What question did this study set out to answer?

Use of Commercially Available Large Language Models to Generate Information Leaflets on Post–Intensive Care Syndrome: Clinical Utility Assessment

View Full Paper

Ask AI

Bookmark

This study evaluates the quality of information leaflets generated by large language models for post-intensive care syndrome.
Generated informational texts using 6 different large language models and 4 prompt designs.
Conducted expert reviews and evaluations by 10 individuals using a 10-point Likert scale.
Selected and analyzed 9 eligible texts after exclusions based on character count and content relevance.
Generated texts averaged scores of 6.8 or higher on evaluation criteria without any harmful content.
LLaMA 3 70B received the highest score using a step-by-step and text-augmented prompting approach.
Evaluation scores varied between healthcare professionals and non-medical personnel, indicating differences in assessment perspectives.

No takes yet. Share an insight, caveat, or question.

Randomized trial assesses quality of information leaflets generated by large language models, suggesting clinical utility for patient understanding.

Hata et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

Randomized trial assesses quality of information leaflets generated by large language models, suggesting clinical utility for patient understanding.