Detection and Classification of Cardiovascular Arrhythmias From ECG Signals Using Deep Learning Algorithms (CNN1D)

Recent progress in Artificial Intelligence (AI), especially in Machine Learning (ML) and Deep Learning (DL), has revolutionized medical science by introducing more precise and efficient techniques for diagnosing, predicting, and treating serious health conditions. This research emphasizes the importance of the human circulatory system, particularly the heart's role in sustaining proper blood flow. Although Electrocardiograms (ECGs) are widely used to identify heartrelated disorders, traditional manual analysis is often slow and prone to inaccuracies. To overcome this limitation, we introduce an automated classification system using a one-dimensional Convolutional Neural Network (1D-CNN). The model was trained and tested on real-world ECG data from the MIT-BIH Arrhythmia Database, delivering exceptional performance with 100 % training accuracy and 99 % testing accuracy. These findings highlight the system's capability for fast and reliable arrhythmia detection, supported by strong precision and recall scores. Additionally, this deep learning framework holds potential for broader applications, such as integrating with other biosignals like EEG to improve cardiovascular anomaly detection and enable earlier diagnosis through multimodal analysis