MULTI-CLASS HEART DISEASE CLASSIFICATION USING MULTI-LEAD ECG FEATURES AND ENSEMBLE LEARNING

(Received: 28-Sep.-2025, Revised: 13-Dec.-2025 , Accepted: 6-Jan.-2026)

Authors Bala Venkateswarlu Isunuri, Venkata Sravya Alapati, Sri Charan Marripudi, Gopala Krishna Parimi, Akshaya Valli Koganti,

Keywords #Electrocardiogram #Ensemble learning #Multi-lead ECG features #Multi-class heart disease classification

Abstract Cardiovascular diseases (CVDs) are the leading causes of global mortality and require an early and precise diagnosis. This work presents an automated multi-class classifier for diagnosing cardiac disease from electrocardiogram (ECG) images through image processing and machine-learning techniques. The proposed framework consists of three steps, including pre-processing, feature extraction, and ensemble learning. Initially, the ECG image undergoes a comprehensive pre-processing pipeline that includes lead segmentation, grayscale conversion, Gaussian filtering, and Otsu thresholding. The contour-based features are extracted and then reduced by PCA to preserve discriminative information. Finally, multiple machine-learning models, including K-nearest neighbors (KNNs), Random Forest and support vector machines (SVMs), are ensembled using voting and stacking classifiers to improve the performance of the proposed framework. The proposed ensemble model is evaluated on a public dataset that consists of ECG images that are categorized into four classes: normal, abnormal, myocardial infarction (MI), and history of MI. The proposed ensemble model attained the highest classification accuracy of 98.06% and outperformed the existing pre-trained and state-of-the-art models.

References

[1] L. Mhamdi, O. Dammak, F. Cottin and I. B. Dhaou, "Artificial Intelligence for Cardiac Diseases’Diagnosis and Prediction Using ECG Images on Embedded Systems," Biomedicines, vol. 10, no. 8, 2022.

[2] M. T. Tahmid, M. E. Kader, T. Mahmud and S. A. Fattah, "MDCardioNet: A Multi-dimensional DeepNeural Network for Cardiovascular Disease Diagnosis from Electrocardiogram," IEEE Journal of Biomedical and Health Informatics, vol. 28, no. 4, pp. 2005-2013, April 2024.

[3] M. B. Abubaker and B. Babayigit, "Detection of Cardiovascular Diseases in ECG Images Using MachineLearning and Deep Learning Methods," IEEE Transactions on Artificial Intelligence, vol. 4, no.2, pp. 373-382, April 2023.

[4] N. Mitra and B. I. Morshed, "Analyzing Clinical 12-lead ECG Images Using Deep Learning Algorithmsfor Objective Detection of Cardiac Diseases," Proc. of the 2022 IEEE 13th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), pp. 0517-0523, New York, USA, 2022.

[5] M. Balipa, M. Murugappan and A. Castalino, "Artificial Intelligence-based ECG Analysis to AssessCardiac Health," Proc. of the 2024 3rd Int. Conf. on Sentiment Analysis and Deep Learning (ICSADL), pp. 587-593, Bhimdatta, Nepal, 2024.

[6] M. Gulhane and S. Kumar, "Deep Learning based Heart Diseases Detection Using ResNet50Architecture," Proc. of the IEEE 2023 Intelligent Methods, Systems and Applications (IMSA), pp. 193-198, Giza, Egypt, 2023.

[7] M.Sakli, N. Sakli and H. Sakli, "ECG Images Automated Diagnosis based on Machine LearningAlgorithms," Proc. of the 2023 20th Int. Multi-Conf. on Systems, Signals & Devices (SSD), pp. 934-939, Mahdia, Tunisia, 2023.

[8] M. D. Gresa and V. Sathya, "Exploring the Potential of Machine Learning and Deep Learning in ECGImage Analysis for Cardiovascular Disease Diagnosis," Proc. of the 2024 5th Int. Conf. on Electronics and Sustainable Communication Systems (ICESC), pp. 13441349, Coimbatore, India, 2024.

[9] D. Rautela, M. Bajeli, A. Kumar and H. Vaidya, "Identifying Cardiovascular Disorders through ECGImage Analysis," Proc. of the 2024 Int. Conf. on Cognitive Robotics and Intelligent Systems (ICC-ROBINS), pp.607-612, Coimbatore, India,2024.

[10] K. Bhangale et al., "Machine Learning-based Heart Disease Prediction Using ECG Image," Proc. of the2024 5th Int. Conf. for Emerging Technology (INCET), pp. 1-9, Belgaum, India, 2024.

[11] I. Farady, V. Patel, C. -C. Kuo and C. -Y. Lin, "ECG Anomaly Detection with LSTM-Autoencoder forHeartbeat Analysis," Proc. of the 2024 IEEE Int. Conf. on Consumer Electronics (ICCE), pp. 1-5, Las Vegas, NV, USA, 2024.

[12] M. L. Meghana et al., "Cardiovascular Disease Detection in ECG Images Using CNN-BiLSTM Model,"Proc. of the 2024 IEEE Int. Conf. on Information Technology, Electronics and Intelligent Communication Systems (ICITEICS), pp. 1-6, Bangalore, India, 2024.

[13] P. G. Aublin, J. Felblinger and J. Oster, "A Generalizable Heartbeat Classifier Leveraging Self-supervisedLearning for ECG Analysis during Magnetic Resonance Imaging," IEEE Journal of Biomedical and Health Informatics, vol. 28, no. 9, pp. 5147-5155, Sept. 2024.

[14] R. Krishna Priya, L. Alias and F. S. S. Al Salehiya, "Cardiac Health Assessment through AdvancedComputational Models for ECG Image Analysis," Proc. of the 2024 10th Int. Conf. on Communication and Signal Processing (ICCSP), Melmaruvathur, India, 2024.

[15] Z. M. Tun and M. A. Khine, "Cardiac Diagnosis based ECG Images Classification System UsingConvolution Neural Network," Proc. of the 2023 IEEE Conf. on Computer Applications (ICCA), pp. 387-392, Yangon, Myanmar, 2023.

[16] S. Krishnakumar et al., "Detection of Arrhythmia and Congestive Heart Failure Through Classificationof ECG Signals Using Deep Learning Neural Network," Proc. of the 2021 Int. Conf. on Advancements in Electrical, Electronics, Communication, Computing and Automation (ICAECA), Coimbatore, India, 2021.

[17] M. Moutaib, M. Fattah, Y. Farhaoui and B. Aghoutane, "Machine Learning in Fetal Health: ImprovingECG Analysis with Random Forest," Proc. of the 2024 Int. Conf. on Circuit, Systems and Communication (ICCSC), pp. 1-5, Fes, Morocco, 2024.

[18] H. R. Esther T. et al., "Identification of Cardiovascular Disease Using ECG Images Based on DeepLearning Procedure," Proc. of the 2023 Int. Conf. on Advances in Computing, Communication and Applied Informatics (ACCAI), pp. 1-6, Chennai, India, 2023.

[19] J. E. Madias, "The 13th Multiuse ECG Lead: Shouldn't We Use It More Often, and on the Same HardCopy or Computer Screen, As the Other 12 Leads?," Journal of Electrocardiology, vol. 37, no. 4, pp. 285-287, 2004.

[20] A. H. Khan and M. Hussain, "ECG Images Dataset of Cardiac Patients," Mendeley Data, V2, DOI:10.17632/gwbz3fsgp8.2, 2021.

[21] R. C. Gonzalez and R. E. Woods, Digital Image Processing, 4th Edn., ISBN 978-0-13-335672-4, PearsonEducation, 2018.

[22] C. Y. Saw and Y. C. Wong, "Neuromorphic Computing Based on Stochastic Spiking Reservoir forHeartbeat Classification," Jordanian Journal of Computers and Information Technology (JJCIT), vol. 8, no. 2, pp. 182-193, 2022.