Large language models for optimizing clinical trial recruitment in ICUs: application to ventilator-induced diaphragm dysfunction
Kieffer Korvin, Zeno Loi, David Morquin, Boris Jung, Joris Pensier, Yassir Aarab, Nacim Benchabane, Eddine Bendiab, Sarah Colombani, Alain Lacampagne, Kevin Yauy, Stefan Matecki · 2026
Read Large language models for optimizing clinical trial recruitment in ICUs: application to ventilator-induced diaphragm dysfunction by Kieffer Korvin, Zeno Loi, David Morquin, Boris Jung, Joris Pensier, Yassir Aarab, Nacim Benchabane, Eddine Bendiab, Sarah Colombani, Alain Lacampagne, Kevin Yauy, Stefan Matecki (2026) 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/PMC13262427.txt.
Description
Kieffer Korvin and colleagues test large language models, AI tools that read text, for trial recruitment in a 2026 journal article. Their test case was a planned trial on diaphragm weakness caused by breathing machines in intensive care. Finding eligible patients by hand is slow, so they built a screening pipeline that reads discharge summaries.
Six clinicians marked 50 stays to set a reference standard, and the best model scored 0.82 on a standard accuracy measure. Applied to 1,342 stays from 2024, it flagged 185 possible candidates, and expert review confirmed 133 as eligible. That gave a 72 percent hit rate among flagged cases. The authors estimate the workflow cut clinician review time by 86 percent.
Catalog record
| CREATOR | Kieffer Korvin, Zeno Loi, David Morquin, Boris Jung, Joris Pensier, Yassir Aarab, Nacim Benchabane, Eddine Bendiab, Sarah Colombani, Alain Lacampagne, Kevin Yauy, Stefan Matecki |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 10634 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |