upcarta
  • Sign In
  • Sign Up
  • Explore
  • Search

Exploring the Boundaries of GPT-4 in Radiology

  • Paper
  • Oct 23, 2023
  • #Naturallanguageprocessing #Health
Ozan Oktay
@ozanoktay__
(Author)
Qianchu (Flora) Liu
@QianchuL
(Author)
Stephanie Hyland
@stephhyland2
(Author)
arxiv.org
Read on arxiv.org
1 Recommender
1 Mention
The recent success of general-domain large language models (LLMs) has significantly changed the natural language processing paradigm towards a unified foundation model across domain... Show More

The recent success of general-domain large language models (LLMs) has significantly changed the natural language processing paradigm towards a unified foundation model across domains and applications. In this paper, we focus on assessing the performance of GPT-4, the most capable LLM so far, on the text-based applications for radiology reports, comparing against state-of-the-art (SOTA) radiology-specific models. Exploring various prompting strategies, we evaluated GPT-4 on a diverse range of common radiology tasks and we found GPT-4 either outperforms or is on par with current SOTA radiology models. With zero-shot prompting, GPT-4 already obtains substantial gains (≈ 10% absolute improvement) over radiology models in temporal sentence similarity classification (accuracy) and natural language inference (F1). For tasks that require learning dataset-specific style or schema (e.g. findings summarisation), GPT-4 improves with example-based prompting and matches supervised SOTA. Our extensive error analysis with a board-certified radiologist shows GPT-4 has a sufficient level of radiology knowledge with only occasional errors in complex context that require nuanced domain knowledge. For findings summarisation, GPT-4 outputs are found to be overall comparable with existing manually-written impressions.

Show Less
Recommend
Post
Save
Complete
Collect
Mentions
See All
Ethan Mollick @emollick · Oct 25, 2023
  • Post
  • From Twitter
Work from Harvard & Microsoft suggests GPT-4 is surprisingly helpful in radiology: “This study evaluates GPT-4 on a diverse range of common radiology text-based tasks. We found GPT-4 either outperforms or is on par with task-specific radiology models.”
  • upcarta ©2025
  • Home
  • About
  • Terms
  • Privacy
  • Cookies
  • @upcarta