An Integrated Deep Learning and Large Language Model for Burn Wound Depth Recognition

Accurate burn depth assessment remains a challenge, especially in emergency settings. This study aimed to develop a low-cost artificial intelligence (AI)-based system for burn wound classification using deep learning and large language models (LLMs). A total of 397 burn wound images from public databases were augmented to 7156 images and categorized by depth. A classification model was trained using PaddlePaddle, and a burn-specific LLM was developed based on clinical guidelines. Model performance was evaluated using accuracy, recall, and F1 score and compared against 10 medical students and 6 general LLMs on 80 out-of-sample images. Our model achieved an overall accuracy of 96.82% and F1 score of 96.70%, outperforming medical students (F1: 76.63%) and general LLMs (F1: 68.75%-73.75%). In a separate test using 10 guideline-based true/false questions, all AI models answered correctly, whereas students had only 64% accuracy. This integrated model offers accurate burn depth recognition and guideline-based treatment suggestions, addressing the shortage of burn care specialists, and supporting medical education.