Enhancing Burn Management Decision-making with ChatGPT: A Study on Accurate Dressing Choice Recommendations


Ishith Seth1, Warren Rozen David Hunter-Smith
1Peninsula Health, Melbourne, Victoria, Australia

Abstract

Abstract:

Background: Burn injury management is a multifaceted process, necessitating the meticulous selection of dressings to optimize wound healing, reduce infection risk, and ensure patient comfort. The emergence of artificial intelligence (AI) tools, such as large language models, offers the potential to improve decision-making in clinical practice. This study aims to evaluate ChatGPT, an AI large language model, in providing accurate dressing choice recommendations for burn management.

Methods: A range of burn scenarios was prompted to ChatGPT, and its responses were compared against international guidelines. The AI-generated recommendations were then evaluated by two specialist plastic surgeons with expertise in burns management. The potential benefits of integrating image-based machine learning AI to enhance ChatGPT’s performance were also explored.

Results: ChatGPT exhibited a high degree of concordance with expert consensus in recommending suitable dressings for various burn injury scenarios. The integration of image-based machine learning AI was identified as a potential avenue for further improvement. This advanced technology could assist medical professionals, particularly in rural clinical settings, in their clinical decision-making process regarding dressing selection for burn management.

Conclusion: ChatGPT demonstrates potential in offering accurate and clinically pertinent advice on dressing choices for burn management. By harnessing image-based machine learning AI-driven recommendations, healthcare professionals can augment their decision-making processes and ultimately improve patient outcomes. Further research is necessary to validate ChatGPT’s performance in real-world clinical settings and investigate its potential applications in other aspects of burn care.

Biography

Ishith Seth is a plastic surgical resident, master of Surgery candidate investigating 3D-printed carpal implants for carpal osteoarthritis. He is associated with Peninsula Health and Monash University. Honorary researcher at the Department of Surgery, Royal Children’s Hospital, Murdoch Children’s Research Institute, and The University of Melbourne. He is a clinical tutor at Monash University and Melbourne University Medical Schools. His special interests include oculoplastics, microsurgery, reconstructive surgery, and artificial intelligence in healthcare.