A crucial component of medical diagnostics is the identification of bone fractures, which helps with prompt patient care and treatment. This work investigates the automatic identification of bone fractures in medical images, specifically X-rays, using Convolutional Neural Networks (CNNs). It has been demonstrated that CNNs perform well in image classification tasks because they can acquire hierarchical features straight from the raw image data. This work develops, trains, and assesses a deep learning model using an extensive collection of X-ray images. In order to enhance generalization, sophisticated image preprocessing methods like augmentation and normalization are utilized. The findings demonstrate that the suggested approach greatly enhances fracture detection performance by achieving high levels of accuracy, sensitivity, and specificity. Multiple convolutional layers are used in the suggested model architecture for feature extraction, and then pooling and fully connected layers are used for classification. A Django-developed, user-friendly web interface is integrated into the system, enabling medical professionals to upload X-ray images and obtain real-time diagnostic results. The model’s efficacy is demonstrated by the experimental results, which show 92% accuracy, 89% sensitivity, and 93% specificity. These performance metrics show that the CNN-based system performs on par with human experts and significantly reduces false negatives, which are crucial in medical diagnostics. By providing a scalable, effective, and highly accurate fracture detection tool, this research advances the expanding field of automated medical diagnostics. There is a chance that the suggested system will be widely used in clinical settings, especially in areas where access to qualified radiologists is scarce. The system facilitates prompt medical intervention by reducing human error and delivering quick diagnostic results, which ultimately leads to better patient outcomes. Future research will focus on improving the model’s real-time deployment in healthcare facilities and extending the system’s capacity to manage increasingly complicated medical conditions.