Could AI be used to make discharge summaries easier for patients to understand

Embargoed until: Publicly released: 2024-03-12 02:00

International

Photo by Jonathan Kemper on Unsplash

Hospital patients can access their discharge summary, which contains all the information about their hospital stay, through their health record, however, these summaries are often full of technical language and difficult to understand. A team of international researchers tested an AI's ability to re-word 50 discharge summaries to be easier to understand but still accurate. The researchers say the AI was able to improve the patient-friendliness of the summaries, however, some summaries omitted potentially important details or contained inaccurate information. The researchers say their findings suggest AI could be useful for improving the readability of these summaries, however with AI's current capability, any re-worded summaries would need to be reviewed by a qualified human.

Media release

From: JAMA

About The Study: The findings of this study of 50 discharge summaries suggest that large language models can be used to translate discharge summaries into patient-friendly language and formats that are significantly more readable and understandable than discharge summaries as they appear in electronic health records. However, implementation will require improvements in accuracy, completeness, and safety. Given the safety concerns, initial implementation will require physician review.

Attachments

Note: Not all attachments are visible to the general public. Research URLs will go live after the embargo ends.

Research JAMA, Web page The URL will go live after the embargo ends

Journal/
conference: JAMA Network Open

Research:Paper

Organisation/s: New York University, USA

Funder: None reported.

Media Contact/s

Contact details are only visible to registered journalists.