General-Purpose Large Language Models Versus a Domain-Specific Natural Language Processing Tool for Label Extraction From Chest Radiograph Reports

AJR Am J Roentgenol. 2024 Apr;222(4):e2330573. doi: 10.2214/AJR.23.30573. Epub 2024 Jan 17.
No abstract available

Plain language summary

GPT-4 outperformed a radiology domain-specific natural language processing model in classifying imaging findings from chest radiograph reports, both with and without predefined labels. Prompt engineering for context further improved performance. The findings indicate a role for large language models to accelerate artificial intelligence model development in radiology by automating data annotation.

Publication types

  • Letter
  • Research Support, N.I.H., Extramural

MeSH terms

  • Humans
  • Natural Language Processing*
  • Radiography, Thoracic* / methods
  • Radiology Information Systems