Application of Machine Learning in Arrhythmia Association: Comparison
View Latest Version
Please note this is a comparison between Version 2 by Wendy Huang and Version 1 by Sadiq Alinsaif.

Cardiac arrhythmias, characterized by deviations from the normal rhythmic contractions of the heart, pose a formidable diagnostic challenge. Early and accurate detection remains an integral component of effective diagnosis, informing critical decisions made by cardiologists. The application of machine learning (ML) for electrocardiogram (ECG) data analysis holds significant promise in the development of prognostic and diagnostic computer-assisted diagnosis (CAD) systems. ECG CAD systems can serve as a valuable tool for medical professionals, facilitating objective diagnosis. The association between different ECG records can be established through supervised, semi-supervised, or unsupervised ML approaches.

  • arrhythmia
  • electrocardiogram (ECG)
  • computer-assisted diagnosis (CAD)
  • machine learning (ML)
  • deep learning (DL)

1. Introduction

Despite its origin in 1980, the Massachusetts Institute of Technology–Beth Israel Hospital (MIT-BIH) electrocardiogram (ECG) Arrhythmia Database retains a substantial and enduring influence on the field of arrhythmia characterization and detection, arguably surpassing initial expectations [1]. This longevity coincides with advancements in artificial and computational intelligence, enabling new analytical and interpretive models for ECG-based diagnoses of arrhythmias and other cardiac pathologies [2,3,4,5,6][2][3][4][5][6]. These techniques can be broadly categorized into:
  • Traditional learning-based approaches: employing classical machine learning (CML) algorithms and established feature extraction/selection methods.
  • Deep learning (DL) approaches: leveraging deep features obtained through training from scratch, model fine-tuning, or hybrid configurations combining traditional descriptors with deep-feature representations.
The application of machine learning (ML) for ECG data analysis holds significant promise in the development of prognostic and diagnostic CAD systems. ECG CAD systems can serve as a valuable tool for medical professionals, facilitating objective diagnosis [3]. The association between different ECG records can be established through supervised [7], semi-supervised [8], or unsupervised [9] ML approaches. Supervised learning entails training a model on a labeled dataset where ground-truth labels are known for each record. In the context of medical data classification, prominent supervised learning algorithms employed include multilayer perceptrons (MLPs) [10] and support vector machines (SVMs) [11]. Conversely, in situations where ground-truth labels are unavailable, unsupervised learning can be utilized to discover latent patterns within the data. Examples of such algorithms include k-means clustering (k-means) [12] and principal component analysis (PCA) [13].
Traditional ML approaches rely on the extraction of informative features that effectively represent the underlying disease [14]. Success in this endeavor hinges on the extraction of numerical measurements that inherently manifest the disease characteristics [15]. When a chosen feature extraction method effectively captures the pathological signatures of the desired phenomenon (disease), the subsequent application of an ML algorithm is more likely to yield accurate disease prediction outcomes [15].
The recent paradigm shift in ECG data analysis has gravitated towards the application of DL techniques. Unlike traditional methods, DL offers generic, non-domain-specific operation sequences directly applicable to raw input signals, including ECG records [3,4,5,16,17,18,19,20][3][4][5][16][17][18][19][20]. A prominent example of DL architecture is the convolutional neural network (CNN), which demonstrably exhibits efficacy in ECG data analysis [3,4,5,16,17,18,19,20][3][4][5][16][17][18][19][20]. The inherent strength of DL models lies in their ability to learn and discover multilevel representations from data. Lower-level layers typically extract fundamental features like edges and color, while higher layers progressively abstract these features into semantically meaningful representations of the input [21]. This characteristic has spurred an active research field exploring the transferability of knowledge gained from pretrained models to the domain of ECG arrhythmia detection [8,22][8][22]. Alternatively, pretrained CNN models can be utilized as unsupervised feature extractors, bypassing the need for fine-tuning [23]. Moreover, hybrid approaches combining hand-crafted features with deep features extracted from pretrained models are also being explored [24].

2. Arrhythmia Association Using Machine Learning

Building on the foundational framework established by Mitchell [40][25], ML can be conceptually understood through the interplay of three key components:
  • Task (T): The specific problem or objective the ML model is designed to tackle. In the context of this woresearkch, the task (T) would be classifying and identifying various arrhythmias within labeled ECG recordings.
  • Experience (E): The training data, a collection of labeled examples, serve as the basis for the model’s learning and knowledge acquisition. For arrhythmia classification, the experience (E) would comprise a labeled dataset of ECG recordings, with each recording assigned to a specific arrhythmia type.
  • Performance (P): The effectiveness of the ML model on the designated task, typically measured by metrics such as accuracy, precision, recall, and other relevant evaluation criteria. The ideal model exhibits a strong generalizability, performing accurately on unseen data beyond the training set.
Within this framework, both hand-crafted and DL models for ECG analysis are constructed. The model ingests an input ECG record from the experience (E) and maps it to an output label representing the detected arrhythmia type. Optimization algorithms refine the model’s internal parameters based on its performance on the training data, aiming to achieve optimal accuracy and generalizability. Ultimately, the ideal ML model demonstrates the ability to accurately classify unseen ECG recordings, potentially assisting cardiologists in diagnostic and treatment decisions. Cross-validation (CV) serves as a widely employed technique for evaluating the performance of both CML and DL models, providing statistically rigorous results. This method assesses the efficacy of a classifier system by partitioning the dataset into training and testing subsets. The testing data remain hidden during the training process, ensuring an unbiased evaluation. The dataset is divided into K folds, with 𝐾−1 folds utilized for training and the remaining fold used for testing. This process is iterated K times, each time employing a different fold for testing. In clinical settings, researchers often investigate the statistical associations between symptoms (represented by test samples) and the presence of disease. Identifying significant associations necessitates expressing data in clinically meaningful ways. To evaluate the performance of different classifiers within each fold, several common metrics [41][26] are employed:
  • Accuracy: the proportion of correctly classified samples.
  • Sensitivity: the ability of the model to correctly identify true positive cases (i.e., identifying diseased patients who truly have the disease).
  • 7,44,45][7]
    Specificity: the ability of the model to correctly identify true negative cases (i.e., identifying healthy patients who truly do not have the disease).
  • Area Under the Curve (AUC): A graphical plot of the model’s performance, showing the relationship between true positive rate (sensitivity) and false positive rate (1 − specificity).
By employing these metrics in conjunction with CV, researchers gain insights into the generalizability and clinical relevance of their proposed models within the context of ECG data analysis. Extracting informative features from ECG signals represents a crucial step in constructing robust classification models for CML-based approaches. This process involves identifying and quantifying relevant characteristics that discriminate between different arrhythmias. Common examples of such features include:
  • Morphological and positional features: These features capture the shape characteristics of the ECG signal. Examples include the amplitudes and widths of peaks and valleys (e.g., R and P waves), interwave distances (e.g., R-R interval), and other relevant shape descriptors [7,42,43][7][27][28].
  • Spectral methods: This category encompasses frequency-domain representations of the ECG signal obtained through transformation techniques. A prominent example is the wavelet transform. This technique decomposes the signal into frequency sub-bands, enabling the analysis of its underlying components at different scales and orientations. Recent research has demonstrated the efficacy of wavelet-based features in ECG classification [[29][30]. Furthermore, hybrid approaches combining DL with wavelet transforms have emerged to leverage the strengths of both methods [17,19,46][17][19][31].
These extracted feature vectors serve as the basis for the subsequent analysis of the ECG signals within CML-based approaches. In contrast, the defining advantage of DL resides in its inherent ability to directly learn features from the raw input ECG data end-to-end [16], effectively bypassing the dedicated feature extraction step. Essentially, the construction of a CAD system employing ML algorithms for distinguishing normal and abnormal samples involves the following core stages:
  • Stage 1: data acquisition: relevant ECG-based arrhythmia datasets are procured.
  • Stage 2: preprocessing: the data undergo a series of preprocessing steps, including:
    –
    Denoising to remove unwanted noise artifacts.
    –
    Peak detection to identify key signal components.
    –
    Signal segmentation to partition the data into meaningful segments.
  • Feature engineering (CML)/feature learning (DL): For CML models, extracting and selecting informative features from the preprocessed data. Conversely, DL approaches learn features directly from the raw input data during model training.
  • Model training and evaluation: the application of the chosen classification algorithm (CML or DL) to the prepared data, followed by a rigorous evaluation to assess its performance and generalizability.
The readily available MIT-BIH dataset completes stage 1 (data acquisition) within the construction process, allowing practitioners to seamlessly transition to stage 2 (preprocessing). This stage focuses on preparing the ECG data for subsequent analysis and model training. A common preprocessing step, employed by both CML and DL approaches, involves denoising the ECG signal to remove unwanted artifacts [45,47,48,49][30][32][33][34]. Denoising aims to mitigate or eliminate the distorting influence of artifacts, which can originate from diverse sources such as respiration, body movements, electrode contact issues, and skin-electrode impedance. This purification step enhances the overall quality of the ECG signal, thereby facilitating the extraction of its inherent and pertinent characteristics. Moreover, the availability of R-peak annotations within the MIT-BIH database offers a robust ground truth for segmenting ECG signals. These readily available annotations enable the delineation of individual cardiac beats [50][35], facilitating further analysis and model development based on segmented data. Consequently, the processed signals lead to building an effective and accurate model in the subsequent anomaly detection/classification model. Following the preprocessing stage, feature extraction commences, aiming to identify a robust and informative set of descriptors from the preprocessed ECG signal. The literature [51,52][36][37] presents a diverse array of feature extraction techniques for differentiating normal and abnormal ECG signals. Texture-based approaches (e.g., local binary pattern, structural co-occurrence matrix), morphological-based methods, and wavelet-transform-based algorithms are utilized for ECG data analysis. Each approach leverages different discriminative properties of the ECG signal to generate a set of features suitable for the subsequent analysis and model training. Beyond approaches based on texture analysis or wavelet transforms, the literature explores alternative feature extraction methods that deviate conceptually. One such example is the utilization of visual-perception-inspired features proposed by Anand et al. [53][38]. These features aim to emulate the human visual system’s ability to discern patterns within the ECG signal. Following the successful extraction of robust and discriminative features through hand-engineering, the choice of the specific CML technique (e.g., SVM or MLP) ought to have a minimal impact on the accuracy and efficiency of ECG anomaly detection/classification. This implies that a well-constructed feature set can mitigate the influence of the chosen CML algorithm on the overall performance of the model. In contrast to CML-based approaches, the alternative pipeline leverages DL, which has emerged as the prevailing paradigm for tackling machine vision tasks [54][39]. CNNs constitute a prevalent DL architecture frequently employed for ECG data analysis, e.g., in [3,4,5,8,16,17,18,19,20,55,56][3][4][5][8][16][17][18][19][20][40][41]. Unlike CML methods that rely on hand-engineered features, CNNs directly process raw ECG data as input. Within these architectures, a series of operations, such as convolution, pooling, and batch normalization, play a pivotal role in extracting discriminative features and ultimately contribute to the robustness of the model. The learned feature maps are then fed to a final classification layer, typically employing a softmax activation function. However, certain studies advocate for utilizing DL models as feature extractors instead of end-to-end classifiers [57][42]. In such cases, the extracted feature vectors serve as input to subsequent CML models. DL models exhibit inherent vulnerabilities when trained on limited datasets, particularly when initializing training from scratch [58][43]. This vulnerability is especially pertinent within the context of specific arrhythmia classes within the MIT-BIH database, where the availability of well-annotated samples is scarce. Consequently, DL models in such scenarios are susceptible to generalization issues and overfitting. Overfitting implies that the model memorizes the intricacies of the training data, hindering its ability to generalize and accurately classify unseen samples. To address this challenge, numerous studies propose various techniques for mitigating the impact of imbalanced datasets within the context of ECG data analysis [59,60,61][44][45][46]. Several studies, such as those by Rai et al. [59][44] and Shoughi et al. [61][46], propose the application of synthetic minority oversampling techniques (SMOTEs) to address the issue of imbalanced datasets in ECG data. SMOTE aims to augment the under-represented classes within the training data by generating synthetic samples that share characteristics with the existing minority samples. This approach effectively balances the class distribution, mitigating the susceptibility of DL models to overfitting and ultimately strengthening their generalizability. By reducing the bias towards the majority class, SMOTE enables the model to learn a more comprehensive representation of the underlying data distribution, leading to improved performance on unseen examples.

References

  1. Moody, G.B.; Mark, R.G. The impact of the MIT-BIH arrhythmia database. IEEE Eng. Med. Biol. Mag. 2001, 20, 45–50.
  2. Merbouti, M.A.; Cherifi, D. Machine learning based electrocardiogram peaks analyzer for Wolff-Parkinson-White syndrome. Biomed. Signal Process. Control 2023, 86, 105302.
  3. Liu, Q.; Feng, Y.; Xu, H.; Li, J.; Lin, Z.; Li, S.; Qiu, S.; WU, X.; Ma, Y. PSC-Net: Integration of Convolutional Neural Networks and Transformers for Physiological Signal Classification. SSRN 4524798. Available online: https://ouci.dntb.gov.ua/en/works/4rDDWYM9/ (accessed on 22 January 2024).
  4. Shukla, N.; Pandey, A.; Shukla, A.P.; Neupane, S.C. ECG-ViT: A transformer-based ECG classifier for energy-constraint wearable devices. J. Sens. 2022, 2022, 2449956.
  5. Al Nazi, Z.; Biswas, A.; Rayhan, M.A.; Abir, T.A. Classification of ECG signals by dot residual LSTM network with data augmentation for anomaly detection. In Proceedings of the 2019 22nd International Conference on Computer and Information Technology (ICCIT), Dhaka, Bangladesh, 18–20 December 2019; IEEE: Piscataway, NJ, USA, 2019; pp. 1–5.
  6. Clifford, G.D.; Azuaje, F.; McSharry, P. Advanced Methods and Tools for ECG Data Analysis; Artech House Boston: Norwood, MA, USA, 2006; Volume 10.
  7. Zadeh, A.E.; Khazaee, A.; Ranaee, V. Classification of the electrocardiogram signals using supervised classifiers and efficient features. Comput. Methods Programs Biomed. 2010, 99, 179–194.
  8. Mohebbian, M.R.; Marateb, H.R.; Wahid, K.A. Semi-supervised active transfer learning for fetal ECG arrhythmia detection. Comput. Methods Programs Biomed. Update 2023, 3, 100096.
  9. He, Z.; Chen, Y.; Yuan, S.; Zhao, J.; Yuan, Z.; Polat, K.; Alhudhaif, A.; Alenezi, F.; Hamid, A. A novel unsupervised domain adaptation framework based on graph convolutional network and multi-level feature alignment for inter-subject ECG classification. Expert Syst. Appl. 2023, 221, 119711.
  10. Haykin, S.; Network, N. A comprehensive foundation. Neural Netw. 2004, 2, 41.
  11. Vapnik, V. The Nature of Statistical Learning Theory; Springer Science & Business Media: New York, NY, USA, 2013.
  12. Krishna, K.; Murty, N.M. Genetic K-means algorithm. IEEE Trans. Syst. Man -Cybern.-Part B Cybern. 1999, 29, 433–439.
  13. Jolliffe, I. Principal Component Analysis; Springer: Berlin/Heidelberg, Germany, 2011.
  14. Alinsaif, S.; Lang, J. Texture features in the Shearlet domain for histopathological image classification. BMC Med. Inform. Decis. Mak. 2020, 20, 312.
  15. Murphy, K.P. Machine Learning: A Probabilistic Perspective; MIT Press: Cambridge, MA, USA, 2012.
  16. Park, J.; Lee, K.; Park, N.; You, S.C.; Ko, J. Self-Attention LSTM-FCN model for arrhythmia classification and uncertainty assessment. Artif. Intell. Med. 2023, 142, 102570.
  17. Wang, B.; Chen, G.; Rong, L.; Liu, Y.; Yu, A.; He, X.; Wen, T.; Zhang, Y.; Hu, B. Arrhythmia Disease Diagnosis Based on ECG Time–Frequency Domain Fusion and Convolutional Neural Network. IEEE J. Transl. Eng. Health Med. 2022, 11, 116–125.
  18. He, X.; Shan, W.; Zhang, R.; Heidari, A.A.; Chen, H.; Zhang, Y. Improved Colony Predation Algorithm Optimized Convolutional Neural Networks for Electrocardiogram Signal Classification. Biomimetics 2023, 8, 268.
  19. Asif, M.S.; Faisal, M.S.; Dar, M.N.; Hamdi, M.; Elmannai, H.; Rizwan, A.; Abbas, M. Hybrid Deep Learning and Discrete Wavelet Transform-Based ECG Biometric Recognition for Arrhythmic Patients and Healthy Controls. Sensors 2023, 23, 4635.
  20. Liu, S.; Zhou, B.; Ding, Q.; Hooi, B.; Zhang, Z.; Shen, H.; Cheng, X. Time series anomaly detection with adversarial reconstruction networks. IEEE Trans. Knowl. Data Eng. 2022, 35, 4293–4306.
  21. Yosinski, J.; Clune, J.; Bengio, Y.; Lipson, H. How transferable are features in deep neural networks? In Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada, 8–13 December 2014; pp. 3320–3328.
  22. Mohebbanaaz; Kumar, L.R.; Sai, Y.P. A new transfer learning approach to detect cardiac arrhythmia from ECG signals. Signal Image Video Process. 2022, 16, 1945–1953.
  23. Diker, A.; Engin, A. Feature extraction of ECG signal by using deep feature. In Proceedings of the 2019 7th International Symposium on Digital Forensics and Security (ISDFS), Barcelos, Portugal, 10–12 June 2019; IEEE: Piscataway, NJ, USA, 2019; pp. 1–6.
  24. Hong, S.; Zhou, Y.; Wu, M.; Shang, J.; Wang, Q.; Li, H.; Xie, J. Combining deep neural networks and engineered features for cardiac arrhythmia detection from ECG recordings. Physiol. Meas. 2019, 40, 054009.
  25. Mitchell, T.M. Machine Learning; McGraw Hill: Burr Ridge, IL, USA, 1997; Volume 45, pp. 870–877.
  26. Alinsaif, S.; Lang, J. 3D shearlet-based descriptors combined with deep features for the classification of Alzheimer’s disease based on MRI data. Comput. Biol. Med. 2021, 138, 104879.
  27. Lee, J.; Nam, Y.; McManus, D.D.; Chon, K.H. Time-varying coherence function for atrial fibrillation detection. IEEE Trans. Biomed. Eng. 2013, 60, 2783–2793.
  28. Oresko, J.J.; Jin, Z.; Cheng, J.; Huang, S.; Sun, Y.; Duschl, H.; Cheng, A.C. A wearable smartphone-based platform for real-time cardiovascular disease detection via electrocardiogram processing. IEEE Trans. Inf. Technol. Biomed. 2010, 14, 734–740.
  29. Alqudah, A.M.; Albadarneh, A.; Abu-Qasmieh, I.; Alquran, H. Developing of robust and high accurate ECG beat classification by combining Gaussian mixtures and wavelets features. Australas. Phys. Eng. Sci. Med. 2019, 42, 149–157.
  30. Yu, K.; Feng, L.; Chen, Y.; Wu, M.; Zhang, Y.; Zhu, P.; Chen, W.; Wu, Q.; Hao, J. Accurate wavelet thresholding method for ECG signals. Comput. Biol. Med. 2023, 169, 107835.
  31. Yildirim, Ö. A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification. Comput. Biol. Med. 2018, 96, 189–202.
  32. Cuomo, S.; De Pietro, G.; Farina, R.; Galletti, A.; Sannino, G. A revised scheme for real time ECG signal denoising based on recursive filtering. Biomed. Signal Process. Control. 2016, 27, 134–144.
  33. Upadhyay, P.; Upadhyay, S.; Shukla, K. Schrödinger Equation Based ECG Signal Denoising. Chin. J. Phys. 2022, 77, 2238–2257.
  34. Zhang, M.; Jin, H.; Zheng, B.; Luo, W. Deep Learning Modeling of Cardiac Arrhythmia Classification on Information Feature Fusion Image with Attention Mechanism. Entropy 2023, 25, 1264.
  35. Hassaballah, M.; Wazery, Y.M.; Ibrahim, I.E.; Farag, A. ECG heartbeat classification using machine learning and metaheuristic optimization for smart healthcare systems. Bioengineering 2023, 10, 429.
  36. Nascimento, N.M.M.; Marinho, L.B.; Peixoto, S.A.; do Vale Madeiro, J.P.; de Albuquerque, V.H.C.; Filho, P.P.R. Heart arrhythmia classification based on statistical moments and structural co-occurrence. Circuits Syst. Signal Process. 2020, 39, 631–650.
  37. Tuncer, T.; Dogan, S.; Pławiak, P.; Acharya, U.R. Automated arrhythmia detection using novel hexadecimal local pattern and multilevel wavelet transform with ECG signals. Knowl.-Based Syst. 2019, 186, 104923.
  38. Anand, G.; Nayak, R. DeLTa: Deep local pattern representation for time-series clustering and classification using visual perception. Knowl.-Based Syst. 2021, 212, 106551.
  39. Khan, A.; Sohail, A.; Zahoora, U.; Qureshi, A.S. A survey of the recent architectures of deep convolutional neural networks. Artif. Intell. Rev. 2020, 53, 5455–5516.
  40. Shaker, A.M.; Tantawi, M.; Shedeed, H.A.; Tolba, M.F. Generalization of convolutional neural networks for ECG classification using generative adversarial networks. IEEE Access 2020, 8, 35592–35605.
  41. Abubaker, M.B.; Babayiğit, B. Detection of cardiovascular diseases in ECG images using machine learning and deep learning methods. IEEE Trans. Artif. Intell. 2022, 4, 373–382.
  42. Dhara, S.K.; Bhanja, N.; Khampariya, P. An adaptive heart disease diagnosis via ECG signal analysis with deep feature extraction and enhanced radial basis function. Comput. Methods Biomech. Biomed. Eng. Imaging Vis. 2023, 1–23.
  43. Wei, B.; Han, Z.; He, X.; Yin, Y. Deep learning model based breast cancer histopathological image classification. In Proceedings of the 2017 IEEE 2nd International Conference on Cloud Computing and Big Data Analysis (ICCCBDA), Chengdu, China, 28–30 April 2017; IEEE: Piscataway, NJ, USA, 2017; pp. 348–353.
  44. Rai, H.M.; Chatterjee, K.; Dashkevych, S. The prediction of cardiac abnormality and enhancement in minority class accuracy from imbalanced ECG signals using modified deep neural network models. Comput. Biol. Med. 2022, 150, 106142.
  45. Liu, Z.; Chen, Y.; Zhang, Y.; Ran, S.; Cheng, C.; Yang, G. Diagnosis of arrhythmias with few abnormal ECG samples using metric-based meta learning. Comput. Biol. Med. 2023, 153, 106465.
  46. Shoughi, A.; Dowlatshahi, M.B. 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), Tehran, Iran, 3–4 March 2021; IEEE: Piscataway, NJ, USA, 2021; pp. 1–6.
More
© Text is available under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/)
Video Production Service
Feedback