Optimizing Feature Selection for Deep Learning Models in Heart Disease Prediction Using ECG Data
Keywords:
Cardiovascular disease, Machine learning, Electrocardiogram (ECG), Heart disease detection, Feature extractionAbstract
Heart disease popularly known as cardiovascular diseases (CVDs), continue to rank among the world's top causes of death, demanding the great need of designing accurate and effective diagnostic techniques. Early detection and accurate assessment of heart conditions can significantly enhance patient outcomes and lower the cost of healthcare. In this paper we have investigated the impact of machine learning (ML) models that use ECG data to predict heart disorder/diseases are affected by advanced feature selection techniques. Utilizing a dataset of 986 patients, the study focused on important features extracted using methods namely- Mutual Information (MI), Recursive Feature Elimination (RFE), L1 Regularisation, and Principal Component Analysis (PCA). The deep learning models involving are CNN, LSTM, MLP and ViT were investigated. With an accuracy of 99.30%, CNN with MI produced results that were competitive among the evaluated configurations, while LSTM with MI showed the best accuracy of 99.07%. With the ten feature selection approach-Top, CNN becomes the best model there also for the task at hand with the accuracy of 99.07%. The MLP and ViT models also performed well, achieving high precision (~97.74%) and accuracy of 97.67%. This comparative analysis emphasizes the significance of feature selection in reducing dimensionality, increasing computing effectiveness, and improving the model’s performance. These finding highlight the potential of integrating advanced feature selection techniques with machine learning algorithms to detect cardiac disorders early. In order to increase clinical usability and ensure reliable performance across a variety of datasets, future research may explore hybrid models and real-time applications.
Downloads
Metrics
References
Bani Hani, S.H. and Ahmad, M.M. (2023) ‘Machine-learning algorithms for ischemic heart disease prediction: A systematic review’, Current Cardiology Reviews, 19, pp. e090622205797. doi: 10.2174/1573403X1966622090622205797.
Manji, R. A., Witt, J., Tappia, P. S., Jung, Y., Menkis, A. H., and Ramjiawan, B.(2013). ‘Cost– effectiveness analysis of rheumatic heart disease prevention strategies’, Expert Rev. Pharmacoecon. Outcomes Res., 13 (6), pp.715–724.
Noroozi, Z., Orooji, A. and Erfannia, L. (2023). ‘Analyzing the impact of feature selection methods on machine learning algorithms for heart disease prediction’, Scientific reports, 13, pp. 1–15. Available from: https://doi.org/10.1038/s41598-023-49962-w.
Yekkala, I., Dixit, S. and Jabbar, M. (2017). ‘Prediction of heart disease using ensemble learning and Particle Swarm Optimization’, In 2017 International Conference On Smart Technologies For Smart Nation (SmartTechCon); IEEE (2017).
Rautaharju, P. M., Surawicz, B., & Gettes, L. S. (2009). ‘AHA/ACCF/HRS recommendations for the standardization and interpretation of the electrocardiogram’, Journal of the American College of Cardiology, 53(11), 976-981.
Badoni, P., Walia, R., and Mehra, R. (2024). ‘Wearable IoT technology: Unveiling the smart hat’, Proceedings - 2024 1st International Conference on Intelligent Systems and Technologies for Emerging Markets (ISTEMS). https://doi.org/10.1109/ISTEMS60181.2024.10560229
Kligfield, P., Gettes, L. S., Bailey, J. J., Childers, R., Deal, B. J., Hancock, E. W., ... & Wagner, G. S. (2007). ‘Recommendations for the standardization and interpretation of the electrocardiogram: part I: the electrocardiogram and its technology’, Journal of the American College of Cardiology, 49(10), 1109-1127.
Morris, F. (2008). ‘ABC of Clinical Electrocardiography’, Blackwell Pub: Oxford, UK.
Clifford, G. D., Liu, C., Moody, B., Li, Q., Silva, I., Li-Pershing, Y., Behar, J., Johnson, A. E. W., Oster, J., Sapojnikov, M., Nemati, S., Scott, D. J., & Mark, R. G. (2017). ‘AF classification from a short single lead ECG recording: The PhysioNet Computing in Cardiology Challenge 2017’, Computing in Cardiology, 44, 1-4. https://doi.org/10.23919/CinC.2017.
Najafi, A., Nemati, A., Ashrafzadeh, M. and Zolfani, S.H. (2023). ‘Multiple-criteria decision making, feature selection, and deep learning: A golden triangle for heart disease identification’, Engineering Applications of Artificial Intelligence,125. Available from: https://doi.org/10.1016/j.engappai.2023.106662.
Satisha, C., Mehra, R., and Giri, M. (2023). Detection of various security attacks on IoT devices using machine learning. 2023 International Conference on Computational Intelligence and Networks (ICCINS). https://doi.org/10.1109/ICCINS58907.2023.10450058
Badoni, P., Walia, R., & Mehra, R. (2024). ‘Enhancing waste separation and management through IoT-based smart bin system’, Proceedings of the 2024 1st International Conference on Intelligent Systems and Technologies for Emerging Markets (ISTEMS). https://doi.org/10.1109/ISTEMS60181.2024.10560260
Kumar, B., Soundararajan, R., Natesan, K.. and Santhi, R. M. (2023). ‘Hybrid Feature Selection and Classifying Stages through Electrocardiogram (ECG) Signal for Heart Disease Prediction’, Eng. Proc., MDPI, 59(126). https://doi.org/10.3390/ engproc2023059126
Raj, S., & Ray, K. C. (2018). ‘A personalized arrhythmia monitoring framework using wearable sensors and a deep learning network’, Biomedical Signal Processing and Control, 44, 42-50. https://doi.org/10.1016/j.bspc.2018.04.001
Kiranyaz, S., Ince, T., & Gabbouj, M. (2016). ‘Real-time patient-specific ECG classification by 1-D convolutional neural networks’, IEEE Transactions on Biomedical Engineering, 63(3), 664-675. https://doi.org/10.1109/TBME.2015.2468589
Golande, A. L. and Pavankumar, T. (2023). ‘Optical electrocardiogram based heart disease prediction using hybrid deep learning’, Journal of Big Data , 10(139). https://doi.org/10.1186/s40537-023-00820-6
Li, X., Zhou, Y., Yu, J., & Wang, X. (2020). ‘ECG signal classification using wavelet transform and deep convolutional neural networks’, Neural Computing and Applications, 32(10), 6849-6861. https://doi.org/10.1007/s00521-019-04144-1
Kunadharaju, H. P. R., Sandhya, N., & Mehra, R. (2019). ‘Multi-sensor image matching using super symmetric classifiers’, International Journal of Recent Technology and Engineering, 8(2), 6161–6166. https://doi.org/10.35940/ijrte.B3764.078219
Ishaq, A., Sadiq, S., Umer, M., Ullah, S., Mirjalili, S., Rupapara, V. and Nappi, M.(2021). ‘Improving the prediction of heart failure patients’ survival using SMOTE and effective data mining techniques’, IEEE Access, 9, pp. 39707–39716.
Badoni, P., Walia, R., and Mehra, R. (2024). ‘Wearable IoT technology: Unveiling the smart hat’, Proceedings - 2024 1st International Conference on Intelligent Systems and Technologies for Emerging Markets (ISTEMS). https://doi.org/10.1109/ISTEMS60181.2024.10560229
Vijay Krishnan, M. R., Mehra, R., & Kunadharaju, H. P. R. (2024). ‘Design of neural network-based approaches for image processing’, Proceedings of the 2024 3rd International Conference on Electrical, Electronics, and Information Communication Technology (ICEEICT). https://doi.org/10.1109/ICEEICT61591.2024.10718442
Thiyagarajan, C. (2016). ‘A survey on diabetes mellitus prediction using machine learning techniques’, Int. J. Appl. Eng., 11, pp. 1810–1814.
Ribeiro, A. H., Ribeiro, M. H., Paixão, G. M. M., Oliveira, D. M., Gomes, P. R., Canazart, J. A., Ferreira, M. P., Andersson, C. R., Macfarlane, P. W., Meira Jr, W., Schön, T. B., & Ribeiro, A. L. (2020). ‘Automatic diagnosis of the 12-lead ECG using a deep neural network’, Nature Communications, 11(1), 1760. https://doi.org/10.1038/s41467-020-15432-4
Guyon, I., & Elisseeff, A. (2003). ‘An introduction to variable and feature selection’, Journal of Machine Learning Research, 3, 1157–1182.
Acharya, U. R., Fujita, H., Lih, O. S., Adam, M., Tan, J. H. and Chua, C. K.. (2017). ‘ Automated detection of arrhythmias using different intervals of tachycardia ECG segments with convolutional neural network’ Information Sciences, 405, pp. 81-90. doi:10.1016/j.ins.2017.04.012
Jadhav, S. M., Ghatol, A. A., & Holambe, R. S. (2010). ‘Artificial neural network models based cardiac arrhythmia disease diagnosis from ECG signal data’, International Journal of Cardiology, 141(1), 1–12.
Kachuee, M., Kiani, M. M., Mohammadzade, H., & Shabany, M. (2018). ‘ECG heartbeat classification: A deep transferable representation’, IEEE Transactions on Biomedical Engineering, 66(5), 1196–1206. https://doi.org/10.1109/TBME.2018.2872652
Yildirim, Ö., Talo, M., Ay, B., Baloglu, U. B., Aydin, G., and Acharya, U. R. (2018). ‘Automated arrhythmia detection using deep learning techniques: A review’, Computers in Biology and Medicine, 96, pp. 189-202.
Sadhukhan, P., Roy, K., and Biswas, S. (2020). ‘Comparative Analysis of Feature Selection Techniques for ECG-based Myocardial Infarction Detection’, Journal of Biomedical Signal Processing and Control, 58, 101869.
Peker, M., Demir, D., and Yildirim, B. (2019). ‘The impact of feature selection on neural networks and support vector machines for arrhythmia classification’, Journal of Medical Systems, 43(6), 178. https://doi.org/10.1007/s10916-019-1357-0.
Mincholé, A. et al. (2019). ‘Impact of Feature Selection on Machine Learning Models for ECG Signal Classification’, Journal of Medical Systems, 43(4), 92. https://doi.org/10.1007/s10916-019-1324-7.
Zhao, Y., Liu, L., and Zhang, Y. (2021). ‘Feature selection for heart disease detection using machine learning: A focus on heart rate variability’, Journal of Medical Systems, 45(8), pp. 1-12. https://doi.org/10.1007/s10916-021-01762-4.
Kiranyaz, S., Ince, T. and Gabbouj, M. (2018). ‘Personalized Monitoring of ECG Signals With Hybrid Feature Selection and Deep CNN Models’, IEEE Transactions on Biomedical Engineering, 65(4), pp. 1015-1023. DOI: 10.1109/TBME.2017.2754295.
Liang, J., Wang, J., and Zhang, Z. (2020). ‘Pre-selecting features for deep learning models: Improving convergence speed and reducing overfitting in ECG-based heart disease detection’, IEEE Transactions on Biomedical Engineering, 67(4), pp.1025-1034.
Choi, H. et al. (2020). ‘Enhancing ECG-Based Myocardial Infarction Detection Using Random Forest and Feature Importance Metrics’, Journal of Medical Systems, Vol. 44, pp. 1-12.
Chen, Y., Wang, X., Li, Z. and Zhang, J. (2021). ‘Hybrid Feature Selection for Enhancing ECG-Based Deep Neural Networks in Heart Abnormality Detection,’ Journal of Medical Signal Processing, 45(3), pp. 245–260.
Lu, R. (2019). ‘Malware detection with LSTM using opcode language’. arXiv preprint arXiv:1906.04593. https://arxiv.org/abs/1906.04593
Sharma, R., Kamble, S. S., Gunasekaran, A., Kumar, V., & Kumar, A. (2020). ‘A systematic literature review on machine learning applications for sustainable agriculture supply chain performance’, Computers & Operations Research, 119, 104926. https://doi.org/10.1016/j.cor.2020.104926
Aeinfar, V., Mazdarani, H., Deregeh, F., Hayati, M., & Payandeh, M. (2009). ‘Multilayer Perceptron Neural Network with supervised training method for diagnosis and predicting blood disorder and cancer’, In 2009 IEEE International Symposium on Industrial Electronics (pp. 2075-2080). IEEE. https://doi.org/10.1109/ISIE.2009.5213842
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018). ‘BERT: Pre-training of deep bidirectional transformers for language understanding’. arXiv preprint arXiv:1810.04805. https://arxiv.org/abs/1810.04805
.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
