De-identification is not enough: a comparison between de-identified and synthetic clinical notes
Atiquer Rahman Sarkar, Yao-Shun Chuang, Noman Mohammed, Xiaoqian Jiang · 2024
Read De-identification is not enough: a comparison between de-identified and synthetic clinical notes by Atiquer Rahman Sarkar, Yao-Shun Chuang, Noman Mohammed, Xiaoqian Jiang (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-11607336.txt.
Description
Sarkar, Chuang, Mohammed, and Jiang compare de-identified and synthetic clinical notes for privacy, in work from twenty twenty-four. Removing names and identifiers is the standard way to share medical records for research. Synthetic data, generated to mimic real data, is a newer alternative.
Large language models now make synthetic clinical notes plausible. The team demonstrated weaknesses in de-identification of real notes, where residual details can re identify patients. They then tested whether synthetic notes keep research utility. The comparison asks a practical question for hospitals: which sharing route protects patients while still letting science proceed.
Catalog record
| CREATOR | Atiquer Rahman Sarkar, Yao-Shun Chuang, Noman Mohammed, Xiaoqian Jiang |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 57 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |