Hospitals often handle a significant volume of bone fractures, which form a major segment of their medical caseload. X-ray imaging is critical for the accurate detection and classification of these fractures, playing a pivotal role in guiding subsequent treatment strategies. This study investigates the potential of the YOLO (You Only Look Once) deep learning framework to advance the automatic detection and classification of bone fractures in X-ray images. Specifically, it aims to enhance the YOLOv8 model's ability to identify various fracture types by training it on an extensive and diverse set of labelled X-ray images and employing data augmentation techniques to improve performance. The diagnostic tool is expected to support radiologists by providing timely and accurate insights, thereby streamlining the decision-making process. The results show that the YOLOv8 model, enhanced with data augmentation outperforms the standard YOLOv8 model in both accuracy and speed for fracture detection and classification. This approach not only promises to elevate diagnostic standards but also has the potential to reduce the workload on radiologists, leading to more effective and efficient patient care.