Integrating a host biomarker with a large language model for diagnosis of lower respiratory tract infection
Hoang Van Phan, Natasha Spottiswoode, Emily C Lydon, Victoria T Chu, Adolfo Cuesta, Alexander D Kazberouk, Natalie L Richmond, Padmini Deosthale, Carolyn S Calfee, Charles R Langelier · 2025
Read Integrating a host biomarker with a large language model for diagnosis of lower respiratory tract infection by Hoang Van Phan, Natasha Spottiswoode, Emily C Lydon, Victoria T Chu, Adolfo Cuesta, Alexander D Kazberouk, Natalie L Richmond, Padmini Deosthale, Carolyn S Calfee, Charles R Langelier (2025) 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-12708615.txt.
Description
Hoang Phan and co-authors pair a lung gene signal with a language model to diagnose chest infection. In very ill patients, lung infection can look just like non infectious lung failure. Wrong calls in either direction carry costs. The team tested a combined judge on critically ill adults.
One input is the level of a gene, FABP4, read from lung related samples. The other is a large language model's read of the chart text. Together they beat either input alone, and beat the admitting team's own call by a wide margin. A second group of patients confirmed the gain. The authors suggest the pairing could sharpen early calls in intensive care.
Catalog record
| CREATOR | Hoang Van Phan, Natasha Spottiswoode, Emily C Lydon, Victoria T Chu, Adolfo Cuesta, Alexander D Kazberouk, Natalie L Richmond, Padmini Deosthale, Carolyn S Calfee, Charles R Langelier |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 33 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |