本論文提出一種利用深度學習辨識器及影像特徵萃取技巧來處理心電訊號和手腕橈動脈脈音訊號時頻轉換的演算法，並應用於心律不整以及結構性心臟病的自動辨識。主要的研究目的包括：1) 探討深層(9層)以及淺層(4層)的深度學習辨識器卷積式類神經網路(convolutional neural networks, CNN)在自動辨識效果上的差異、2) 探討應用不同的影像特徵萃取技巧於心電訊號和手腕橈動脈脈音訊號轉換出的時頻圖辨識率差異、3) 探討單純使用卷積式類神經網路作為辨識器以及使用卷積式類神經網路（特徵擷取）並結合支持向量機辨識器對辨識正確率造成的差異。本論文所探討的演算法流程為：首先將心電訊號及手腕橈動脈上的脈音時域訊號經過連續小波轉換(continuous wavelet transfomation)產生時域訊號對應的時頻圖(Time-frequency spectrogram)。接著透過傳統影像處理的特徵萃取技巧，如主成分分析(principal componenet analysis, PCA)，Harris-Stephens特徵擷取演算法(Harris)，KAZE特徵擷取演算法，加速強健特徵擷取演算法(speeded-up robust features, SURF)，最大穩定極值區域特徵萃取演算法(maximum stable extreme region, MSER)。接著將有經過影像處理特徵萃取的時頻圖、以及原始的時頻圖作為特徵輸入到深層卷積式神經網路(convolutional neural networks)辨識器，最後使用k-fold交叉驗證來確認最終效果。本論文用於測試的心電圖資料來自麻省理工學院的Physionet開源心電圖資料庫、及成功大學附設醫院所收集的心臟病患者手腕橈動脈脈音訊號(pulse audiogram, PAG)。本論文以心電圖資料竇性心律(sinus ryhthm, SR)與心房早期收縮atrial premature contraction, APC)，心室早期收縮(ventricular premature contraction, VPC), 左束支傳導阻滯(left bundle branch block beat, LBBB)，和右束支傳導阻滯(right bundle branch block beat, RBBB)等疾病，每一個視窗包含一個完整的QRS複合波(此視窗包含256個資料點，包括R波的前127個與後128個資料點，取樣率為360 Hz)。使用原始時頻圖分辨三類(竇性心律、心房早期收縮、與心室早期收縮)達到最高辨識率是99.37%；加上特徵提取之後，辨識率為98.33%(使用Harris特徵提取)。在辨識竇性心律(SR)、心房早期收縮(APC)、心室早期收縮(VPC)、左束支傳導阻滯(LBBB)、與右束支傳導阻滯(RBBB)等五種疾病心電圖，本論文在k-fold (k=10)交叉驗證中得到99.42%辨識率。在手腕橈動脈脈音訊號處理的方面，本論文進行以下三種探討：首先是測試演算法辨識竇性心律與心房顫動的功效。在使用原始時頻圖以及k-fold (k=5)交叉驗證的狀況下，可以達到100%的正確率。第二是測試本論文演算法基於脈音圖於辨識心律不整的疾病（如：心房顫動(AFib)、心房撲動(AFL)、心房早期收縮(APC)、和心室早期收縮(VPC)），當小波轉換時頻圖結合主成份分析(PCA)作為影像特徵擷取方法時，搭配卷積式類神經網路，在5秒視窗下，可達到95.91%的辨識率，原始時頻圖辨識率為95.82%，使用Harris特徵提取之後識率為95.57%。第三是測試演算法辨識心臟結構異常的心臟疾病（如：主動脈瓣閉鎖不全(aortic regurgitation, AR)，主動脈瓣狹窄(aortic stenosis, AS)，鬱血性心衰竭(congestive heart failure, CHF)，和肥厚性心肌症(hypertrophic cardiomyopathy, HCM)），透過小波轉換的脈音時頻圖結合Harris特徵提取作為影像特徵擷取方法時，搭配卷積式類神經網路，在10秒視窗下，可達到99.53%的辨識率，原始時頻圖辨識率為99.29%，使用主成份分析(PCA)特徵提取之後識率為88.12%。本論文也比較了9層以及4層的的卷積式類神經網路辨識器的辨識結果。在竇性心律與心房顫動的辨識，辨識率從99.29%（4層CNN）提升到100%（9層CNN）；在竇性心律與心律不整的疾病的辨識，辨識率91.61%（4層CNN）提升到95.82%（9層CNN）；在竇性心律與心臟結構異常的心臟疾病的辨識，辨識率從98.68%（4層CNN）提升到99.33%（9層CNN）。綜合以上，本論文提出並驗證了一種深度學習及影像特徵提取於心電圖和脈音圖時頻轉換的心臟疾病自動辨識演算法，實驗數據顯示出使用9層的卷積式類神經網路比4層的卷積式類神經網路可以有效提升辨識率。此外，本論文探討使用傳統影像處理的特徵萃取技巧（如主成分分析、KAZE特徵擷取演算法、加速強健特徵擷取演算法、最大穩定極值區域特徵萃取演算法）強化影像特徵再使用卷積式類神經網路辨識，數據顯示使用影像處理的特徵萃取技巧強化心電圖/手腕橈動脈脈音時頻圖對於最終辨識效率並沒有顯著提升。本論文使用了探討了探討單純使用卷積式類神經網路作為辨識器以及使用卷積式類神經網路（特徵擷取）並結合支持向量機辨識器對辨識正確率的影響，上述兩種辨識器效果不相上下，但使用卷積式類神經網路（特徵擷取）並結合支持向量機辨識器的運算時間(39.79秒)遠低於使用卷積式類神經網路作為辨識器(335秒)。本論文提出並驗證了將時域訊號（心電圖以及手腕橈動脈脈音訊號）轉換至時頻圖、再透過卷積式類神經網路進行自動辨識的演算法，在辨識心律不整或結構性心臟病上，都可以達到至少9成5以上的辨識正確率。

This study presents an algorithm of deep learning and feature extraction for processing the time-frequency transformation spectrogram of electrocardiogram and pulse-audiogram signals, and is applied to the automatic cardiovascular disease recognition for arrhythmia and structural heart disease. The main research purposes include: 1) exploring the difference in the automatic recognition effect of the deep (9 layers) and shallow (3 layers) deep learning classifier convolutional neural networks (CNN), 2) exploring the difference in the accuracy of time-frequency spectrogram transformed from ECG signals and pulse-audiogram (PAG) signals using different feature extraction methods, 3) exploring the use of AlexNet convolutional neural networks as calssifier and the use of AlexNet convolutional neural networks (feature extraction) combined with support vector machine calssifier to identify the difference in the accuracy. The algorithm flow proposed in this thesis firstly generates the spectrogram using time-frequency transform (continuous wavelet transform, CWT) of electrocardiogram and pulse-audiogram signals. Then through the feature extraction methods of traditional image processing, such as principal component analysis (PCA), Harris–Stephens algorithm (Harris), KAZE feature, speeded-up robust features (SURF), maximally stable extremal regions (MSER). Second, a convolutional neural networks (CNN, with deeper architecture AlexNet) classifier with original time-frequency spectrogram and images after feature extraction as input. Finally, use k-fold cross-validation to validate the final result.
The ECG signal database used in this paper was obtained from PhysioNet of Massachusetts Institute of Technology (MIT), and the pulse-audiogram (PAG) of heart disease patients collected by National Cheng Kung University Hospital (NCKUH). In the ECG classifications, this study identifies SR (sinus rhythm), APC (atrial premature contraction), VPC (ventricular premature contraction), LBBB (left bundle branch block beat), and RBBB (right bundle branch block beat), each window contains a complete QRS complex (256 signal samples, 127 samples before and 128 samples after the R peak). The highest accuracy for identifying five types of the heart disease is 99.42%, with 10-fold cross-validation. Using the original CWT spectogram to identify three types (SR, APC, and VPC), the highest accuracy is 99.37%; after feature extraction, the highest accuracy is 98.33% (using Harris feature extraction).
In the PAG classifications, this study makes the following three main comparisons. 1) To classify sinus rhythm (SR) and atrial fibrillation (AFib), the accuracy of 100% can be achieved with the original CWT spectogram and 5-fold cross-validation. 2) To classify arrhythmia group (eg, atrial fibrillation (AFib), atrial flutter (AFL), atrial premature contraction (APC), and ventricular premature contraction (VPC)), when combined CWT spectrogram and principal component analysis (PCA) is used as an image feature extraction method, with a convolutional neural networks classifier in a 5-sec time-window can achieve accuracy of 95.91%; The accuracy was 95.82% when using the original spectrogram, and the accuracy was 95.57% after using Harris feature extraction. 3) To classify structural heart disease (SHD) group (eg, aortic regurgitation (AR), aortic stenosis (AS), congestive heart failure (CHF), and hypertrophic cardiomyopathy (HCM)), when combined CWT spectrogram and Harris-Stephens algorithm (Harris) is used as an image feature extraction method, with a convolutional neural networks classifier in a 10-sec time-window can achieve accuracy of 99.53%; The accuracy was 99.29% when using the original spectrogram, and the accuracy was 88.12% after using PCA feature extraction.
We also compared the classification result of a deep (9-layer) shallow (3-layer) convolutional neural networks classifier. The classification of SR and AFib was improved from the highest 99.29% (4-layer CNN) to 100% (9-layer CNN); the classification of arrhythmia group and SR, was improved from the highest 91.61% (4-layer CNN) to 95.82% (9-layer CNN); the classification of SHD group and SR is increased from accuracy of 98.68% (4-layer CNN) to 99.33% (9-layer CNN).
Based on the above, this paper proposes and verifies an algorithm of deep learning and feature extraction for processing the time-frequency transformation spectrogram of electrocardiogram and pulse-audiogram signals, and is applied to the automatic cardiovascular disease recognition for arrhythmia and structural heart disease. The experimental data shows that the use of a 9-layer CNN can effectively improve the accuracy than a 4-layer CNN. In addition, this paper explores the feature extraction methods using traditional image processing (eg, principal component analysis, KAZE feature extraction algorithm, speeded-up robust features, and maximally stable extremal regions) to enhance image features. Then, the identification using CNN, the data shows that using the feature extraction methods to strengthen the ECG/PAG time-frequency spectrogram has no significant improvement in the final result. This paper explores the use of AlexNet convolutional neural networks as calssifier and the use of AlexNet convolutional neural networks (feature extraction) combined with support vector machine calssifier. The above two calssifiers are comparable, but the computation time of AlexNet CNN combined with SVM (39.79 seconds) is much lower than using AlexNet CNN ( 335 seconds).
This paper proposes and verifies an algorithm of time-domain signal (electrocardiogram (ECG) and pulse-audiogram (PAG) signals) transform into time-frequency transformation spectrogram of, and automatic recognition by convolutional neural networks.The automatic cardiovascular disease recognition for arrhythmia and structural heart disease all can achieve accuracy over 95%.

[1] P. Cheriyath, F. He, I. Peters, X. Li, P. Alagona, C. Wu, M. Pu, W. Cascio and D. Liao, “Relation of atrial and/or ventricular premature complexes on a two-minute rhythm strip to the risk of sudden cardiac death (the atherosclerosis risk in communities [aric] study),” The American Journal of Cardiology, vol. 107, no. 2, pp. 151-155, 2011.
[2] J. Sandham, “EBME & Clinical Engineering Articles Haemodynamics,” ebme.co.uk, May, 2011. [Online]. Available: https://bit.ly/30wTEfj. [Accessed: July 10, 2019].
[3] J. Lian, L. Wang, and D. Muessig, “A simple method to detect atrial fibrillation using RR intervals,” The American journal of cardiology, vol. 107, pp. 1494-1497, 2011.
[4] E. R. Pfeiffer, J. R. Tangney, J. H. Omens, and A. D. McCulloch, “Biomechanics of cardiac electromechanical coupling and mechanoelectric feedback,” Journal of biomechanical engineering, vol. 136, no. 2, pp. 0210071-02100711, 2014.
[5] J. Lee, Y. Nam, and K. Chon, “Time-varying coherence function for atrial fibrillation detection,” IEEE Transactions on Biomedical Engineering, vol. 60, no. 10, pp. 2783-2793, Oct. 2013.
[6] L. Jinseok, B. A. Reyes, D. D. McManus, O. Mathias, and K. H. Chon, “Atrial fibrillation detection using an iPhone 4S,” IEEE Transactions on Biomedical Engineering, vol. 60, no. 1, pp. 203-206, Jan. 2013.
[7] D. D. McManus, J. Lee, O. Maitas, N. Esa, R. Pidikiti, A. Carlucci, J. Harrington, E. Mick, and K. H. Chon, “A novel application for the detection of an irregular pulse using an iPhone 4S in patients with atrial fibrillation,” Heart Rhythm, vol. 10, pp. 315-319, Mar. 2013.
[8] J. Comstock, “Using Zio data, Stanford team trains AI to best cardiologists at detecting 14 arrhythmias,” mobihealthnews.com, July 11, 2017. [Online]. Available: https://bit.ly/2JtcHS9. [Accessed: July 10, 2019].
[9] S. P. Shashikumar, A. J. Shah, Q. Li, G. D. Clifford and S. Nemati, “A deep learning approach to monitoring and detecting atrial fibrillation using wearable technology,” 2017 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), Orlando, FL, pp. 141-144, 2017.
[10] M. Balouchestani and S. Krishnan, “Fast clustering algorithm for large ECG data sets based on CS theory in combination with PCA and K-NN methods,” 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Chicago, Illinois, United States, pp. 98-101, 2014.
[11] V. Kumari and P. Kumar, “Classification of cardiac arrhythmia using hybrid genetic algorithm optimization for multi-layer perceptron neural network,” International Journal of Biomedical Engineering and Technology, vol. 20, no. 2, pp. 132-149, 2016.
[12] A. Chetan, R. Tripathy and S. Dandapat, “A diagnostic system for detection of atrial and ventricular arrhythmia episodes from electrocardiogram,” Journal of Medical and Biological Engineering, pp. 1-12, 2017.
[13] U. Desai, R. Martis, C. G. nayak, G. Seshikala, K. Sarika and R. Shetty K., “Decision support system for arrhythmia beats using ECG signals with DCT, DWT, and EMD methods: a comparative study,” Journal of Mechanics in Medicine and Biology, vol. 16, no. 01, pp. 1-19, 2016.
[14] Wikipedia, “Continuous wavelet transform,” en.wikipedia.org. [Online]. Available: https://bit.ly/2XSXCBk. [Accessed: July 10, 2019].
[15] Wikipedia, “Convolutional neural network,” en.wikipedia.org. [Online]. Available: https://bit.ly/1WbDkrR. [Accessed: July 10, 2019].
[16] MathWorks, “Deep Learning Toolbox,” mathworks.cn. [Online]. Available: https://bit.ly/2XFBgPf. [Accessed: July 10, 2019].
[17] A. Krizhevsky, I. Sutskever and G. Hinton, “ImageNet classification with deep convolutional neural networks,” Advances in neural information processing systems, pp. 1106-1114, 2012.
[18] ImageNet. [Online]. Available: http://image-net.org/index . [Accessed: July 10, 2019].
[19] MathWorks, “Pretrained Deep Neural Networks,” mathworks.cn. [Online]. Available: https://bit.ly/2NKknna. [Accessed: July 10, 2019].
[20] P. S. Addison, “Wavelet transforms and the ECG: a review,” Physiol. Meas., vol. 26, no. 5, pp. 155-199, 2005.
[21] L. Y. Shyu, Y. H. Wu, W. Hu, “Using wavelet transform and fuzzy neural network for VPC detection from the holter ECG”, IEEE Transactions on Biomedical Engineering, vol.51 1269-73,2004
[22] I. R. Legarreta, P. S. Addison, M. I. Reed, N. Grubb, G. R. Clegg, C. E. Robertson, J. N. Watson, “Continuous wavelet transform modulus maxima analysis of the electrocardiogram: beat characterisation and beat-to-beat measurement,” International Journal of Wavelets Multiresolution and Information Processing, vol. 03, no. 1, pp. 19-42, 2005.
[23] Wikipedia, “Cardiovascular disease,” en.wikipedia.org. [Online]. Available: https://bit.ly/1Tf2mZj. [Accessed: July 10, 2019].
[24] Wikipedia, “Time-frequency analysis,” en.wikipedia.org. [Online]. Available: https://bit.ly/30tdZlo. [Accessed: July 10, 2019].
[25] MathWorks, “Extract Image Features Using Pretrained Network,” mathworks.cn. [Online]. Available: https://bit.ly/2JriB6f. [Accessed: July 10, 2019].
[26] MathWorks, “Transfer Learning Using AlexNet,” mathworks.cn. [Online]. Available: https://bit.ly/2XPhmFV. [Accessed: July 10, 2019].
[27] Wikipedia, “Cross-validation (statistics),” en.wikipedia.org. [Online]. Available: https://bit.ly/2cEQ6Oz. [Accessed: July 10, 2019].
[28] P. Du, W. A. Kibbe, S. M. Lin, “Improved peak detection in mass spectrum by incorporating continuous wavelet transform-based pattern matching,” Bioinformatics, Volume 22, Issue 17, pp. 2059-2065, 2006.
[29] MathWorks, “Extract interest point descriptors,” mathworks.cn. [Online]. Available: https://bit.ly/2NZMzCH. [Accessed: July 10, 2019].
[30] Wikipedia, “Principal component analysis,” en.wikipedia.org. [Online]. Available: https://bit.ly/1MkX8V3. [Accessed: July 10, 2019].
[31] Wikipedia, “Eigenface,” en.wikipedia.org. [Online]. Available: https://bit.ly/2njyxfr. [Accessed: July 10, 2019].
[32] S. Lawrence, M. Kirby, “Low-dimensional procedure for the characterization of human faces,” Journal of the Optical Society of America A, vol. 4, no. 3, pp. 519-524, 1987.
[33] M. A. Turk, A. P. Pentland, “Face recognition using eigenfaces,” Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Maui, HI, USA, pp. 586-591, 1991.
[34] C. Harris, M. Stephens, “A Combined Corner and Edge Detector,” Proceedings of the 4th Alvey Vision Conference, Manchester, England, pp. 147-151, 1988.
[35] J. Matas, O. Chum, M. Urba, and T. Pajdla, “Robust wide baseline stereo from maximally stable extremal regions,” Proceedings of British Machine Vision Conference, Cardiff, Wales, UK, pp. 384-396, 2002.
[36] C. Harris, M. Stephens, “A Combined Corner and Edge Detector,” Proceedings of the 4th Alvey Vision Conference, Manchester, England, pp. 147-151, 1988.
[37] Wikipedia, “Harris Corner Detector,” en.wikipedia.org. [Online]. Available: https://bit.ly/30pBZ97. [Accessed: July 10, 2019].
[38] MathWorks, “detectHarrisFeatures,” mathworks.cn. [Online]. Available: https://bit.ly/2JrHIWv. [Accessed: July 10, 2019].
[39] P. F. Alcantarilla, A. Bartoli, A. J. Davison, “KAZE Features,” ECCV 2012, Part VI, LNCS 7577, p. 214-227, 2012.
[40] MathWorks, “detectKAZEFeatures,” mathworks.cn. [Online]. Available: https://bit.ly/2XYmdo0. [Accessed: July 10, 2019].
[41] H. Bay, A. Ess, T. Tuytelaars, L. Van Gool, “SURF: Speeded Up Robust Features,” Computer Vision and Image Understanding (CVIU), vol. 110, no. 3, pp. 346-359, 2008.
[42] MathWorks, “detectSURFFeatures,” mathworks.cn. [Online]. Available: https://bit.ly/2YKp1CB. [Accessed: July 10, 2019].
[43] D. G. Lowe, “Object recognition from local scale-invariant features,” Proceedings of the International Conference on Computer Vision, Kerkyra, Corfu, Greece, pp. 1150-1157, 1999.
[44] Ing. Marek Hr´uz, “Lesson 03 - Harris, SIFT, SURF,” department of cybernetics. [Online]. Available: https://bit.ly/2LKolcz. [Accessed: July 10, 2019].
[45] MathWorks, “detectMSERFeatures,” mathworks.cn. [Online]. Available: https://bit.ly/32hkycK. [Accessed: July 10, 2019].
[46] J. Matas, O. Chum, M. Urba, T. Pajdla, “Robust wide baseline stereo from maximally stable extremal regions,” Proceedings of British Machine Vision Conference, Cardiff, Wales, UK, pp. 384-396, 2002.
[47] Y. Chang, “Development of an AI-based Arrhythmia and Structural Heart Disease Classification Algorithm based on Pulse AudioGram,” M. S. thesis, department of biomedical engineering, NCKU, Tainan, Taiwan (R.O.C), 2018.
[48] A. Isin, S. Ozdalili, “Cardiac arrhythmia detection using deep learning,” Procedia computer science, vol. 120, pp. 268-275, 2017.
[49] U. R. Acharya, H. Fujita, S. L. Oh, Y. Hagiwara, J. H. Tan, “Automated detection of arrhythmias using different intervals of tachycardia ECG segments with convolutional neural network,” Information sciences, vol. 405 ,pp. 81-90, 2017.
[50] F. A. Elhaj, N. Salim, A. R. Harris, T. T. Swee, “Arrhythmia recognition and classification using combined linear and nonlinear features of ECG signals,” Computer methods and programs in biomedicine, vol. 127 , pp. 52-63, 2016.
[51] R. G. Afkhami, G. Azarnia, M. A. Tinati, “Cardiac arrhythmia classification using statistical and mixture modeling features of ECG signals,” Pattern Recognition Letters, vol. 70, pp. 45-51, 2016.
[52] M. Thomas, M. K. Das, S. Ari, “Automatic ECG arrhythmia classification using dual tree complex wavelet based features,” AEU-International Journal of Electronics and Communications, vol. 69.4, pp. 715-721, 2015.
[53] M. R. Homaeinezhad, S. A. Atyabi, E. Tavakkoli, “ECG arrhythmia recognition via a neuro-SVM-KNN hybrid classifier with virtual QRS image-based geometrical features,” Expert Systems with Applications, vol. 39, no. 2, pp. 2047-2058, 2012.
[54] R. J. Martis, U. R. Acharya, K. M. Mandana, A. K. Ray, “Application of principal component analysis to ECG signals for automated diagnosis of cardiac health,” Expert Systems with Applications, vol. 39, no. 14, pp. 11792-11800, 2012.
[55] J. Oster, J. Behar, O. Sayadi, S. Nemati, A. Johnson and G. Clifford, “Semisupervised ECG Ventricular Beat Classification With Novelty Detection Based on Switching Kalman Filters,” IEEE Transactions on Biomedical Engineering, vol. 62, no. 9, pp. 2125-2134, 2015.
[56] B. Doğan and M. Korürek, “A new ECG beat clustering method based on kernelized fuzzy c-means and hybrid ant colony optimization for continuous domains,” Applied Soft Computing, vol. 12, no. 11, pp. 3442-3451, 2012.
[57] Can Ye, B. Kumar and M. Coimbra, “Heartbeat Classification Using Morphological and Dynamic Features of ECG Signals,” IEEE Transactions on Biomedical Engineering, vol. 59, no. 10, pp. 2930-2941, 2012.
[58] P. de Chazal, M. O’Dwyer, R.B. Reilly, “Automatic classification of heartbeats using ECG morphology and heartbeat interval features,” IEEE Transactions on Biomedical Engineering, vol. 51, no. 7, pp. 1196-1206, 2004.
[59] S. W. Chen, P. M. Clarkson, Q. Fan, “A robust sequential detection algorithm for cardiac arrhythmia classification,” IEEE Transactions on Biomedical Engineering, vol. 43, no. 11, pp. 1120-1124, 1996.
[60] M. Lagerholm, C. Peterson, G. Braccini, L. Edenbrandt, L. Sornmo, “Clustering ECG complexes using hermite functions and self-organizing maps,” IEEE Transactions on Biomedical Engineering, vol. 47, no. 7, pp. 838-848, 2000.
[61] M. M. Al Rahhal, Y. Bazi, H. AlHichri, N. Alajlan, F. Melgani, R. R. Yager, “Deep learning approach for active classification of electrocardiogram signals,” Information Sciences, vol. 345, pp. 340-354, 2016.
[62] J. H. Tan, Y. Hagiwara, W. Pang, I. Lim, S. L. Oh, M. Adam, R. San Tan, M. Chen, and U. R. Acharya, “Application of stacked convolutional and long short-term memory network for accurate identification of cad ecg signals,” Comput. Biol. Med., 2018.
[63] A. Majumdar, and R. Ward, “Robust greedy deep dictionary learning for ecg arrhythmia classification,” Neural Networks (IJCNN), 2017 International Joint Conference on. IEEE, Anchorage, Alaska, pp. 4400-4407, 2017.
[64] S. Narula, K. Shameer, AMS Omar, J. T. Dudley, and P. P. Sengupta, “Machine-learning algorithms to automate morphological and functional assessments in 2D echocardiography,” Journal of the American College of Cardiology, vol. 68, no. 21, pp. 2287-2295, 2016.
[65] T. L. Fonseca, L. Goliatt, L. C. D. Campos,F. S. Bastos, L. P. S. Barra, R. W. dos Santos, ”Machine Learning Approaches to Estimate Simulated Cardiac Ejection Fraction from Electrical Impedance Tomography,” Ibero-American Conference on Artificial Intelligence, San Jose, Costa Rica, 2016.
[66] P. C. Austin, J. V. Tu, J. E. Ho, D. Levy, D. S. Lee, ”Using methods from the data-mining and machine-learning literature for disease classification and prediction: a case study examining classification of heart failure subtypes,” Journal of clinical epidemiology, vol. 66, no. 4, pp. 398-407, 2013.
[67] J. F. Silva, J. M. Silva, A. Guerra, S. Matos, C. Costa, “Ejection fraction classification in transthoracic echocardiography using a deep learning approach,” 2018 IEEE 31st International Symposium on Computer-Based Medical Systems (CBMS). IEEE, pp. 123-128, 2018.
[68] T. Kubota, “Stanford computer scientists develop an algorithm that diagnoses heart arrhythmias with cardiologist-level accuracy,” news.stanford.edu, July 6, 2017. [Online]. Available: https://stanford.io/2t8KtWs. [Accessed: July 10, 2019].
[69] P. Rajpurkar, A. Y. Hannun, M. Haghpanahi, C. Bourn, A. Y. Ng, “Cardiologist-level arrhythmia detection with convolutional neural networks,” arXiv preprint arXiv:1707.01836, 2017.
[70] A. Y. Hannun, P. Rajpurkar, M. Haghpanahi, G. H. Tison, C. Bourn, M. P. Turakhia, and A. Y. Ng, “Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network,” Nature medicine, vol. 25, no. 1, pp. 65-69, 2019.
[71] Z. I. Attia, S. Kapa, F. Lopez-Jimenez, P. M. McKie, et al., “Screening for cardiac contractile dysfunction using an artificial intelligence–enabled electrocardiogram,” Nat. Med., vol. 25, pp. 70-74, 2019.
[72] PhysioNet, “MIT-BIT Arrhythmia Database,” physionet.org. [Online]. Available: https://physionet.org/physiobank/database/mitdb/. [Accessed: July 10, 2019].