Automated classification of clinical T staging pulmonary oncology from chest CT reports: a natural language processing framework for real-world data utilization
Nobuo Nishijima, Kento Sugimoto, Shozo Konishi, Shoya Wada, Haruhiko Hirata, Masahiro Yanagawa, Takahiro Tsuboyama, Ayumi Fujii, Taizo Murata, Naoki Mihara, Katsuki Okada, Yasushi Matsumura, Noriyuki Tomiyama, Toshihiro Takeda · 2026
Read Automated classification of clinical T staging pulmonary oncology from chest CT reports: a natural language processing framework for real-world data utilization by Nobuo Nishijima, Kento Sugimoto, Shozo Konishi, Shoya Wada, Haruhiko Hirata, Masahiro Yanagawa, Takahiro Tsuboyama, Ayumi Fujii, Taizo Murata, Naoki Mihara, Katsuki Okada, Yasushi Matsumura, Noriyuki Tomiyama, Toshihiro Takeda (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/PMC13520422.txt.
Description
Nobuo Nishijima and colleagues build in 2026 software that reads chest CT reports and assigns lung cancer tumour stage automatically, following the ninth edition staging rules. Stage labels often sit buried in free text, which makes large real-world studies slow and costly.
The system mixes deep learning with rule checks, first judging whether a report holds enough detail, then assigning the substage. Most reports in training and test sets held enough detail. Accuracy scores stayed above 0.93 across sets, rising slightly when only fully detailed reports were staged. Automating this chore could unlock registry-scale research without manual chart review.
Catalog record
| CREATOR | Nobuo Nishijima, Kento Sugimoto, Shozo Konishi, Shoya Wada, Haruhiko Hirata, Masahiro Yanagawa, Takahiro Tsuboyama, Ayumi Fujii, Taizo Murata, Naoki Mihara, Katsuki Okada, Yasushi Matsumura, Noriyuki Tomiyama, Toshihiro Takeda |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 48770 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |