The quality and safety of using generative AI to produce patient-centred discharge instructions
Kristian Stanceski, Sharleen Zhong, Xumou Zhang, Sam Khadra, Marguerite Tracy, Linda Koria, Sarita Lo, Vasi Naganathan, Jinman Kim, Adam G Dunn, Julie Ayre · 2024
Read The quality and safety of using generative AI to produce patient-centred discharge instructions by Kristian Stanceski, Sharleen Zhong, Xumou Zhang, Sam Khadra, Marguerite Tracy, Linda Koria, Sarita Lo, Vasi Naganathan, Jinman Kim, Adam G Dunn, Julie Ayre (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11579500.txt.
Description
Kristian Stanceski leads a large team in grading AI-written discharge notes for patients. The paper is from two thousand twenty-four. Notes that fit the patient can lift follow-through and outcomes after a hospital stay. They test GPT-3.5 drafts built from a hundred real discharge summaries.
Each draft is checked for safety, truth, and plain words. Near one in five holds a safety flaw tied to the tool. A small share invents facts, and some add drugs the patient never had. The tool can shape warm, clear notes, the team finds, but care in how it is rolled out is a must to dodge harm.
Catalog record
| CREATOR | Kristian Stanceski, Sharleen Zhong, Xumou Zhang, Sam Khadra, Marguerite Tracy, Linda Koria, Sarita Lo, Vasi Naganathan, Jinman Kim, Adam G Dunn, Julie Ayre |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 24 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |