An Interval-Informed Hybrid CNN-LSTM for Ten-Category ECG Beat and Event Classification
- I Putu Bagus Erix Wijaya Telkom University, Bandung, Indonesia
- Arda Ardiyansyah Telkom University, Bandung, Indonesia
-
Satria Mandala
*
Telkom University, Bandung,
Indonesia
(*) Corresponding Author
Abstract
Automated electrocardiogram (ECG) classification remains challenging because waveform-based deep-learning models capture rich morphology, whereas clinically relevant conduction and timing intervals are not always represented explicitly. This study investigates whether a compact interval-informed representation can retain useful discriminative information for ten ECG beat and event categories. MIT-BIH Arrhythmia Database recordings were filtered and divided into seven-second segments. RR, PR, and QT intervals and QRS width were summarized using minimum, maximum, mean, median, skewness, and kurtosis, yielding 24 features. To prevent information leakage, the original samples were partitioned before oversampling; feature scaling and SMOTE were applied only to training data, while validation and held-out test data retained their original distributions. Leakage-controlled five-fold cross-validation yielded 92.15% ± 0.43% accuracy and 86.78% ± 0.68% macro-F1. On the untouched 826-sample test set, the model achieved 92.62% accuracy, 87.49% macro-F1, and 92.68% weighted F1. The most frequent bidirectional errors occurred between Normal and Premature Ventricular Contraction beats. These results support the use of interval-statistical features as a compact representation for multicategory ECG analysis, while showing that rare-class performance and fiducial reliability remain limiting factors for broader clinical use.
Downloads
References
G. B. Moody and R. G. Mark, “The impact of the MIT-BIH Arrhythmia Database,” IEEE Engineering in Medicine and Biology Magazine, vol. 20, no. 3, pp. 45–50, 2001, doi: 10.1109/51.932724.
X. Xu, S. Jeong, and J. Li, “Interpretation of Electrocardiogram (ECG) rhythm by combined CNN and BiLSTM,” IEEE Access, vol. 8, pp. 125380–125388, 2020, doi: 10.1109/ACCESS.2020.3006707.
J. Zhang, A. Liu, M. Gao, X. Chen, X. Zhang, and X. Chen, “ECG-based multi-class arrhythmia detection using spatio-temporal attention-based convolutional recurrent neural network,” Artif. Intell. Med., vol. 106, p. 101856, 2020, doi: 10.1016/j.artmed.2020.101856.
G. Petmezas and others, “Automated atrial fibrillation detection using a hybrid CNN-LSTM network on imbalanced ECG datasets,” Biomed. Signal Process. Control, vol. 63, p. 102194, 2021, doi: 10.1016/j.bspc.2020.102194.
M. Jiang et al., “HADLN: Hybrid attention-based deep learning network for automated arrhythmia classification,” Front. Physiol., vol. 12, p. 683025, 2021, doi: 10.3389/fphys.2021.683025.
Y. M. Obeidat and A. M. Alqudah, “A hybrid lightweight 1D CNN-LSTM architecture for automated ECG beat-wise classification,” Traitement du Signal, vol. 38, no. 5, pp. 1281–1291, 2021, doi: 10.18280/ts.380503.
E. Essa and X. Xie, “An ensemble of deep learning-based multi-model for ECG heartbeats arrhythmia classification,” IEEE Access, vol. 9, pp. 103452–103464, 2021, doi: 10.1109/ACCESS.2021.3098986.
P. Madan, V. Singh, D. P. Singh, M. Diwakar, B. Pant, and A. Kishor, “A hybrid deep learning approach for ECG-based arrhythmia classification,” Bioengineering, vol. 9, no. 4, p. 152, 2022, doi: 10.3390/bioengineering9040152.
J. Rahul and L. D. Sharma, “Automatic cardiac arrhythmia classification based on hybrid 1-D CNN and Bi-LSTM model,” Biocybern. Biomed. Eng., vol. 42, no. 1, pp. 312–324, 2022, doi: 10.1016/j.bbe.2022.02.006.
S. Sowmya and D. Jose, “Contemplate on ECG signals and classification of arrhythmia signals using CNN-LSTM deep learning model,” Measurement: Sensors, vol. 24, p. 100558, 2022, doi: 10.1016/j.measen.2022.100558.
T. H. Rafi and Y. W. Ko, “HeartNet: Self multihead attention mechanism via convolutional network with adversarial data synthesis for ECG-based arrhythmia classification,” IEEE Access, vol. 10, pp. 100501–100512, 2022, doi: 10.1109/ACCESS.2022.3206431.
M. S. Islam and others, “HARDC: A novel ECG-based heartbeat classification method to detect arrhythmia using hierarchical attention based dual structured RNN with dilated CNN,” Neural Networks, vol. 162, pp. 271–287, 2023, doi: 10.1016/j.neunet.2023.03.004.
N. Alamatsaz, L. Tabatabaei, M. Yazdchi, H. Payan, N. Alamatsaz, and F. Nasimi, “A lightweight hybrid CNN-LSTM explainable model for ECG-based arrhythmia detection,” Biomed. Signal Process. Control, vol. 90, p. 105884, 2024, doi: 10.1016/j.bspc.2023.105884.
A. Eleyan and E. Alboghbaish, “Electrocardiogram signals classification using deep-learning-based incorporated convolutional neural network and long short-term memory framework,” Computers, vol. 13, no. 2, p. 55, 2024, doi: 10.3390/computers13020055.
A. Sun, W. Hong, J. Li, and J. Mao, “An arrhythmia classification model based on a CNN-LSTM-SE algorithm,” Sensors, vol. 24, no. 19, p. 6306, 2024, doi: 10.3390/s24196306.
N. Sharma, R. K. Sunkaria, and A. Kaur, “Electrocardiogram heartbeat classification using machine learning and ensemble convolutional neural network-bidirectional long short-term memory technique,” IEEE Transactions on Artificial Intelligence, vol. 5, no. 6, pp. 2816–2827, 2024, doi: 10.1109/TAI.2023.3324627.
H. Anu, S. Rathnakara, and S. Mallikarjunaswamy, “Enhanced ECG signal classification with CNN-LSTM networks using Aquila optimization,” Engineering, Technology & Applied Science Research, vol. 15, no. 3, pp. 23461–23466, 2025, doi: 10.48084/etasr.10492.
Y. Ye, K. Chipusu, M. A. Ashraf, B. Ding, Y. Huang, and J. Huang, “Hybrid CNN-BLSTM architecture for classification and detection of arrhythmia in ECG signals,” Sci. Rep., vol. 15, p. 34510, 2025, doi: 10.1038/s41598-025-17671-1.
A. S. Ba Mahel, F. M. G. Alotaibi, Z. M. Lonseko, and N.-N. Rao, “XABH-CNN-GRU: Explainable attention-based hybrid CNN-GRU model for accurate identification of common arrhythmias,” Journal of Electronic Science and Technology, vol. 23, no. 3, p. 100322, 2025, doi: 10.1016/j.jnlest.2025.100322.
K. Saranya, U. Karthikeyan, A. S. Kumar, A. O. Salau, and T. T. Tin, “DenseNet-ABiLSTM: Revolutionizing multiclass arrhythmia detection and classification using hybrid deep learning approach leveraging PPG signals,” International Journal of Computational Intelligence Systems, vol. 18, p. 33, 2025, doi: 10.1007/s44196-025-00765-z.
Y. Wang and S. Rani, “Hybrid CNN-LSTM model for ECG-based arrhythmia detection in Internet of Medical Things,” Discover Internet of Things, vol. 6, no. 1, p. 7, 2026, doi: 10.1007/s43926-025-00131-7.
G. S. Manivannan and others, “An efficient deep CNN based BiLSTM framework with RanA optimization for accurate cardiac arrhythmia detection,” Sci. Rep., vol. 16, p. 7156, 2026, doi: 10.1038/s41598-026-38227-x.
E. A. Dinsel and H. Kodaz, “A lightweight and robust parallel CNN-LSTM network with random crop augmentation for single-lead raw ECG arrhythmia classification,” Engineering Science and Technology, an International Journal, vol. 79, p. 102417, 2026, doi: 10.1016/j.jestch.2026.102417.
M. T. Al-Bairmani, M. Yazdchi, and F. Nasimi, “A joint CNN-Bi-LSTM-Transformer architecture with SHAP explanations for multi-label arrhythmia detection from 12-lead ECGs,” Sci. Rep., vol. 16, p. 11123, 2026, doi: 10.1038/s41598-026-40925-5.
A. Ardiyansyah and S. Mandala, “Accurate model for arrhythmia classification using hybrid attention-based convolutional neural network and gated recurrent units with explainable artificial intelligence,” in Proc. 12th International Conference on Information and Communication Technology (ICoICT), 2024, pp. 57–64. doi: 10.1109/ICoICT61617.2024.10698622.
A. Singh and S. Krishnan, “ECG signal feature extraction trends in methods and applications,” Biomed. Eng. Online, vol. 22, p. 22, 2023, doi: 10.1186/s12938-023-01075-1.
N. Rastogi and R. Mehra, “Analysis of Butterworth and Chebyshev filters for ECG denoising using wavelets,” IOSR Journal of Electronics and Communication Engineering, vol. 6, no. 6, pp. 37–44, 2013, doi: 10.9790/2834-0663744.
J. Emrich, T. Koka, S. Wirth, and M. Muma, “Accelerated sample-accurate R-peak detectors based on visibility graphs,” in Proc. 31st European Signal Processing Conference (EUSIPCO), Helsinki, Finland, 2023, pp. 1090–1094. doi: 10.23919/EUSIPCO58844.2023.10290007.
T. N. Alotaiby, S. R. Alrshoud, S. A. Alshebeili, and L. M. Aljafar, “ECG-based subject identification using statistical features and random forest,” J. Sens., vol. 2019, p. 6751932, 2019, doi: 10.1155/2019/6751932.
N. V Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, “SMOTE: Synthetic minority over-sampling technique,” Journal of Artificial Intelligence Research, vol. 16, pp. 321–357, 2002, doi: 10.1613/jair.953.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel An Interval-Informed Hybrid CNN-LSTM for Ten-Category ECG Beat and Event Classification
Pages: 859-880
Copyright (c) 2026 I Putu Bagus Erix Wijaya, Arda Ardiyansyah, Satria Mandala
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
