Abstract
Cardiovascular diseases (CVDs) are leading causes of mortality all over the world, and arrhythmias are a leading cause of cardiac mortality. Arrhythmia detection in a timely and accurate manner is essential for medical intervention and plays a very important role in modern healthcare. In this work, the proposed automated arrhythmia identification process involves data collection from the PhysioNet repository such as AF, CHF and NSR-related ECG signals. Arrhythmia features are extracted through a CapsNet by capturing spatial hierarchies and relations in the ECG signals in an efficient manner. Features are filtered and optimized through feature selection by Deep CNNs such as EfficientNet B3, ResNet152, DenseNet201, and VGG19 to consider only the most significant features for the purpose of classification. These features are classified through BiLSTM by employing its sequential learning capability to learn temporal dependencies in the ECG signal and enhance the accuracy of the classifier. RanA hyperparameter optimization is also employed to optimize the model parameters further to achieve improved performance. The purpose of this work is to classify different types of ECG signals by formulating classification problems in which the abnormal heart arrhythmias are compared with NSR. Especially, the classification problems involve the discrimination of AF vs. NSR and CHF vs. NSR. The findings reveal EfficientNet B3 + BiLSTM + RanA performing outstandingly in AF vs. NSR and CHF vs. NSR classification with the use of multiple deep learning techniques in an optimal architecture. The model achieves an impressive accuracy of 99.48% in AF vs. NSR and 99.32% in CHF vs. NSR and outperforms other methods in the literature. With computational efficiency and accuracy, the proposed approach provides an optimal and reliable solution for real time cardiac disease diagnosis.
Data availability
The datasets analyzed during the current study are available in the PhysioNet repository, https://physionet.org/about/database/#open.
References
Rogers, A. J. et al. Identification of cardiac wall motion abnormalities in diverse populations by deep learning of the electrocardiogram. Npj Digit. Med. 8, 21 (2025).
Bouzid, Z. et al. Electrocardiogram-based machine learning for risk stratification of patients with suspected acute coronary syndrome. Eur. Heart J. ehae880 (2025).
Ha, F. J., Chong, T., Cook, M. J. & Paratz, E. D. Epilepsy and cardiac arrhythmias: a state-of-the-art review. Clin. Electrophysiol. 11, 217–229 (2025).
Guo, Z. et al. Improving atrial fibrillation detection using a shared latent space for ECG and PPG signals. Harv. Data Sci. Rev. 7, (2025).
Pukkila, T., Molkkari, M., Hernesniemi, J., Kanniainen, M. & Räsänen, E. Detection of congestive heart failure from RR intervals during long-term ECG recordings. Heart Rhythm O2 (2025).
Bulut, M. G., Unal, S., Hammad, M. & Pławiak, P. Deep CNN-based detection of cardiac rhythm disorders using PPG signals from wearable devices. PloS One. 20, e0314154 (2025).
Fan, L., Chen, B., Zeng, X., Zhou, J. & Zhang, X. Knowledge-enhanced meta-transfer learning for few-shot ECG signal classification. Expert Syst. Appl. 263, 125764 (2025).
Manivannan, G. S., Babu, C. G. & Rajaguru, H. Amelioration of multitudinous classifiers performance with hyper-parameters tuning in elephant search optimization for cardiac arrhythmias detection. J. Supercomput. 80, 14848–14924 (2024).
Serhani, M. A., Ismail, H., El-Kassabi, H. T. & Al Breiki, H. Enhancing arrhythmia prediction through an adaptive deep reinforcement learning framework for ECG signal analysis. Biomed. Signal Process. Control. 101, 107155 (2025).
Kim, Y. & Choi, C. Utilization of a hierarchical electrocardiogram classification model for enhanced biometric identification. Comput. Biol. Med. 184, 109254 (2025).
Zhang, Y. et al. A sequential MAE-clustering self-supervised learning method for arrhythmia detection. Expert Syst. Appl. 269, 126379 (2025).
Zhang, X. et al. A multi-scale feature-based transformer model for arrhythmia classification. Biomed. Signal Process. Control. 100, 106968 (2025).
Ochoa, E. J. & Revilla, L. C. A convolutional neural network for early supraventricular arrhythmia identification. Eng. Proc. 83, 8 (2025).
Nguimdo, R. T. & Tiedeu, A. Automated ECG Analysis with Dual-Channel SqueezeNet Using Hilbert Huang Transform, Fuzzy Entropy, and Circuits, Systems, and Signal Processing 1–26 (2025).
Shankar, M. G., Babu, C. G. & Rajaguru, H. Classification of cardiac diseases from ECG signals through bio inspired classifiers with Adam and R-Adam approaches for hyperparameters updation. Measurement 194, 111048 (2022).
Kim, E., Kim, J., Park, J., Ko, H. & Kyung, Y. TinyML-based classification in an ECG monitoring embedded system. Computers Mater. Continua. 75, 1751–1764 (2023).
Majeed, F. et al. Detection of atrial fibrillation and normal sinus rhythm using multiple machine learning classifiers. J. Med. Imaging Health Inf. 11, 1453–1462 (2021).
Sherly, S. I. & Mathivanan, G. An efficient honey badger based faster region CNN for chronc heart failure prediction. Biomed. Signal Process. Control. 79, 104165 (2023).
Raza, M. A. et al. Classification of electrocardiogram signals for arrhythmia detection using convolutional neural network. Computers Mater. Continua. 77, 3817–3834 (2023).
Olanrewaju, R. F., Ibrahim, S. N., Asnawi, A. L. & Altaf, H. Classification of ECG signals for detection of arrhythmia and congestive heart failure based on continuous wavelet transform and deep neural networks. Indonesian J. Electr. Eng. Comput. Sci. 22, 1520–1528 (2021).
Çınar, A. & Tuncer, S. A. Classification of normal sinus rhythm, abnormal arrhythmia and congestive heart failure ECG signals using LSTM and hybrid CNN-SVM deep neural networks. Comput. Methods Biomech. BioMed. Eng. 24, 203–214 (2021).
Rao, B. M. & Kumar, A. Congestive heart failure detection based on electrocardiomatrix method with ECG signal. Comput. Assist. Methods Eng. Sci. 30, 291–304 (2023).
Kumar, A. S. & Rekha, R. An improved hawks optimizer based learning algorithms for cardiovascular disease prediction. Biomed. Signal. Process. Control. 81, 104442 (2023).
Arunachalam, S. K. & Rekha, R. A novel approach for cardiovascular disease prediction using machine learning algorithms. Concurr Comput. 34, (2022).
Anu, H., Rathnakara, S. & Mallikarjunaswamy, S. Enhanced ECG signal classification with CNN-LSTM networks using aquila optimization. Eng. Technol. Appl. Sci. Res. 15, 23461–23466 (2025).
Sun, A., Hong, W., Li, J. & Mao, J. An arrhythmia classification model based on a CNN-LSTM-SE algorithm. Sensors 24, 6306 (2024).
Akkuş, M., Karabatak, M. & Tekin, R. Classification of ECG signals encrypted with CNN based autoencoder with LSTM. In 2024 12th International Symposium on Digital Forensics and Security (ISDFS) 01–06 (IEEE, 2024).
Sowmya, S. & Jose, D. Contemplate on ECG signals and classification of arrhythmia signals using CNN-LSTM deep learning model. Measurement: Sens. 24, 100558 (2022).
Alamatsaz, N. et al. A lightweight hybrid CNN-LSTM explainable model for ECG-based arrhythmia detection. Biomed. Signal Process. Control. 90, 105884 (2024).
Moody, G. B. PhysioNet. In Encyclopedia of Computational Neuroscience, 2806–2808 (Springer, 2022).
Ghosh, S. & Chander, S. A precise deep learning-based ECG arrhythmia classification scheme using deep bidirectional capsule network classifier. Int. J. Comput. Sci. Eng. 28, 127–141 (2025).
Kumar, A. S. & Rekha, R. A dense network approach with Gaussian optimizer for cardiovascular disease prediction. New. Gener Comput. https://doi.org/10.1007/s00354-023-00234-1 (2023).
Rodríguez, R., Mexicano, A., Bila, J., Cervantes, S. & Ponce, R. Feature extraction of electrocardiogram signals by applying adaptive threshold and principal component analysis. J. Appl. Res. Technol. 13, 261–269 (2015).
Rajagopal, R. & Ranganathan, V. Evaluation of effect of unsupervised dimensionality reduction techniques on automated arrhythmia classification. Biomed. Signal. Process. Control. 34, 1–8 (2017).
Yeh, Y. C., Wang, W. J. & Chiou, C. W. Cardiac arrhythmia diagnosis method using linear discriminant analysis on ECG signals. Measurement 42, 778–789 (2009).
Chang, C. D., Wang, C. C. & Jiang, B. C. Singular value decomposition based feature extraction technique for physiological signal analysis. J. Med. Syst. 36, 1769–1777 (2012).
Bahaj, M. et al. Advanced cardiovascular disease diagnosis with machine learning: Exploring KBest, t-SNE, grid search, and ensemble methods. In 2023 IEEE International Conference on Advances in Data-Driven Analytics And Intelligent Systems (ADACIS) 1–6 (IEEE, 2023).
Suh, J. et al. Learning ECG representations for multi-label classification of cardiac abnormalities. In 2021 Computing in Cardiology (CinC) Vol. 48, 1–4 (IEEE, 2021).
Ghaffari, A. & Madani, N. Atrial fibrillation identification based on a deep transfer learning approach. Biomedical Phys. Eng. Express. 5, 035015 (2019).
Ullah, H. et al. An end-to-end cardiac arrhythmia recognition method with an effective DenseNet model on imbalanced datasets using ECG signal. Comput. Intell. Neurosci. 2022, 9475162 (2022).
Ezz, M. Deep learning-driven single-lead ECG classification: A rapid approach for comprehensive cardiac diagnostics. Diagnostics 15, 384 (2025).
Xie, Y. L. & Lin, C. W. Imbalanced ectopic beat classification using a low-memory-usage CNN LMUEBCNet and correlation-based ECG signal oversampling. Mathematics 11, 1833 (2023).
Venkatesh, N. P., Kumar, R. P., Neelapu, B. C., Pal, K. & Sivaraman, J. Automated atrial arrhythmia classification using 1D-CNN-BiLSTM: A deep network ensemble model. Biomed. Signal Process. Control. 97, 106703 (2024).
Saranya, K., Karthikeyan, U., Kumar, A. S., Salau, A. O. & Tin Tin, T. DenseNet-ABiLSTM: revolutionizing multiclass arrhythmia detection and classification using hybrid deep learning approach leveraging PPG signals. Int. J. Comput. Intell. Syst. 18, (2025).
Manivannan, G. S., Mani, K., Rajaguru, H. & Talawar, S. V. Detection of alcoholic EEG signal using LASSO regression with metaheuristics algorithms based LSTM and enhanced artificial neural network classification algorithms. Sci. Rep. 14, 21437 (2024).
Author information
Authors and Affiliations
Contributions
Gowri Shankar Manivannan: Conceptualization, Methodology, Validation, Software, Formal analysis, Visualization, Writing – original draft. Satish V. Talawar and M. G. Vasundhara : Formal analysis, Visualization and Review. A. Karthik Lal, S. M. Gagana, S. K. Hemanth and H. L. Srijan Gowda : Data Collection and Visualization.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Manivannan, G.S., Talawar, S.V., Vasundhara, M.G. et al. An efficient deep CNN based BiLSTM framework with RanA optimization for accurate cardiac arrhythmia detection. Sci Rep (2026). https://doi.org/10.1038/s41598-026-38227-x
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-38227-x
