Cardiac Health Assessment through Advanced Computational Models for ECG Image Analysis

The extensive research initiative focuses on the application of MobileNet techniques for identifying Heart diseases through the examination of electrocardiogram (ECG) images. Given the critical importance of accurate and timely diagnosis in cardiac health, this project explores state-of-the-art computational techniques. By leveraging a carefully curated dataset containing ECG images from individuals with various cardiac conditions, a sophisticated Convolutional Neural Network (CNN) model is developed. The performance metrics highlight not only the effectiveness of the proposed approach but also its ability to classify four major cardiac irregularities, such as irregular heart rhythm, heart attack, past occurrences of myocardial infarction, and instances categorized as normal. Furthermore, the study investigates the potential of the CNN model for feature extraction, demonstrating exceptional results with a 98.79% score when combined with the Naive Bayes (NB) algorithm. Beyond technological achievements, this research contributes to the field of medical image analysis by exploring the fusion of deep learning and traditional machine learning methods for improved accuracy. The findings presented here drive advancements in automated cardiovascular disease diagnosis and offer promise for enhanced early detection strategies and interventions, ultimately leading to better patient outcomes and advancements in cardiac healthcare.