Artificial intelligence classification methods of atrial fibrillation with implementation technology

Figures & data

Figure 1. ECG for normal heart condition and AFIB [11].

Table 1. Parameters of time domain analysis.

Index	Definition
AVNN	Average of NN intervals
SDNN	Standard deviation of the NN intervals
SDANN	Standard deviation of the average of NN intervals
RMSSD	Root Mean Square Standard Deviation
NN50	Number of pairs of successive NNs that differ by more than 50ms
pNN50	Proportion of NN50 divided by total number of NNs.
TINN	Triangular interpolation of NN interval histogram

Table 2. Parameters of frequency domain analysis.

Index	Frequency of power spectrum/definition
ULF	0 and 0.0033 Hz
VLF	0.0033 and 0.04 Hz
LF	0.04 and 0.15 Hz
HF	0.15 and 0.40 Hz
LF/HF ratio	Ratio of low- to high-frequency power

Figure 2. Simple example for kNN classification [19].

Figure 3. ANN layers [24].

Table 3. Related work of AFIB detection with implementation platform.

Years	Journals	Platforms	ECG sensor	Arrhythmia class	Features	Classification AFIB	Performance (%)
							Sen	Spec	Acc
2014	Jeon et al. [34]	ARM processor	√	AFIB, MI	RR intervals	SVM	95.10	95.90	—
2013	Chong et al. [40]	Smart phone	Pulsatile	AFIB, PVC, PAC	RR intervals	Decision rule	96.84	97.83	—
2013	Kwon et al. [41]	Smart phone	√	AFIB	ECG morphological, FFT	SVM	—	—	87.50
2013	Oster et al. [42]	Smart phone	√	AFIB	RR intervals	Decision rule	92.70	94.20	—
2011	Bruser et al. [35]	Matlab	Ballistocardiogram	AFIB	PSD	SVM	96.20	91.90	95.10
2010	Kaiser et al. [43]	Smart phone	X	AFIB	RR intervals	Decision rule	99.10	88.30	—

Table 4. Related work of AFIB detection algorithm using SVM classifier.

			Performance (%)
Years	Journals	Features extraction	Sensitivity	Specificity	Accuracy
2015	Asgari et al. [33]	Peak to average power ratio log energy entropy	97.00	97.10	—
2015	Ortigos et al. [38]	Modulus and phase	—	—	81.00
2015	Padmavathi and Ramakrishna [21]	Burg method	—	—	100.00
2014	Jeon et al. [34]	RR intervals with Pointcare plot	95.10	95.90	—
2013	Colloca et al. [37]	R peak	100.00	82.00	85.45
2009	Park et al. [36]	RR intervals with Pointcare plot	91.40	92.90	—

Table 5. Related work of AFIB detection algorithm using ANN classifier.

			Performance (%)
Years	Journals	Features extraction	Sensitivity	Specificity	Accuracy
2013	Prasad et al. [23]	Higher order spectra	99.60	99.22	98.87
2009	Kikilus et al. [29]	HRV analysis	92.31	98.36	—
2008	Pourbabaee and Lucas [17]	PQRST wave Power spectral density	—	—	87.50
2007	Chesnokov et al. [28]	FFT HRV analysis	94.50	96.50	—
2007	Kostka and Tkacz [30]	P wave Energy and entropy	88.00	85.00	—
1994	Yang et al. [27]	P wave PR wave	92.00	92.30	—

Table 6. Related work of AFIB detection algorithm using kNN classifier.

			Performance (%)
Years	Journals	Features extraction	Sensitivity	Specificity	Accuracy
2015	Padmavathi and Ramakrishna [21]	Burg method	—	—	100.00
2013	Prasad et al. [23]	Higher order spectra	100.00	99.22	99.50
2008	Pourbabaee and Lucas [17]	PQRST wave	—	—	93.75
2004	Ros et al. [22]	P wave	84.00	76.00	—

Table 7. Related work of AFIB detection algorithm using LDA classifier.

			Performance (%)
Years	Journals	Features extraction	Sensitivity	Specificity	Accuracy
2007	Sovilj et al. [44]	P wave RR intervals	42.00	90.00	—
2002	Blanc [45]	Hidden Markov Model	70.00	65.00	—
2001	Lepage et al. [46]	Hidden Markov Model	70.00	65.00	—

Table 8. Related work of AFIB detection algorithm using NBC classifier.

			Performance (%)
Years	Journals	Features extraction	Sensitivity	Specificity	Accuracy
2013	Joy et al. [18]	QRS complexes	99.32	99.33	99.33
2008	Pourbabaee and Lucas [17]	PQRST wave Power spectral density	—	—	75.00

Malmivuo J. The basis of ECG diagnosis. Bioelectromagnetism. 1995;91;1–23.

 Google Scholar

Cunningham P, Delany SJ. k-Nearest neighbour classifiers. Multiple Classifier Syst. 2007;34:1–17.

 Google Scholar

Acharya R, Kumar A, Bhat PS, et al. Classification of cardiac abnormalities using heart rate signals: a comparative study. Med Biol Eng Comput. 2004;42:288–293.

 PubMed Web of Science ®Google Scholar

Jeon T, Kim B, Jeon M, et al. Implementation of a portable device for real-time ECG signal analysis. Biomed Eng Online [Internet]. 2014;13:160. Available from: http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=4273439&tool=pmcentrez&rendertype=abstract.

 PubMed Web of Science ®Google Scholar

Chong JW, McManus DD, Chon KH. Arrhythmia discrimination using a smart phone. 2013 IEEE International Conference on Body Sensor Networks, Vol. 19; 2013. p. 1–4.

 Google Scholar

Kwon K, Hwang H, Kang H, et al. A remote cardiac monitoring system for preventive care. 2013 IEEE International Conference on Consumer Electronics (ICCE); 2013. p. 197–200.

 Google Scholar

Oster J, Behar J, Colloca R, et al. Open source Java-based ECG analysis software and Android app for atrial fibrillation screening. Comput Cardiol. 2013;40:731–734.

 Google Scholar

Bruser C, Zink MDH, Winter S, et al. A feasibility study on the automatic detection of atrial fibrillation using an unobtrusive bed-mounted sensor. Comput Cardiol (CinC). 2011;18:13–16.

 Google Scholar

Kaiser S, Kirst M, Kunze C. Automatic detection of atrial fibrillation for mobile devices. International Joint Conference on Biomedical Engineering Systems and Technologies; 2009. p. 258–270.

 Google Scholar

Asgari S, Mehrnia A, Moussavi M. Automatic detection of atrial fibrillation using stationary wavelet transform and support vector machine. Comput Biol Med [Internet]. 2015;60:132–142. Available from: http://www.sciencedirect.com/science/article/pii/S0010482515000839.

 PubMed Web of Science ®Google Scholar

Ortigosa N, Fernández C, Galbis A, et al. Phase information of time–frequency transforms as a key feature for classification of atrial fibrillation episodes. Physiol Meas. 2015;36:409–424.

 PubMed Web of Science ®Google Scholar

Padmavathi K, Ramakrishna KS, Classification of ECG signal during Atrial Fibrillation using Autoregressive modeling. International Conference on Information and Communication Technologies, Vol. 46; 2015. p. 53–59.

 Google Scholar

Colloca R, Johnson AEW, Mainardi L, et al. A support vector machine approach for reliable detection of atrial fibrillation events. Comput Cardiol. 2013;40:1047–1050.

 Google Scholar

Park J, Lee S, Jeon M. Atrial fibrillation detection by heart rate variability in Poincare plot. Biomed Eng Online. 2009;8:38.

 PubMed Web of Science ®Google Scholar

Prasad H, Martis RJ, Acharya UR, et al. Application of higher order spectra for accurate delineation of atrial arrhythmia. Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. 2013. p. 57–60.

 Google Scholar

Kikillus N, Schweikert M, Bolz A. Identifying patients suffering from atrial fibrillation during atrial fibrillation and non-atrial fibrillation episodes. Int Fed Med Biol Eng. 2008;22:1349–1352.

 Google Scholar

Pourbabaee B, Lucas C. Automatic detection and prediction of paroxysmal atrial fibrillation based on analyzing ECG signal feature. IEEE Eng Med Biol. 2008;8:3–6.

 Google Scholar

Chesnokov YV, Holden AV, Zhang H, Screening patients with paroxysmal atrial fibrillation (PAF) from non-PAF heart rhythm using HRV data analysis. Comput Cardiol. 2007;34:459–462.

 Google Scholar

Kostka P, Tkacz E. Hybrid feature vector creation for atrial fibrillation detection improvement. Energy. 2007;14:922–925.

 Google Scholar

Yang TF, Devine B, Macfarlane P. Artificial neural networks for the diagnosis of atrial fibrillation. Med Biol Eng Comput [Internet]. 1994;32:615–619. Available from: http://www.springerlink.com/index/9V37872MR4J68T22.pdf.

 PubMed Web of Science ®Google Scholar

Ros E, Mota S, Fernández FJ, et al. ECG characterization of paroxysmal atrial fibrillation: parameter extraction and automatic diagnosis algorithm. Comput Biol Med. 2004;34:679–696.

 PubMed Web of Science ®Google Scholar

Sovilj S, Magjarevi R, Rajsman G. Classification methods for atrial fibrillation prediction after CABG. 11th Mediterranean Conference on Medical and Biomedical Engineering and Computing 2007, Vol. 16; 2007. p. 46–49.

 Google Scholar

Blanc J. Automatic P-wave analysis of patients prone to atrial fibrillation. Med Biol Eng. 2002;40:63–71.

 Google Scholar

Lepage R, Boucher J-M, Blanc J-J, et al. ECG segmentation and P-wave feature extraction: application to patients prone to atrial fibrillation. 2001 Conference Proceedings of the 23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Vol. 1; 2001. p. 298–301.

 Google Scholar

Joy R, Acharya UR, Prasad H, et al. Automated detection of atrial fibrillation using Bayesian paradigm. Knowledge-Based Syst [Internet] 2013;54:269–275. Available from: http://dx.doi.org/10.1016/j.knosys.2013.09.016.

 Web of Science ®Google Scholar