Medicina, Vol. 61, Pages 1677: Augmenting Patient Education in Hand Surgery—Evaluation of ChatGPT as an Informational Tool in Carpal Tunnel Syndrome

Medicina doi: 10.3390/medicina61091677

Authors:
Benedikt Fuchs
Nikolaus Thierfelder
Irene Mesas Aranda
Verena Alt
Constanze Kuhlmann
Elisabeth M. Haas-Lützenberger
Konstantin C. Koban
Riccardo E. Giunta
Sinan Mert

Background and Objectives: Carpal tunnel syndrome (CTS) is the most common entrapment neuropathy caused by chronic compression of the median nerve within the carpal tunnel. Patient education is a cornerstone of informed consent and postoperative outcomes, yet time constraints often limit traditional consultations. Recently, generative AI tools such as ChatGPT have emerged as potential adjuncts in delivering standardized medical information. Materials and Methods: This study evaluated the quality and comprehensiveness of ChatGPT-generated patient education on CTS and open carpal tunnel release. A standardized prompt was used with ChatGPT-4o to generate educational material. A structured and standardized questionnaire was then administered to both patients and physicians (n = 8) to assess content quality, clarity, comprehensiveness, and perceived usefulness. Results: Both patients and physicians reported high satisfaction with the information provided. The etiology, procedural risks, and general anatomical principles were well conveyed. However, certain intraoperative concepts—such as neurolysis, synovectomy, and hemostasis—were underrepresented. While conservative therapies were addressed, the omission of endoscopic surgical options limited informational completeness. Prognostic information and long-term consequences of untreated CTS were rated as average by some participants. Postoperative guidance was adequately covered but lacked individualized nuance. Conclusions: ChatGPT shows promise as an adjunct in surgical patient education, offering clear and standardized information. Nevertheless, it is not a substitute for clinician–patient interaction. While it may bridge preliminary knowledge gaps, emotional support and individualized consent discussions remain essential. Further refinement and clinical validation of AI-generated educational content are needed to ensure safe and effective integration into routine practice.

Source link

Benedikt Fuchs www.mdpi.com