Unveiling Hearts: Deep Learning-Based Electrocardiogram Classification for Congenital Heart Disease Detection

Abstract

The electrical activity of the human heart, recorded via an electrocardiogram (ECG), is characterized by distinct waveforms such as the P wave, QRS complex, and T wave. By analyzing the duration, morphology, and intervals between these waveforms, various cardiac disorders can be identified. This study aims to develop a deep learning-based approach for the accurate classification of congenital heart disease (CHD) using ECG data. We employed convolutional neural networks (CNNs) and recurrent neural networks (RNNs) to analyze ECG signals, leveraging their ability to detect multiple features in time-series data. A deep learning model was developed and trained using features such as estimated peak locations, inter-peak intervals, and other ECG parameters. To address class imbalance, we applied the synthetic minority oversampling technique (SMOTE), which generates synthetic samples to balance each class. The analysis was conducted using the MIT-BIH Arrhythmia Database, enabling CHD classification based on ECG patterns. The proposed method improved classification accuracy by effectively balancing the dataset with SMOTE. Compared to conventional methods, the deep learning algorithms demonstrated robust performance in analyzing ECG data and detecting disease-related patterns, achieving superior results. This study highlights the potential of CNNs and RNNs for classifying CHD from ECG signals. By mitigating data imbalance with SMOTE, the approach enhances both accuracy and reliability. Future work will focus on validating the model with additional datasets and addressing real-world challenges such as noise handling and external validation.

Keywords

Congenital heart disease / ECG classification / VGG16 / SMOTE / Deep learning / Electrocardiography / Imbalanced data

References

[1] Narasimhan C, Francis J. LeoSchamroth: An Introduction to Electro Cardiography, 20238New Delhi, Wiley

[2] Chan HL, Chou WS, Chen SW, et al.. Continuous and online analysis of heart rate variability. J Med Eng Technol., 2005, 29(5): 227-234

[3] Laguna P, Jané R, Caminal P. Automatic detection of wave boundaries in multilead ECG signals: validation with the CSE database. Comput Biomed Res., 1994, 27(1): 45-60

[4] Edhouse J. ABC of clinical electrocardiography: Conditions affecting the left side of the heart. Bmj., 2002, 324(7348): 1264-1267

[5] Wu Y, Rangayyan RM, Zhou Y, et al.. Filtering electrocardiographic signals using an unbiased and normalized adaptive noise reduction system. Med Eng Phys., 2009, 31(1): 17-26

[6] Moody GB, Mark RG. The impact of the MIT-BIH arrhythmia database. IEEE Eng Med Biol Mag., 2001, 20(3): 45-50

[7] Chen J, Huang S, Zhang Y, et al.. Congenital heart disease detection by pediatric electrocardiogram based deep learning integrated with human concepts. Nat Commun., 2024, 15(1): 976

[8] Sarma A. Crochetage sign: an invaluable independent ECG sign in detecting ASD. Indian J Crit Care Med., 2021, 25(2234-235

[9] MacAlpin RN. Significance of abnormal Q waves in the electrocardiograms of adults less than 40 years old. Ann Noninvasive Electrocardiol., 2006, 11(3): 203-210

[10] Brink AJ, Neill CA. The electrocardiogram in congenital heart disease; with special reference to left axis deviation. Circulation., 1955, 12(4): 604-611

[11] Bronzetti G. Congenital heart disease. Atlas of Pediatric and Youth ECG. Cham: Springer International Publishing, 2017:317–358.

[12] Charlap S, Shani J, Schulhoff N, et al. R- and S-wave amplitude changes with acute anterior transmural myocardial ischemia. Correlations with left ventricular filling pressures. Chest. 1990;97(3):566–571.

[13] Istolahti T, Lyytikäinen LP, Huhtala H, et al.. The prognostic significance of T-wave inversion according to ECG lead group during long-term follow-up in the general population. Ann Noninvasive Electrocardiol., 2021, 26(1 e12799

[14] Mousavi S, Afghah F, Khadem F, et al.. ECG Language processing (ELP): a new technique to analyze ECG signals. Comput Methods Programs Biomed., 2021, 202 105959

[15] Turnip A, Ilham Rizqywan M, Kusumandari DE, et al.. Classification of ECG signal with support vector machine method for arrhythmia detection. J Phys Conf Ser., 2018, 970(1 012012

[16] Jun TJ, Nguyen HM, Kang D, et al. ECG arrhythmia classification using a 2-D convolutional neural network [preprint]. 2018: arXiv:1804.06812. Available from: https://arxiv.org/abs/1804.06812

[17] Wu YN, Yang F, Liu Y, et al. A comparison of 1-D and 2-D deep convolutional neural networks in ECG classification [preprint]. 2018: arXiv:1810.07088. Available from: https://arxiv.org/abs/1810.07088

[18] Ribeiro AH, Ribeiro MH, Paixão GMM, et al.. Automatic diagnosis of the 12-lead ECG using a deep neural network. Nat Commun., 2020, 11(11760

[19] Casas MM, Avitia RL, Gonzalez-Navarro FF, et al.. Bayesian classification models for premature ventricular ontraction detection on ECG traces. J Healthc Eng., 2018, 2018: 2694768

[20] Shoughi A, Dowlatshahi MB. A practical system based on CNN-BLSTM network for accurate classification of ECG heartbeats of MIT-BIH imbalanced dataset. In: Proceedings of the 2021 26th International Computer Conference, Computer Society of Iran (CSICC); 03–04 March 2021; Tehran, Iran. Piscataway (NJ): IEEE; 2021. pp. 1–6. Available from: https://ieeexplore.ieee.org/document/9420620.

[21] Savalia S, Emamian V. Cardiac arrhythmia classification by multi-layer perceptron and convolution neural networks. Bioengineering (Basel)., 2018, 5(235

[22] Mohamed B, Issam A, Mohamed A, et al.. ECG image classification in real time based on the haar-like features and artificial neural networks. Procedia Comput Sci., 2015, 73: 32-39

[23] Liang Y, Yin S, Tang Q, et al.. Deep learning algorithm classifies heartbeat events based on electrocardiogram signals. Front Physiol., 2020, 11 569050

[24] Oliveira AT, Nobrega EGO. A novel arrhythmia classification method based on convolutional neural networks interpretation of electrocardiogram images. In: Proceedings of 2019 IEEE International Conference on Industrial Technology (ICIT); 13–15 February 2019; Melbourne, VIC, Austrilia. Piscataway (NJ): IEEE; 2019. pp. 841–846.

[25] Zhou FY, Jin LP, Dong J. Premature ventricular contraction detection combining deep neural networks and rules inference. Artif Intell Med., 2017, 79: 42-51

[26] Porumb M, Iadanza E, Massaro S, et al.. A convolutional neural network approach to detect congestive heart failure. Biomed Signal Process Control., 2020, 55 101597

[27] Diker A, Avci E, Tanyildizi E, et al.. A novel ECG signal classification method using DEA-ELM. Med Hypotheses., 2020, 136 109515

[28] Kwon JM, Lee SY, Jeon KH, et al.. Deep learning-based algorithm for detecting aortic stenosis using electrocardiography. J Am Heart Assoc., 2020, 9(7 e014717

[29] He R, Wang K, Li Q, et al.. A novel method for the detection of R-peaks in ECG based on K-Nearest Neighbors and Particle Swarm Optimization. EURASIP J Adv Signal Process., 2017, 2017(182

[30] Makimoto H, Höckmann M, Lin T, et al.. Performance of a convolutional neural network derived from an ECG database in recognizing myocardial infarction. Sci Rep., 2020, 10(18445

[31] Li H, Yuan D, Wang Y, et al.. Arrhythmia classification based on multi-domain feature extraction for an ECG recognition system. Sensors (Basel)., 2016, 16(101744

[32] Khan MU, Aziz S, Javeria MC, et al. ECG Signal Analysis for Classification of Congenital Heart Defects. In: Proceedings of 2020 International Conference on Computing and Information Technology (ICCIT-1441); 09–10 September 2020; Tabuk, Saudi Arabia. Piscataway (NJ): IEEE; 2020. pp. 1–5. Available from: https://ieeexplore.ieee.org/document/9213825

[33] Muthukumar B, Kartheesan L, Pasupathy V, et al. Advanced OptiDLCardioNet-Based Cardiac Arrhythmia Detection Model from ECG Signals. In: Proceedings of the 2024 International Conference on Sustainable Communication Networks and Application (ICSCNA); 11–13 December 2024; Theni, India. Piscataway (NJ): IEEE; 2024. pp. 217–223. Available from: https://ieeexplore.ieee.org/document/10863976.

RIGHTS & PERMISSIONS

The Author(s), under exclusive licence to the Huazhong University of Science and Technology