Fine-Tuning Large Language Models for Structured Extraction of Infectious Disease–Related Information From Clinical Notes in Japanese Primary Care: Development and Internal Validation Study
Hiroshi Yoshihara, Haruka Maeda, Yuriko Hagiwara, Daichi Sato, Kei Kitajima, Akihiro Iwata, Nicolas Van de Velde, Yuta Nakamura, Yosuke Yamagishi, Ataru Igarashi, Javad Sarvestan · 2026
Read Fine-Tuning Large Language Models for Structured Extraction of Infectious Disease–Related Information From Clinical Notes in Japanese Primary Care: Development and Internal Validation Study by Hiroshi Yoshihara, Haruka Maeda, Yuriko Hagiwara, Daichi Sato, Kei Kitajima, Akihiro Iwata, Nicolas Van de Velde, Yuta Nakamura, Yosuke Yamagishi, Ataru Igarashi, Javad Sarvestan (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/pmc-13561044.txt.
Description
Hiroshi Yoshihara and co-authors tune language models to mine germ facts from Japanese clinic notes, in a study from 2026. Notes in health files hold rich, fast word on coughs, shots, and fevers, but as free text they hide from counts. Old watch ways lag and miss such grit.
The bank held 773 notes from 526 patients, marked by three doctors for germ signs and shot past. Four in five notes trained the models; one in five graded them. The aim is a form-filling tool that turns prose into rows a watch desk can sum, with low lag. Home checks come first, the team notes, ere the tool can feed a true watch. Notes, they show, can be taught to talk in tables.
Catalog record
| CREATOR | Hiroshi Yoshihara, Haruka Maeda, Yuriko Hagiwara, Daichi Sato, Kei Kitajima, Akihiro Iwata, Nicolas Van de Velde, Yuta Nakamura, Yosuke Yamagishi, Ataru Igarashi, Javad Sarvestan |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 37 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |