The enlargement of the heart, known as cardiomegaly, serves as a vital indicator for various cardiovascular conditions and can be discerned through chest X-ray images. In this study, we propose a novel deep learning methodology for the automated detection of cardiomegaly from chest X-ray images. The dataset utilized has been obtained from Kaggle, encompasses True and False class images. Subsequently, the dataset was evenly partitioned into training and testing subsets, ensuring an equitable representation of both classes. Leveraging transfer learning with the EfficientNet architecture, particularly EfficientNetB7, we developed a convolutional neural network (CNN) tailored for cardiomegaly classification. Experimental findings showcase the efficacy of our approach in accurately discerning cardiomegaly from chest X-ray images, yielding promising performance metrics on the testing subset. This research contributes to the advancement of automated medical image analysis, fostering early detection and diagnosis of cardiovascular ailments, thereby enhancing patient care outcomes.