Optimizing Machine Learning-Based Classification of Cardiac Arrhythmias Through Feature Selection

Seyed Ali Fatemi Aghda; Arezoo  Abasi

doi:10.30699/3ehyes32

Authors

Seyed Ali Fatemi Aghda Student Research Committee, School of Health Management and Information Sciences, Iran University of Medical Sciences, Tehran, Iran
Arezoo Abasi Student Research Committee, School of Health Management and Information Sciences, Iran University of Medical Sciences, Tehran, Iran Corresponding Author
https://orcid.org/0000-0002-8308-5657
abasi.arezoo@gmail.com

DOI:

https://doi.org/10.30699/3ehyes32

Keywords:

Cardiac Arrhythmias, Machine Learning Algorithms, Classification, Feature Selection, Electrocardiography

Abstract

Introduction: The clinical complexity of cardiac arrhythmias drives the adoption of Machine Learning (ML) for diagnosis. However, model efficacy critically depends on identifying the most predictive features. This study investigates advanced feature selection methods to isolate optimal parameters, aiming to enhance the accuracy and efficiency of arrhythmia classification models. Using optimal feature selection, this study identifies key Electrocardiogram (ECG) and clinical predictors to enhance ML model accuracy in detecting cardiac arrhythmias.

Material and Methods: This computational study employed a two-phase feature refinement using Correlation Feature Selection (CFS) with Best-First Search, distilling best 50 features and 27 elite predictive features from global and localized ECG characteristics. Multiple machine learning models were then developed and assessed based on this optimized feature set.

Results: The results demonstrated significant improvements in classification accuracy with feature selection. Random forest achieved an accuracy of 69.46% without feature selection, which increased to 73.67% with the top 50 features and further improved to 75.66% with the elite features. Similarly, LogitBoost showed a remarkable increase in accuracy from 74.55% to 80.97% when using the elite features.

Conclusion: Considering the increase in cardiac diseases and their treatment costs, finding the most important features and using Artificial Intelligence (AI) will improve the screening and diagnosis of these patients. Also, electronic health record data and the design of medical decision support systems can be helpful in helping to treat and improve patient management.

References

1. Ha ACT, Doumouras BS, Wang CN, Tranmer J, Lee DS. Prediction of sudden cardiac arrest in the general population: Review of traditional and emerging risk factors. Can J Cardiol. 2022; 38(4): 465-78. PMID: 35041932 DOI: 10.1016/j.cjca.2022.01.007

2. Ozcan M, Peker S. A classification and regression tree algorithm for heart disease modeling and prediction. Healthcare Analytics. 2023; 3: 100130.

3. Zhong L, Xie B, Wang H-L, Ji X-W. Causal association between remnant cholesterol level and risk of cardiovascular diseases: A bidirectional two sample mendelian randomization study. Sci Rep. 2024; 14(1): 27038. PMID: 39511362 DOI: 10.1038/s41598-024-78610-0

4. Lallah PN, Laite C, Bangash AB, Chooah O, Jiang C. The use of artificial intelligence for detecting and predicting atrial arrhythmias post catheter ablation. Rev Cardiovasc Med. 2023; 24(8): 215. PMID: 39076714 DOI: 10.31083/j.rcm2408215

5. Truong ET, Lyu Y, Ihdayhid AR, Lan NS, Dwivedi G. Beyond clinical factors: Harnessing artificial intelligence and multimodal cardiac imaging to predict atrial fibrillation recurrence post-catheter ablation. J Cardiovasc Dev Dis. 2024; 11(9): 291. PMID: 39330349 DOI: 10.3390/jcdd11090291

6. Roth GA, Mensah GA, Johnson CO, Addolorato G, Ammirati E, Baddour LM, et al. Global burden of cardiovascular diseases and risk factors, 1990–2019: Update from the GBD 2019 study. J Am Coll Cardiol. 2020; 76(25): 2982-3021. PMID: 33309175 DOI: 10.1016/j.jacc.2020.11.010

7. Mehta LS, Warnes CA, Bradley E, Burton T, Economy K, Mehran R, et al. Cardiovascular considerations in caring for pregnant patients: A scientific statement from the American heart association. Circulation. 2020; 141(23): e884-903. PMID: 32362133 DOI: 10.1161/CIR.0000000000000772

8. Mela A, Rdzanek E, Poniatowski LA, Jaroszynski J, Furtak-Niczyporuk M, Galazka-Sobotka M, et al. Economic costs of cardiovascular diseases in Poland estimates for 2015–2017 years. Front Pharmacol. 2020; 11: 1231. PMID: 33013357 DOI: 10.3389/fphar.2020.01231

9. Li X, Cai W, Xu B, Jiang Y, Qi M, Wang M. SEResUTer: A deep learning approach for accurate ECG signal delineation and atrial fibrillation detection. Physiol Meas. 2023; 44(12): 125005. PMID: 37827168 DOI: 10.1088/1361-6579/ad02da

10. Abasi A, Nazari A, Moezy A, Fatemi Aghda SA. Machine learning models for reinjury risk prediction using cardiopulmonary exercise testing (CPET) data: Optimizing athlete recovery. BioData Mining. 2025; 18(1): 16. PMID: 39962522 DOI: 10.1186/s13040-025-00431-2

11. Quartieri F, Marina-Breysse M, Toribio-Fernandez R, Lizcano C, Pollastrelli A, Paini I, et al. Artificial intelligence cloud platform improves arrhythmia detection from insertable cardiac monitors to 25 cardiac rhythm patterns through multi-label classification. J Electrocardiol. 2023; 81: 4-12. PMID: 37473496 DOI: 10.1016/j.jelectrocard.2023.07.001

12. Zhang Y, Liu S, He Z, Zhang Y, Wang C. A CNN model for cardiac arrhythmias classification based on individual ECG signals. Cardiovasc Eng Technol. 2022; 13(4): 548-57. PMID: 34981316 DOI: 10.1007/s13239-021-00599-8

13. Garcha I, Phillips SP. Social bias in artificial intelligence algorithms designed to improve cardiovascular risk assessment relative to the Framingham Risk Score: A protocol for a systematic review. BMJ Open. 2023; 13(5): e067638. PMID: 37258078 DOI: 10.1136/bmjopen-2022-067638

14. Shi J, Li Z, Liu W, Zhang H, Guo Q, Chang S, et al. Optimized solutions of electrocardiogram lead and segment selection for cardiovascular disease diagnostics. Bioengineering (Basel). 2023; 10(5): 607. PMID: 37237677 DOI: 10.3390/bioengineering10050607

15. Jekova I, Christov I, Krasteva V. Atrioventricular synchronization for detection of atrial fibrillation and flutter in one to twelve ECG leads using a dense neural network classifier. Sensors (Basel). 2022; 22(16): 6071. PMID: 36015834 DOI: 10.3390/s22166071

16. Guvenir H, Acer B, Muderrisoglu H, Quinlan R. UCI machine learning repository: Arrhythmia [dataset]. 1997 [cited: 15 Sep 2025]. Available from: https://archive.ics.uci.edu/dataset/5/arrhythmia

17. Irfan S, Anjum N, Althobaiti T, Alotaibi AA, Siddiqui AB, Ramzan N. Heartbeat classification and arrhythmia detection using a multi-model deep-learning technique. Sensors (Basel). 2022; 22(15): 5606. PMID: 35957162 DOI: 10.3390/s22155606

18. Xiao Q, Lee K, Mokhtar SA, Ismail I, Pauzi AL, Zhang Q, et al. Deep learning-based ECG arrhythmia classification: A systematic review. Applied Sciences (Basel). 2023; 13(8): 4964.

19. Zhang H, Wang X, Liu C, Liu Y, Li P, Yao L, et al. Detection of coronary artery disease using multi-modal feature fusion and hybrid feature selection. Physiol Meas. 2020; 41(11): 115007. PMID: 33080588 DOI: 10.1088/1361-6579/abc323

20. Doran K, Resnick B. Cardiovascular risk factors of long-term care workers. Workplace Health Saf. 2017; 65(10): 467-77. PMID: 28422575 DOI: 10.1177/2165079917693018

21. Motwani M, Dey D, Berman DS, Germano G, Achenbach S, Al-Mallah MH, et al. Machine learning for prediction of all-cause mortality in patients with suspected coronary artery disease: A 5-year multicentre prospective registry analysis. Eur Heart J. 2017; 38(7): 500-7. PMID: 27252451 DOI: 10.1093/eurheartj/ehw188

22. You J, Guo Y, Kang J-J, Wang H-F, Yang M, Feng J-F, et al. Development of machine learning-based models to predict 10-year risk of cardiovascular disease: A prospective cohort study. Stroke Vasc Neurol. 2023; 8(6): 475-85. PMID: 37105576 DOI: 10.1136/svn-2023-002332

23. Kang MG, Koo B-K, Tantry US, Kim K, Ahn J-H, Park HW, et al. Association between thrombogenicity indices and coronary microvascular dysfunction in patients with acute myocardial infarction. JACC Basic Transl Sci. 2021; 6(9): 749-61. PMID: 34754989 DOI: 10.1016/j.jacbts.2021.08.007

24. Ma C-Y, Luo Y-M, Zhang T-Y, Hao Y-D, Xie X-Q, Liu X-W, et al. Predicting coronary heart disease in Chinese diabetics using machine learning. Comput Biol Med. 2024; 169: 107952. PMID: 38194779 DOI: 10.1016/j.compbiomed.2024.107952

25. Allegra A, Mirabile G, Tonacci A, Genovese S, Pioggia G, Gangemi S. Machine learning approaches in diagnosis, prognosis and treatment selection of cardiac amyloidosis. Int J Mol Sci. 2023; 24(6): 5680. PMID: 36982754 DOI: 10.3390/ijms24065680