Abstract: Cardiovascular disease (CVD) is a global health burden, with heart attacks being a major contributor to mortality. Early detection of risk factors is crucial for preventive measures. This paper investigates the application of Convolutional Neural Networks (CNNs) for analysing retinal images to predict heart attack risk. The rationale lies in the ability of retinal vasculature to reflect systemic vascular health. CNNs, a powerful deep learning technique, are adept at learning intricate patterns from image data. By analysing retinal images, the proposed model can identify subtle features associated with an increased risk of heart attack. This approach offers a non-invasive and potentially cost-effective screening method for CVD. The effectiveness of the proposed method is evaluated using a benchmark retinal image dataset. Metrics such as accuracy, sensitivity, and specificity are employed to assess the model's performance.
Keywords: Convolution neural network , Retinal Image Analysis , Deep Learning ,Non-invasive Screening,
|
DOI:
10.17148/IJARCCE.2024.13507
