How does ChatGPT 4omni perform in consenting for common orthopedic and musculoskeletal interventional procedures?

Objectives ChatGPT 4omni is OpenAI’s newest multimodal software featuring improvements in speed, cost-efficiency, and capability over previous versions such as GPT-4 and GPT-4 Turbo. This article looks at the performance of ChatGPT in consenting patients for ten commonly performed orthopedic and musculoskeletal interventional procedures at our tertiary cold orthopedic center. Materials and Methods ChatGPT 4omni was asked to consent for these procedures. The results were compared against existing guidelines and clinical knowledge by a fellowship trained orthopedic surgeon and interventional radiologist. A 5-point Likert scale was used to grade the response across four parameters: (i) description of the procedure, (ii) benefits, (iii) risks, and (iv) overall impression of the document. Results A Likert scale score of 5 was given to the domains of benefits and risks in all surgical and intervention orthopedic procedures. For description of procedure, a score of 3 was given in total hip and knee replacement, and score of 4 for image-guided trochanteric bursal injection, by one scorer, due to a lack of procedural description. Overall, impression was scored as 4 for these procedures. These procedures received a score of 5 for all other parameters. Conclusion ChatGPT 4omni demonstrates promising results in obtaining consent, compared to the gold-standard of consent being obtained by a surgeon/radiologist, for commonly performed cold surgical and interventional orthopedic procedures. It may have a role in supporting patients, clinicians, and healthcare systems in the future although certain ethical, governance, and medicolegal challenges still need to be addressed.