Keyword-optimized template insertion for clinical note classification via prompt-based learning.

Journal: BMC medical informatics and decision making
Published Date: Jul 3, 2025

Abstract

BACKGROUND: Prompt-based learning involves the additions of prompts (i.e., templates) to the input of pre-trained large language models (PLMs) to adapt them to specific tasks with minimal training. This technique is particularly advantageous in clinical scenarios where the amount of annotated data is limited. This study aims to investigate the impact of template position on model performance and training efficiency in clinical note classification tasks using prompt-based learning, especially in zero- and few-shot settings.

Authors

  • Eugenia Alleva
    Windreich Department for Artificial Intelligence and Human Health and Hasso Plattner Institute for Digital Health at Mount Sinai, Ichan School of Medicine at Mount Sinai, New York, United States of America. Electronic address: eugeniaalessandrae.allevabonomi@mssm.edu.
  • Isotta Landi
    The Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, 770 Lexington Ave, 15th Fl, New York, NY, 10065, USA.
  • Leslee J Shaw
    Division of Cardiology, Emory University School of Medicine, Atlanta, GA, USA.
  • Erwin Böttinger
    Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, USA.
  • Ipek Ensari
    Columbia University Data Science Institute, New York, NY, 10025, USA. Electronic address: ie2145@columbia.edu.
  • Thomas J Fuchs
    Weill Cornell Medicine, New York, USA; Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, USA; Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, USA. Electronic address: gac2010@med.cornell.edu.

Keywords

External Resources

Popular Topics
Recent Journals