Research on Electrocardiogram Abnormality Detection Method Based on Integrated Learning Models

Miaomiao Gao

doi:10.54097/2qezrq41

Authors

Miaomiao Gao

DOI:

https://doi.org/10.54097/2qezrq41

Keywords:

Electrocardiogram (ECG), AdaBoost-RF Algorithm, Deep Learning, Heartbeat Classification.

Abstract

For the early detection and prompt treatment of arrhythmias and other related problems, ECG anomaly detection is essential to the diagnostic process of cardiovascular illnesses. But for ECG anomaly detection applications, conventional single models frequently face drawbacks such overfitting and low robustness to abnormalities. To enhance the accuracy and robustness of ECG anomaly detection, this research emphasizes the application of ensemble learning techniques, particularly by constructing an ensemble model that employs the AdaBoost algorithm in conjunction with Random Forest as the base classifier. The experimental outcomes demonstrate that the ensemble model achieves outstanding performance in various assessment metrics, including precision, sensitivity, and F1 score. We validated our findings using the reputable MIT-BIH Arrhythmia Database. In particular, the model's overall accuracy was 99.53%, its recall rate for ventricular ectopic beats (V) was 99.57%, and its overall F1 score was 97.7%. The ensemble model suggested in this study exhibits notable benefits over conventional machine learning algorithms and deep methods of learning, offering strong technical support and a reference for clinical ECG diagnosis decision-making.

Downloads

Download data is not yet available.

References

[1] Wang Z W, Hu S S. Key Points Interpretation of "China Cardiovascular Health and Disease Report 2019"[J]. Chinese Journal of Cardiology, 2020, 25 (05): 401 - 410.

[2] Y. Birnbaum, K. Nikus, P. Kligfield, M. Fiol, J. A. Barrabés, A. Sionis, O. Pahlm, J. G. Niebla, and A. B. de Luna, ‘‘The role of the ECG in diagnosis, risk estimation, and catheterization laboratory activation in patients with acute coronary syndromes: A consensus document,’’ Ann. Noninvasive Electricidal., vol. 19, no. 5, pp. 412 – 425, Sep. 2014.

[3] Li, Hui, et al. "Clinical knowledge-based ECG abnormalities detection using dual-view CNN-Transformer and external attention mechanism." Computers in Biology and Medicine 178 (2024): 108751.

[4] Saini, Indu, Dilbag Singh, and Arun Khosla. "QRS detection using K-Nearest Neighbor algorithm (KNN) and evaluation on standard ECG databases." Journal of advanced research 4.4 (2013): 331 - 344.

[5] Pham, Huy, et al. "Machine learning-based detection of cardiovascular disease using ECG signals: performance vs. complexity." Frontiers in Cardiovascular Medicine 10 (2023): 1229743.

[6] Liu, X., Wang, H., Li, Z., & Qin, L. (2021). Deep learning in ECG diagnosis: A review. Knowledge-Based Systems, 227, 107187.

[7] Singh, Anupreet Kaur, and Sridhar Krishnan. "ECG signal feature extraction trends in methods and applications." BioMedical Engineering OnLine 22.1 (2023): 22.

[8] Indu Saini, Dilbag Singh, Arun Khosla, QRS detection using K-Nearest Neighbor algorithm (KNN) and evaluation on standard ECG databases, Journal of Advanced Research, Volume 4, Issue 4, 2013, Pages 331 - 344, ISSN 2090 - 1232.

[9] Hamza, Sihem, and Yassine Ben Ayed. "Svm for human identification using the ECG signal." Procedia computer science 176 (2020): 430 - 439.

[10] Manna, Tishya, Aleena Sweta Padma, and Moloud Abdar. “Decision Tree Predictive Learner-Based Approach for False Alarm Detection in ICU.” Journal of Medical Systems 43, no. 7 (May 21, 2019): 191.

[11] Wang, Haoren, Haotian Shi, Xiaojun Chen, Liqun Zhao, Yixiang Huang, and Chengliang Liu. “An Improved Convolutional Neural Network Based Approach for Automated Heartbeat Classification.” Journal of Medical Systems 44, no. 2 (December 18, 2019): 35.

[12] Chen Chen, Zhengchun Hua, Ruiqi Zhang, Guangyuan Liu, and Wanhui Wen. “Automated Arrhythmia Classification Based on a Combination Network of CNN and LSTM.” Biomedical Signal Processing and Control 57 (March 1, 2020): 101819.

[13] Karim, F., Majumdar, S., Darabi, H., & Harford, S. (2019). Multivariate LSTM-FCNs for time series classification. Neural networks, 116, 237 - 245.

[14] Hannun, Awni Y., Pranav Rajpurkar, Masoumeh Haghpanahi, Geoffrey H. Tison, Codie Bourn, Mintu P. Turakhia, and Andrew Y. Ng. “Cardiologist-Level Arrhythmia Detection and Classification in Ambulatory Electrocardiograms Using a Deep Neural Network.” Nature Medicine 25, no. 1 (January 1, 2019): 65 – 69.

[15] Sexton, Joseph, and Petter Laake. "Standard errors for bagged and random forest estimators." Computational Statistics & Data Analysis 53.3 (2009): 801 - 811.

[16] Dogan, Alican, and Derya Birant. "A weighted majority voting ensemble approach for classification." 2019 4th International Conference on Computer Science and Engineering (UBMK). IEEE, 2019.

[17] S. Kiranyaz, T. Ince and M. Gabbouj, "Real-Time Patient-Specific ECG Classification by 1-D Convolutional Neural Networks," in IEEE Transactions on Biomedical Engineering, vol. 63, no. 3, pp. 664 - 675, March 2016.

[18] Ghiasi, Mohammad M., Sohrab Zendehboudi, and Ali Asghar Mohseni pour. "Decision tree-based diagnosis of coronary artery disease: CART model." Computer methods and programs in biomedicine 192 (2020): 105400.

[19] Loh, W. Y. (2011). Classification and regression trees. Wiley interdisciplinary reviews: data mining and knowledge discovery, 1 (1), 14 - 23.

[20] Chen, C., Hua, Z., Zhang, R., Liu, G., & Wen, W. (2020). Automated arrhythmia classification based on a combination network of CNN and LSTM. Biomedical Signal Processing and Control, 57, 101819.

[21] Xu, X., Jeong, S., & Li, J. (2020). Interpretation of electrocardiogram (ECG) rhythm by combined CNN and BiLSTM. Ieee Access, 8, 125380 - 125388.