Enhancing the effectiveness and dependability of healthcare systems requires precise categorization and content extraction from medical prescriptions. The current work suggests a method for automatically identifying, categorizing, and extracting data from medical prescriptions, including patient, hospital, and medicine information using the YOLOv8 object detection model. Through analysis and experimental evaluation, we highlight the performance of the YOLOv8 model in handling complex, handwritten prescriptions with varying formats. Using a custom dataset, the model was able to achieve a Precision of 96%. Despite achieving promising results, challenges such as noisy data, handwriting variability, and overlapping text are some ongoing obstacles. This work provides valuable insights into the potential of deep learning models for medical document processing, offering a robust solution for healthcare applications.