Application of large language models in clinical record correction: a comprehensive study on various retraining methods.

Journal: Journal of the American Medical Informatics Association : JAMIA
Published Date: Feb 1, 2025

Abstract

OBJECTIVES: We evaluate the effectiveness of large language models (LLMs), specifically GPT-based (GPT-3.5 and GPT-4) and Llama-2 models (13B and 7B architectures), in autonomously assessing clinical records (CRs) to enhance medical education and diagnostic skills.

Authors

  • Ana M Maitin
    CEIEC, Universidad Francisco de Vitoria, Pozuelo de Alarcón, 28223 Madrid, Spain.
  • Alberto Nogales
    CEIEC, Research Institute, Universidad Francisco de Vitoria, Ctra. M-515 Pozuelo-Majadahonda km 1800, 28223, Pozuelo de Alarcón, Spain. Electronic address: alberto.nogales@ceiec.es.
  • Sergio Fernández-Rincón
    CEIEC, Universidad Francisco de Vitoria, Pozuelo de Alarcón, 28223 Madrid, Spain.
  • Enrique Aranguren
    CEIEC, Universidad Francisco de Vitoria, Pozuelo de Alarcón, 28223 Madrid, Spain.
  • Emilio Cervera-Barba
    Facultad de Medicina, Universidad Francisco de Vitoria, Pozuelo de Alarcón, 28223 Madrid, Spain.
  • Sophia Denizon-Arranz
    Facultad de Medicina, Universidad Francisco de Vitoria, Pozuelo de Alarcón, 28223 Madrid, Spain.
  • Alonso Mateos-Rodríguez
    Facultad de Medicina, Universidad Francisco de Vitoria, Pozuelo de Alarcón, 28223 Madrid, Spain.
  • Álvaro J García-Tejedor
    CEIEC, Research Institute, Universidad Francisco de Vitoria, Ctra. M-515 Pozuelo-Majadahonda km 1800, 28223, Pozuelo de Alarcón, Spain. Electronic address: a.gtejedor@ceiec.es.

Keywords

External Resources

Popular Topics
Recent Journals