Analyzing Key Factors in Heart Disease Detection Using Deep Learning And Data Visualization Techniques

Heart disease remains one of the leading causes of mortality globally, claiming numerous lives each year.Early and accurate detection is critical to improving patient outcomes.This study explores the application of deep learning and data visualization techniques to enhance heart disease detection.By utilizing a Deep Convolutional Neural Network (DCNN) and employing advanced image classification methods, we aim to improve detection accuracy over traditional approaches.Our model leverages the UCI heart disease dataset t, which comprises data from 1050 patients and includes 14 attributes.The feature vector derived from this dataset serves as input for our DCNN, which classifies instances into healthy or cardiac disease categories.The performance of our proposed model is evaluated using metrics such as accuracy, precision, recall, and F1 score.Our results demonstrate a validation accuracy of 99.4%, underscoring the effectiveness of the deep learning approach in real-world applications.The integration of data visualization techniques further aids in interpreting the model's outcomes, facilitating better understanding and decision-making for healthcare professionals.