Your browser doesn't support javascript.
loading
Prompt engineering to increase GPT3.5's performance on the Plastic Surgery In-Service Exams.
Nahass, George R; Chin, Sydney W; Scharf, Isabel M; Kazmouz, Sobhi; Kaplan, Nicolas; Chiu, Richard; Yang, Kevin; Bou Zeid, Naji; Corcoran, Julia; Alkureishi, Lee W T.
Afiliación
  • Nahass GR; The Craniofacial Center, Division of Plastic, Reconstructive, and Cosmetic Surgery, University of Illinois at Chicago, Chicago, IL 60612, USA; Richard and Loan Hill Department of Biomedical Engineering, University of Illinois at Chicago, Chicago, IL 60612, USA.
  • Chin SW; The Craniofacial Center, Division of Plastic, Reconstructive, and Cosmetic Surgery, University of Illinois at Chicago, Chicago, IL 60612, USA.
  • Scharf IM; The Craniofacial Center, Division of Plastic, Reconstructive, and Cosmetic Surgery, University of Illinois at Chicago, Chicago, IL 60612, USA.
  • Kazmouz S; The Craniofacial Center, Division of Plastic, Reconstructive, and Cosmetic Surgery, University of Illinois at Chicago, Chicago, IL 60612, USA.
  • Kaplan N; The Craniofacial Center, Division of Plastic, Reconstructive, and Cosmetic Surgery, University of Illinois at Chicago, Chicago, IL 60612, USA.
  • Chiu R; The Craniofacial Center, Division of Plastic, Reconstructive, and Cosmetic Surgery, University of Illinois at Chicago, Chicago, IL 60612, USA.
  • Yang K; The Craniofacial Center, Division of Plastic, Reconstructive, and Cosmetic Surgery, University of Illinois at Chicago, Chicago, IL 60612, USA; Shriners Children's Chicago Hospital, Chicago, IL 60707, USA.
  • Bou Zeid N; The Craniofacial Center, Division of Plastic, Reconstructive, and Cosmetic Surgery, University of Illinois at Chicago, Chicago, IL 60612, USA.
  • Corcoran J; The Craniofacial Center, Division of Plastic, Reconstructive, and Cosmetic Surgery, University of Illinois at Chicago, Chicago, IL 60612, USA; Shriners Children's Chicago Hospital, Chicago, IL 60707, USA.
  • Alkureishi LWT; The Craniofacial Center, Division of Plastic, Reconstructive, and Cosmetic Surgery, University of Illinois at Chicago, Chicago, IL 60612, USA; Shriners Children's Chicago Hospital, Chicago, IL 60707, USA. Electronic address: lalk@uic.edu.
J Plast Reconstr Aesthet Surg ; 98: 158-160, 2024 Sep 05.
Article en En | MEDLINE | ID: mdl-39255523
ABSTRACT
This study assesses ChatGPT's (GPT-3.5) performance on the 2021 ASPS Plastic Surgery In-Service Examination using prompt modifications and Retrieval Augmented Generation (RAG). ChatGPT was instructed to act as a "resident," "attending," or "medical student," and RAG utilized a curated vector database for context. Results showed no significant improvement, with the "resident" prompt yielding the highest accuracy at 54%, and RAG failing to enhance performance, with accuracy remaining at 54.3%. Despite appropriate reasoning when correct, ChatGPT's overall performance fell in the 10th percentile, indicating the need for fine-tuning and more sophisticated approaches to improve AI's utility in complex medical tasks.
Palabras clave
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Idioma: En Revista: J Plast Reconstr Aesthet Surg Año: 2024 Tipo del documento: Article País de afiliación: Estados Unidos Pais de publicación: Países Bajos
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Idioma: En Revista: J Plast Reconstr Aesthet Surg Año: 2024 Tipo del documento: Article País de afiliación: Estados Unidos Pais de publicación: Países Bajos