Evaluating the Utility of ChatGPT in Diagnosing and Managing Maxillofacial Trauma

Maxillofacial trauma is a significant concern in emergency departments (EDs) due to its high prevalence and the complexity of its management. However, many ED physicians lack specialized training and confidence in handling these cases, leading to a high rate of facial trauma referrals and increased stress on consult services. Recent advancements in artificial intelligence, particularly in large language models such as ChatGPT, have shown potential in aiding clinical decision-making. This study specifically examines the efficacy of ChatGPT in diagnosing and managing maxillofacial trauma. Ten clinical vignettes describing common facial trauma scenarios were presented to a group of plastic surgery residents from a tertiary care center and to ChatGPT. The chatbot and residents were asked to provide their diagnosis, ED management, and definitive management for each scenario. Responses were scored by attending plastic surgeons who were blinded to the response source. The study included 13 resident and ChatGPT responses. The mean total scores were similar between residents and ChatGPT (23.23 versus 22.77, P > 0.05). ChatGPT outperformed residents in diagnostic accuracy (9.85 versus 8.54, P < 0.001) but underperformed in definitive management (8.35 versus 6.35, P < 0.001). There was no significant difference in ED management scores between ChatGPT and the residents. ChatGPT demonstrated high accuracy in diagnosing maxillofacial trauma. However, its ability to suggest appropriate ED management and definitive treatment plans was limited. These findings suggest that while ChatGPT may serve as a valuable diagnostic tool in ED settings, further advancements are necessary before it can reliably contribute to treatment planning in emergent maxillofacial clinical scenarios.