Heart failure detection using deep learning and Gradient Boosting classifier

Abstract

Heart failure (HF) is marked by a diminished capacity of the heart to effectively pump blood. Traditionally, the electrocardiogram (ECG) has served as a non-invasive diagnostic tool, gauging the heart's electrical activity and rhythm. Recent advancements have leveraged machine learning (ML) and deep learning (DL) techniques to automate the identification and classification of HF types from ECG data. This study introduces a novel deep learning architecture, blending the efficacy of a convolutional neural network (CNN) for feature extraction with an eXtreme Gradient Boosting (XGBoost) layer for final classification. The first CNN model operates on ECG segments in the time domain, while the second CNN processes the Continuous Wavelet Transform (CWT) of the same segments. This composite model offers superior automatic HF detection, particularly with 2-second ECG fragments, by capturing intricate features from both time and frequency domains. Training and testing utilize datasets from the MIT-BIH, BIDMC, and PTB Diagnostic ECG databases. Through 10-fold cross-validation, the proposed approach attains remarkable accuracy, sensitivity, and F1-score, all surpassing 99.9\%. This modality represents a significant stride in DL applications for ECG diagnosis, holding promise for enhanced clinical utility.

Keywords

• Convolutional neural network
• deep learning
• electrocardiogram
• eXtreme Gradient Boosting
• heart failure.

References

1. [1] A. A. Inamdar and A. C. Inamdar, ‘‘Heart failure: diagnosis, management and utilization,’’ Journal of Clinical Medicine, vol. 5, no. 7, p. 62, Jun 2016.
2. [2] P. A. H. et al., ‘‘2022 american college of cardiology/american heart association/heart failure society of america guideline for the management of heart failure: executive summary,’’ Journal of Cardiac Failure, vol. 28, no. 5, pp. 810–830, May 2022.
3. [3] N. R. A. H. Kashou and P. A. Noseworthy, ‘‘Ecg interpretation: clinical relevance challenges and advances,’’ Hearts, vol. 2, no. 4, pp. 505–513, Nov 2021.
4. [4] J. Schläpfer and H. J. Wellens, ‘‘Computer-interpreted electrocardiograms: benefits and limitations,’’ Journal of the American College of Cardiology, vol. 70, no. 9, pp. 1183–1192, Aug 2017.
5. [5] W. B. A. et al., ‘‘Implementing machine learning in interventional cardiology: the benefits are worth the trouble,’’ Frontiers in Cardiovascular Medicine, vol. 8, p. 711401, Dec 2021.
6. [6] S. M. et al., ‘‘Artificial intelligence for clinical decision support for monitoring patients in cardiovascular icus: A systematic review,’’ Frontiers in Medicine, vol. 10, p. 1109411, Mar 2023.
7. [7] M. A. Rahman and A. Tumian, ‘‘Variables influencing machine learning-based cardiac decision support system: A systematic literature review,’’ Applied Mechanics and Materials, vol. 892, pp. 274–283, Jul 2019.
8. [8] B. Mahesh, ‘‘Machine learning algorithms-a review,’’ International Journal of Science and Research (IJSR), vol. 9, no. 1, pp. 381–386, Jan 2020.

9. [9] S. S. et al., ‘‘Convolutional neural networks for radiologic images: a radiologist’s guide,’’ Radiology, vol. 290, no. 3, pp. 590–606, Mar 2019.
10. [10] J. Xue and L. Yu, ‘‘Applications of machine learning in ambulatory ecg,’’ Hearts, vol. 2, no. 4, pp. 472–494, Oct 2021.
11. [11] I. U. H. I. Haq and B. Xu, ‘‘Artificial intelligence in personalized cardiovascular medicine and cardiovascular imaging,’’ Cardiovascular Diagnosis and Therapy, vol. 11, no. 3, p. 911, Jun 2021.
12. [12] L. C. Y. Q. B. J. Schmidt and G.W.Wei, ‘‘Review of applications and challenges of quantitative systems pharmacology modeling and machine learning for heart failure,’’ Journal of Pharmacokinetics and Pharmacodynamics, pp. 1–2, Feb 2022.
13. [13] M. H. Asyali, ‘‘Discrimination power of long-term heart rate variability measures,’’ in Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No. 03CH37439), vol. 1, Sep 2003, pp. 200–203.
14. [14] Z. J. Y. Sun and A. C. Cheng, ‘‘Predicting cardiovascular disease from real-time electrocardiographic monitoring: An adaptive machine learning approach on a cell phone,’’ in 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Sep 2009, pp. 6889–6892.
15. [15] W. C. G. L. S. S. Q. Jiang and H. Nguyen, ‘‘A chf detection method based on deep learning with rr intervals,’’ in 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Jul 2017, pp. 3369–3372.
16. [16] Z. Masetic and A. Subasi, ‘‘Congestive heart failure detection using random forest classifier,’’ Computer Methods and Programs in Biomedicine, vol. 130, pp. 54–64, Jul 2016.
17. [17] M. Liu and Y. Kim, ‘‘Classification of heart diseases based on ecg signals using long short-term memory,’’ in 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Jul 2018, pp. 2707–2710.
18. [18] U. R. A. et al., ‘‘Deep convolutional neural network for the automated diagnosis of congestive heart failure using ecg signals,’’ Applied Intelligence, vol. 49, pp. 16–27, Jan 2019.
19. [19] J. C. Q. Zou and Y. Zhao, ‘‘Ecg signal classification based on deep cnn and bilstm,’’ BMC Medical Informatics and Decision Making, vol. 21, pp. 1–2, Dec 2021.
20. [20] C. Padmavathi and S. V. Veenadevi, ‘‘Heart disease recognition from ecg signal using deep learning,’’ International Journal of Advanced Science and Technology, vol. 29, no. 5, pp. 2303–2316, 2020, online.
21. [21] O. S. L. et al., ‘‘Comprehensive electrocardiographic diagnosis based on deep learning,’’ Artificial Intelligence in Medicine, vol. 103, p. 101789, Mar 2020.
22. [22] Y. Zhang and M. Xia, ‘‘Application of deep neural network for congestive heart failure detection using ecg signals,’’ in Journal of Physics: Conference Series, vol. 1642, no. 1, Sep 2020, p. 012021.
23. [23] S. Kusuma and K. R. Jothi, ‘‘Ecg signals-based automated diagnosis of congestive heart failure using deep cnn and lstm architecture,’’ Biocybernetics and Biomedical Engineering, vol. 42, no. 1, pp. 247–257, Jan 2022.
24. [24] J. B. F. Mourad-Chehade and D. Laplanche, ‘‘Cnn and svm-based models for the detection of heart failure using electrocardiogram signals,’’ Sensors, vol. 22, no. 23, p. 9190, Nov 2022.
25. [25] A. A. R. M. K. Elbashir and A. M. Ahmed, ‘‘Ecg heartbeat classification using convxgb model,’’ Electronics, vol. 11, no. 15, p. 2280, Jul 2022.
26. [26] T. W. et al., ‘‘Automatic ecg classification using continuous wavelet transform and convolutional neural network,’’ Entropy, vol. 23, no. 1, p. 119, Jan 2021.
27. [27] R. Mogili and G. Narsimha, ‘‘Detection of cardiac arrhythmia from ecg using cnn and xgboost,’’ International Journal of Intelligent Engineering & Systems, vol. 15, no. 2, 2022.
28. [28] G. Premalatha and V. T. Bai, ‘‘Design and implementation of intelligent patient in-house monitoring system based on efficient xgboost-cnn approach,’’ Cognitive Neurodynamics, vol. 16, no. 5, pp. 1135–1149, 2022.
29. [29] F. K. X. Y. Z. Yuan and A. U. Rehman, ‘‘Ecg classification using 1-d convolutional deep residual neural network,’’ Plos One, vol. 18, no. 4, p. e0284791, 2023.
30. [30] A. A.-J. S. A.-A. S. Islam and A. M. Artoli, ‘‘Person identification with arrhythmic ecg signals using deep convolution neural network,’’ Scientific Reports, vol. 14, no. 1, p. 4431, 2024.
31. [31] B. Majhi and A. Kashyap, ‘‘Explainable ai-driven machine learning for heart disease detection using ecg signal,’’ Applied Soft Computing, vol. 167, p. 112225, 2024.
32. [32] D. S. B. et al., ‘‘Survival of patients with severe congestive heart failure treated with oral milrinone,’’ Journal of the American College of Cardiology, vol. 7, no. 3, pp. 661–670, Mar 1986.
33. [33] A. L. G. et al., ‘‘Physiobank, physiotoolkit, and physionet: components of a new research resource for complex physiologic signals,’’ Circulation, vol. 101, no. 23, pp. e215–e220, Jun 2000.
34. [34] R. B. D. Kreiseler and A. Schnabel, ‘‘Nutzung der ekg-signaldatenbank cardiodat der ptb über das internet,’’ Biomed. Tech., vol. 40, pp. 317–318, 1995.
35. [35] Y. C. C. K. H. Chang and G. J.Wu, ‘‘Application of extreme gradient boosting trees in the construction of credit risk assessment models for financial institutions,’’ Applied Soft Computing, vol. 73, pp. 914–920, Dec 2018.
36. [36] J. H. Friedman, ‘‘Greedy function approximation: a gradient boosting machine,’’ Annals of Statistics, vol. 29, no. 5, pp. 1189–1232, Oct 2001.
37. [37] W. T. et al., ‘‘Xgboost prediction model based on 3.0 t diffusion kurtosis imaging improves the diagnostic accuracy of mri birads 4 masses,’’ Frontiers in Oncology, vol. 12, p. 833680, Mar 2022. 8