Monitoring And Detecting Anomalies in Cardiovascular Readings with Special Reference to Electrocardiogram Data

Cardiovascular diseases (CVDs) are a leading cause of global mortality, emphasizing the need for efficient diagnostic tools. Electrocardiograms (ECGs) are essential for diagnosing heart conditions but are often prone to human error and inefficiencies in large-scale data analysis. This research develops an automated ECG classification system using convolutional neural networks (CNNs) to detect anomalies. The system classifies ECG images into four categories: Myocardial Infarction, Abnormal Heartbeat, History of Myocardial Infarction, and Normal heart activity. With a trained CNN model, achieving over 90% accuracy, the project demonstrates its potential for clinical application. The model is integrated into a web-based interface via Streamlit, allowing real-time ECG image uploads for immediate classification results. This tool is designed to assist healthcare professionals, particularly in remote areas, offering rapid and accurate diagnosis. The system's broader impact lies in enhancing diagnostic efficiency, reducing manual interpretation reliance, and facilitating timely cardiac interventions. Future work includes integrating the model with wearable ECG devices for real-time, personalized healthcare monitoring.