Large language models for simplifying radiology reports: a systematic review and meta-analysis of patient, public, and clinician evaluations

Key Points

• The research aims to assess how effective large language models are in simplifying radiology reports for various audiences.
• Conducted a systematic review of available literature on the use of AI for radiology report simplification.
• Performed meta-analysis on patient, public, and clinician evaluations.
• Examined outcomes related to understanding and satisfaction.
• Found that large language models significantly improve understanding of radiology reports among patients and clinicians.
• Highlighted that simplified reports lead to higher satisfaction rates across evaluated groups.
• Indicated a need for better integration of AI tools in clinical settings to enhance communication.