Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{200295,
        author = {Dr. P. Sunitha Devi and G. Manisha and B. Akshitha and R. Harshitha and P. Sharanya Reddy},
        title = {A GAN-DRIVEN DEEP LEARNING FRAMEWORK FOR CARDIAC ARRHYTHMIA CLASSIFICATION},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {2593-2601},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=200295},
        abstract = {Accurate detection and classification of heart rhythm disorders are crucial in modern medical care. Untreated or inappropriately diagnosed heart rhythm disorders can lead to life-threatening complications like stroke, heart failure, or sudden death. Conventional methods of Electrocardiogram (ECG) analysis are mostly dependent on medical professionals 
interpretations. This not only consumes time but is also fraught with possibilities of diagnostic inaccuracies. A common issue in the publicly available MIT-BIH Arrhythmia database is that the number of normal heartbeats is imbalanced with supraventricular, ventricular, fusion, and unknown heartbeats [4]. This paper presents an AI-based arrhythmia classification system that utilizes deep learning and data augmentation techniques. Using the Generative Adversarial Network (GAN) approach for generating the minority class of ECG signals, the dataset gets balanced, thus helps in increasing the accuracy of the classifiers [1]. Once this happens, the process uses the combination of Convolutional Neural Networks (CNN) , Long Short-Term Memory (LSTM), for data analysis. Each heartbeat is categorized into five different categories like normal, supraventricular, ventricular, fusion, and unknown. These categories can then be mapped into different clinical labels like bradyarrhythmia, tachyarrhythmia, and normal rhythm. This proposed system is designed for fast,
reliable arrhythmia diagnosis.},
        keywords = {Cardiac Arrhythmia, Heartbeat Classification, Electrocardiogram, Deep Learning, Generative Adversarial Network.},
        month = {May},
        }