Patient-Friendly Discharge Summaries in Korea Based on ChatGPT: Software Development and Validation.

Hanjae Kim Hee Min Jin Yoon Bin Jung Seng Chan You

Published in: Journal of Korean medical science (2024)

Large-language models utilizing Few-shot prompts generally produce acceptable discharge summaries without significant misinformation. Our research highlights the potential of such models in creating patient-friendly discharge summaries for Korean patients to support patient-centered care.

Keyphrases

end stage renal disease
case report
newly diagnosed
healthcare
ejection fraction
chronic kidney disease
social media
palliative care
prognostic factors
peritoneal dialysis
autism spectrum disorder
quality improvement
patient reported outcomes