Explainable AI-Powered ECG Anomaly Detection Using SHAP and LSTM Autoencoders
Received: 23 January 2026 | Revised: 7 March 2026 | Accepted: 15 March 2026 | Online: 6 April 2026
Corresponding author: K. Nayana
Abstract
Cardiovascular diseases are the leading cause of mortality, underscoring the need for accurate and early detection of cardiac abnormalities. This study proposes a Long Short-Term Memory (LSTM) autoencoder framework for automated Electrocardiogram (ECG) anomaly detection, integrated with SHapley Additive exPlanations (SHAP) to ensure transparent and clinically interpretable decision-making. Using the ECG5000 dataset, the model learns the intrinsic characteristics of normal cardiac cycles and identifies deviations through reconstruction error analysis. The proposed framework achieved an accuracy of 97.6%, a precision of 95.8%, and an F1-score 96.7%, outperforming traditional machine-learning baselines and earlier deep-learning approaches. SHAP-based visualization highlights the specific temporal segments influencing anomaly predictions, enhancing clinical trust and applicability. This work demonstrates a robust, explainable, and efficient approach, suitable for real-time cardiac monitoring.
Keywords:
ECG anomaly detection, LSTM autoencoders, explainable AI, SHAPDownloads
References
A. Y. Hannun et al., "Cardiologist-Level Arrhythmia Detection and Classification in Ambulatory Electrocardiograms Using a Deep Neural Network," Nature Medicine, vol. 25, no. 1, pp. 65–69, Jan. 2019.
C.-H. Hsieh, Y.-S. Li, B.-J. Hwang, and C.-H. Hsiao, "Detection of Atrial Fibrillation Using 1D Convolutional Neural Network," Sensors, vol. 20, no. 7, Apr. 2020, Art. no. 2136.
P. Malhotra, L. Vig, G. Shroff, and P. Agarwal, "Long Short-Term Memory Networks for Anomaly Detection in Time Series," in Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges, Belgium, Apr. 2015, pp. 89–94.
S. Lundberg and S.-I. Lee, "A Unified Approach to Interpreting Model Predictions." arXiv, 2017.
U. R. Acharya, H. Fujita, S. L. Oh, Y. Hagiwara, J. H. Tan, and M. Adam, "Application of Deep Convolutional Neural Network for Automated Detection of Myocardial Infarction Using ECG Signals," Information Sciences, vol. 415–416, pp. 190–198, Nov. 2017.
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, May 2001.
S. Osowski, L. T. Hoai, and T. Markiewicz, "Support Vector Machine-Based Expert System for Reliable Heartbeat Recognition," IEEE Transactions on Biomedical Engineering, vol. 51, no. 4, pp. 582–589, Apr. 2004.
O. AlZoubi, N. AlAbabneh, I. Hmeidi, and M. Bani Yassein, "A Deep Learning System for the Diagnosis of Heart Problems from ECG Media Files," International Journal on Communications Antenna and Propagation, vol. 11, no. 5, Oct. 2021, Art. no. 363.
Haibo He and E. A. Garcia, "Learning from Imbalanced Data," IEEE Transactions on Knowledge and Data Engineering, vol. 21, no. 9, pp. 1263–1284, Sep. 2009.
Y. Xia, N. Wulan, K. Wang, and H. Zhang, "Detecting Atrial Fibrillation by Deep Convolutional Neural Networks," Computers in Biology and Medicine, vol. 93, pp. 84–92, Feb. 2018.
T. Chen and C. Guestrin, "XGBoost: A Scalable Tree Boosting System," in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, Aug. 2016, pp. 785–794.
C. K. N., Neelappa, M. T. Sreedevi, and R. Asha, "Hybrid Deep Learning Models for Accurate ECG Classification in Cardiovascular Disease Diagnosis," Engineering, Technology & Applied Science Research, vol. 15, no. 5, pp. 26683–26688, Oct. 2025.
S. M. Lundberg et al., "From Local Explanations to Global Understanding with Explainable AI for Trees," Nature Machine Intelligence, vol. 2, no. 1, pp. 56–67, Jan. 2020.
Y. Chen and E. Keogh, "Dataset: ECG5000." Time Series Classification, Mar. 2020, [Online]. Available: https://www.timeseriesclassification.com/description.php?Dataset=ECG5000.
Downloads
How to Cite
License
Copyright (c) 2026 K. Nayana, S. Vinay
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 the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement 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 acknowledgement 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) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
