March 11, 2024JAMA Network OpenOpen Access

Generative Artificial Intelligence to Transform Inpatient Discharge Summaries to Patient-Friendly Language and Format

View Full Paper

Ask AI

Bookmark

Large language models transformed complex discharge summaries into accessible language, substantially improving readability over electronic health records.
Mean Flesch-Kincaid Grade Level decreased from 11.0 to 6.2, demonstrating a substantial reduction in reading difficulty for adult discharge summaries.
Cross-sectional study evaluation identified safety concerns and factual hallucinations, highlighting that generative artificial intelligence requires physician review.

Discussion

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

Implication

Cross-sectional study demonstrates large language models improve discharge summary readability in hospitalized adults, highlighting the need for physician oversight to ensure safety.

Cite This Study

Zaretsky et al. (2024) studied this question.

synapsesocial.com/papers/68e747eeb6db6435876c126c https://doi.org/10.1001/jamanetworkopen.2024.0357

View Full Paper

Ask AI

Bookmark

Implication

Cross-sectional study demonstrates large language models improve discharge summary readability in hospitalized adults, highlighting the need for physician oversight to ensure safety.

Generative Artificial Intelligence to Transform Inpatient Discharge Summaries to Patient-Friendly Language and Format

Key Points

Discussion

Implication

Cite This Study

Generative Artificial Intelligence to Transform Inpatient Discharge Summaries to Patient-Friendly Language and Format

Key Points

Discussion

Implication

Cite This Study

Keep reading

Keep reading