Heart Disease Prediction Using CT Scan

Cardiovascular diseases (CVDs), particularly coronary artery disease (CAD), are among the primary causes of mortality worldwide. Timely and accurate identification of CAD facilitates effective management, improves patient outcomes, and reduces healthcare costs. This research investigates the application of advanced machine learning techniques and deep learning algorithms to predict CAD using coronary computed tomography angiography (CTA) and coronary artery calcium (CAC) scoring. We employed a detailed dataset that includes CTA images and CAC scores obtained from X patients (please specify the source of the dataset, if available) to create predictive models. The dataset underwent several preprocessing steps, such as image normalization, augmentation, and segmentation, to improve data quality and enhance model performance. Various machine learning models were utilized, including Convolutional Neural Networks (CNNs) for feature extraction. The effectiveness of each model was evaluated using metrics such as accuracy, precision, recall, F1 score, and the area under the receiver operating characteristic curve (AUC-ROC). Our CNN model exhibited exceptional performance, achieving an accuracy of X%, surpassing both traditional diagnostic methods and other machine learning models. Importantly, the inclusion of CAC scores as an additional feature significantly enhanced the model's predictive capabilities, highlighting the importance of non-invasive calcium scoring in the evaluation of CAD. This study illustrates the potential of combining image processing with machine learning for automated CAD diagnosis, providing a non-invasive, efficient, and precise method for early detection and risk assessment.