Performance of Large Language Models for Radiology Report Impression Generation: A Systematic Review
Abstract
To date, no systematic review has focused on the application of large language models (LLMs) for generating impressions from findings in radiology reports. The purpose of this paper is to systematically review the performance of LLMs in this task and their associated evaluation methodologies.
Fields of Study & Subjects
Artificial Intelligence in Healthcare and Education
Multimodal Machine Learning Applications
Topic Modeling
Publication details
- Journal / source
- Open Science Framework
- Publication date
- 14 January 2026