logo
ResearchBunny Logo
ZERO-SHOT INFORMATION EXTRACTION FROM RADIOLOGICAL REPORTS USING CHATGPT

Computer Science

ZERO-SHOT INFORMATION EXTRACTION FROM RADIOLOGICAL REPORTS USING CHATGPT

D. Hu, B. Liu, et al.

This study investigates ChatGPT's ability to perform zero-shot information extraction from radiological reports. Conducted by Danqing Hu, Bing Liu, Xiaofeng Zhu, Xudong Lu, and Nan Wu, the research demonstrates competitive performance with CT reports, highlighting both efficacy and existing limitations.

00:00
00:00
Playback language: English
Abstract
This study explores the capability of ChatGPT, a large language model, to perform zero-shot information extraction from radiological reports. A prompt template was designed, combined with CT reports as input to ChatGPT, and a post-processing module was developed to structure the extracted information. Experiments using 847 CT reports showed ChatGPT achieved competitive performance on some extraction tasks compared to a baseline system, but limitations remain.
Publisher
Not specified in the provided text
Published On
Jan 01, 2023
Authors
Danqing Hu, Bing Liu, Xiaofeng Zhu, Xudong Lu, Nan Wu
Tags
ChatGPT
zero-shot learning
information extraction
radiological reports
CT reports
machine learning
natural language processing

Related Publications

Explore these studies to deepen your understanding of the subject.

A scoping review of large language model based approaches for information extraction from radiology reports
Medicine and Health

A scoping review of large language model based approaches for information extraction from radiology reports

D. Reichenpfader, H. Müller, et al.

Multilingual translation for zero-shot bio-medical classification using BioTranslator
Biology

Multilingual translation for zero-shot bio-medical classification using BioTranslator

H. Xu, A. Woicik, et al.

A general-purpose material property data extraction pipeline from large polymer corpora using natural language processing
Engineering and Technology

A general-purpose material property data extraction pipeline from large polymer corpora using natural language processing

P. Shetty, A. C. Rajan, et al.

TRANSLATING RADIOLOGY REPORTS INTO PLAIN LANGUAGE USING CHATGPT AND GPT-4 WITH PROMPT LEARNING: PROMISING RESULTS, LIMITATIONS, AND POTENTIAL
Medicine and Health

TRANSLATING RADIOLOGY REPORTS INTO PLAIN LANGUAGE USING CHATGPT AND GPT-4 WITH PROMPT LEARNING: PROMISING RESULTS, LIMITATIONS, AND POTENTIAL

Q. Lyu, J. Tan, et al.

Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny