Cardiovascular disease (CVD)is the leading cause of death globally and is a significant public health problem. An echocardiogram, a non-invasive imaging technique, is crucial in diagnosing and assessing cardiovascular disease. However, the manual analysis of echocardiograms requires significant expertise and is time-consuming, prompting the need for automated approaches. Precision medicine, or personalized medicine, supports using new testing techniques and data analysis to identify and differentiate the patient’s features and develop therapies according to the differences in patient characteristics. The result is improved treatment outcomes that positively impact patients’ quality of life and reduce unnecessary use of medical resources. Convolutional Neural Networks, a type of deep learning model, are highly effective for image data and are employed in tasks such as segmentation, classification, and object detection. This study aims to detect the possibility of CVD through echocardiogram images using the CNN architecture. The performance model of ResNet-101 achieved an accuracy of 71%, which indicated that the model could be employed as an efficient solution for the automated analysis of echocardiograms and offers significant improvements in diagnostic accuracy and operational efficiency. This enhanced capability can lead to better diagnostic outcomes and streamlined workflows in cardiovascular medicine.