IEEE, 2001).38
R.
Seker
, S.
Saliu
, A.
Birand
, and G.
Kudaiberdieva
, “Validity test for a set of nonlinear measures for short data length with reference to short-term heart rate variability signal
,” J. Syst. Integr.
10
, 41
–53
(2000
). 39
J.
Pan
and W. J.
Tompkins
, “A real-time QRS detection algorithm
,” IEEE Trans. Biomed. Eng.
BME-32
, 230
–236
(1985
). 40
P.
Langley
, D.
di Bernardo
, J.
Allen
, E.
Bowers
, F. E.
Smith
, S.
Vecchietti
, and A.
Murray
, “Can paroxysmal atrial fibrillation be predicted?,” in Computers in Cardiology 2001. Vol. 28 (Cat. No. 01CH37287) (IEEE, 2001).41
A. P.
Hallstrom
, P. K.
Stein
, R.
Schneider
, M.
Hodges
, G.
Schmidt
, and K.
Ulm
, “Structural relationships between measures based on heart beat intervals: Potential for improved risk assessment
,” IEEE Trans. Biomed. Eng.
51
, 1414
–1420
(2004
). 42
G. G.
Berntson
, J. T.
Bigger
, Jr., D. L.
Eckberg
, P.
Grossman
, P. G.
Kaufmann
, M.
Malik
, H. N.
Nagaraja
, S. W.
Porges
, J. P.
Saul
, P. H.
Stone
, and M. W.
van der Molen
, “Heart rate variability: Origins, methods, and interpretive caveats
,” Psychophysiology
34
, 623
–648
(1997
). 43
G. D.
Clifford
and L.
Tarassenko
, “Quantifying errors in spectral estimates of HRV due to beat replacement and resampling
,” IEEE Trans. Biomed. Eng.
52
, 630
–638
(2005
). 44
G. D.
Clifford
, F.
Azuaje
, and P. E.
McSharry
, Advanced Methods and Tools for ECG Data Analysis
(Artech House, Inc.
, Norwood, MA
, 2006
).45
E. J. M.
Weber
, P. C. M.
Molenaar
, and M. W.
van der Molen
, “A nonstationarity test for the spectral analysis of physiological time series with an application to respiratory sinus arrhythmia
,” Psychophysiology
29
, 55
–62
(1992
). 46
M. P.
Tarvainen
, P. O.
Ranta-Aho
, and P. A.
Karjalainen
, “An advanced detrending method with application to HRV analysis
,” IEEE Trans. Biomed. Eng.
49
, 172
–175
(2002
). 47
R. O.
Duda
, P. E.
Hart
, and D. G.
Stork
, Pattern Classification
, 2nd ed. (Wiley
, New York
, 2001
).48
N. R.
Lomb
, “Least-squares frequency analysis of unequally spaced data
,” Astrophys. Space Sci.
39
, 447
–462
(1976
). 49
J. D.
Scargle
, “Studies in astronomical time series analysis. II. Statistical aspects of spectral analysis of unevenly spaced data
,” Astrophys. J.
263
, 835
(1982
). 50
P.
Laguna
, G. B.
Moody
, and R. G.
Mark
, “Power spectral density of unevenly sampled data by least-square analysis: Performance and application to heart rate signals
,” IEEE Trans. Biomed. Eng.
45
, 698
–715
(1998
). 51
P. W.
Kamen
and A. M.
Tonkin
, “Application of the Poincaré plot to heart rate variability: A new measure of functional status in heart failure
,” Aust. N. Z. J. Med.
25
, 18
–26
(1995
). 52
P. W.
Kamen
, H.
Krum
, and A. M.
Tonkin
, “Poincaré plot of heart rate variability allows quantitative display of parasympathetic nervous activity in humans
,” Clin. Sci.
91
, 201
–208
(1996
). 53
M.
Brennan
, M.
Palaniswami
, and P.
Kamen
, “Do existing measures of Poincaré plot geometry reflect nonlinear features of heart rate variability?
,” IEEE Trans. Biomed. Eng.
48
, 1342
–1347
(2001
). 54
F.
Marciano
, M. L.
Migaux
, D.
Acanfora
, G.
Furgi
, and F.
Rengo
, “Quantification of Poincaré maps for the evaluation of heart rate variability,” in Computers in Cardiology 1994 (IEEE Computer Society Press, 1994).55
R. Q.
Quiroga
, O. A.
Rosso
, E.
Basar
, and M.
Schurmann
, “Wavelet entropy in event-related potentials: A new method shows ordering of EEG oscillations
,” Biol. Cybern.
84
, 291
–299
(2001
). 56
E.
Sayilgan
, Y.
Yuce
, and Y.
Isler
, “Evaluation of wavelet features selected via statistical evidence from steady-state visually evoked potentials to predict the stimulating frequency
,” J. Fac. Eng. Archit. Gazi Univ.
36
, 593
(2021
). 57
E.
Sayilgan
, Y. K.
Yuce
, and Y.
Isler
, “Evaluation of mother wavelets on steady-state visually-evoked potentials for triple-command brain-computer interfaces
,” Turk. J. Electr. Eng. Comput. Sci.
29
, 2263
–2279
(2021
). 58
J.
Schmidhuber
, “Deep learning in neural networks: An overview
,” Neural Netw.
61
, 85
–117
(2015
). 59
Y.
LeCun
, Y.
Bengio
, and G.
Hinton
, “Deep learning
,” Nature
521
, 436
–444
(2015
). 60
Y.
Bengio
, A.
Courville
, and P.
Vincent
, “Representation learning: A review and new perspectives
,” IEEE Trans. Pattern Anal. Mach. Intell.
35
, 1798
–1828
(2013
). 61
N.
Srivastava
, G.
Hinton
, A.
Krizhevsky
, I.
Sutskever
, and R.
Salakhutdinov
, “Dropout: A simple way to prevent neural networks from overfitting
,” J. Mach. Learn. Res.
15
, 1929
–1958
(2014
).62
J.
Bergstra
and Y.
Bengio
, “Random search for hyper-parameter optimization
,” J. Mach. Learn. Res.
13
, 281
–305
(2012
).63
A. H.
Abdi
, C.
Luong
, T.
Tsang
, G.
Allan
, S.
Nouranian
, J.
Jue
, D.
Hawley
, S.
Fleming
, K.
Gin
, J.
Swift
, R.
Rohling
, and P.
Abolmaesumi
, “Automatic quality assessment of echocardiograms using convolutional neural networks: Feasibility on the apical four-chamber view
,” IEEE Trans. Med. Imaging
36
, 1221
–1230
(2017
). 64
Y.
Isler
, A.
Narin
, and M.
Ozer
, “Comparison of the effects of cross-validation methods on determining performances of classifiers used in diagnosing congestive heart failure
,” Meas. Sci. Rev.
15
, 196
–201
(2015
). 65
D.
Chicco
and G.
Jurman
, “The advantages of the Matthews correlation coefficient (MCC) over f1 score and accuracy in binary classification evaluation
,” BMC Genom.
21
, 6
(2020
). 66
W.
Zong
, R.
Mukkamala
, and R. G.
Mark
, “A methodology for predicting paroxysmal atrial fibrillation based on ECG arrhythmia feature analysis,” in Computers in Cardiology 2001. Vol. 28 (Cat. No. 01CH37287) (IEEE, 2001).67
H.
Costin
, C.
Rotariu
, and A.
Pasarica
, “Atrial fibrillation onset prediction using variability of ECG signals,” in 2013 8TH International Symposium on Advanced Topics in Electrical Engineering (ATEE) (IEEE, 2013).© 2021 Author(s). Published under an exclusive license by AIP Publishing.
2021
Author(s)
You do not currently have access to this content.
