Real - Time Recognition of Cardiovascular Conditions from ECG Images with Deep Learning

Cardiovascular disease (CVD) remains the leading cause of mortality globally. This study proposes a deep learning-based framework for the detection of cardiovascular conditions from electrocardiogram (ECG) images. Three architectures AlexNet, SqueezeNet, and a custom-designed Convolutional Neural Network (CNN) were trained and evaluated, achieving classification accuracies of 88%, 81%, and 100%, respectively. To facilitate real-world applicability, the models were deployed via a web application using Streamlit, enabling real-time prediction from uploaded ECG images. Furthermore, a majority voting scheme was employed to enhance prediction reliability. The proposed system demonstrates the potential of deep learning models in aiding cardiovascular diagnosis and emphasizes the importance of accessible deployment tools. Future research will focus on larger datasets, additional cardiac conditions, and model interpretability through explainable AI techniques.  Impact Statement Artificial intelligence (AI) continues to transform the field of healthcare, particularly in enhancing early detection and diagnosis of life-threatening diseases. In this work, an automated system for the detection of cardiovascular diseases from ECG images has been developed using deep learning methods, including AlexNet, SqueezeNet, and a custom-designed CNN. The proposed models achieved remarkable classification accuracy, with the custom CNN attaining 100% accuracy on the testing dataset. Importantly, the lightweight architectures are optimized to operate efficiently on systems with limited computational resources, enabling real-time deployment on standard CPUs without the need for high-end GPUs. Furthermore, ensemble techniques such as majority voting have been incorporated to enhance prediction reliability. This advancement has the potential to assist clinicians by providing quick, accurate, and scalable diagnostic support, ultimately contributing to earlier intervention and improved patient outcomes.