Using machine learning algorithms based on laboratory indicators to establish a diagnostic model for lung cancer
Jie Wu, Lu Zhang, Zheng Zhang, Shuo Gao, Seng Wang, Xuewen Zheng, Xuejing Xu, Hai Ding, Han Shen, Hong Yan · 2026
Read Using machine learning algorithms based on laboratory indicators to establish a diagnostic model for lung cancer by Jie Wu, Lu Zhang, Zheng Zhang, Shuo Gao, Seng Wang, Xuewen Zheng, Xuejing Xu, Hai Ding, Han Shen, Hong Yan (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/PMC13555920.txt.
Description
Jie Wu leads a ten-author team training learning models to sort lung nodules by routine blood tests in a 2026 study. Scans and biopsies remain the standard route, yet both are invasive or hard to repeat. Their Nanjing hospital cohort held 1,238 patients with lung nodules, plus 250 healthy controls. Five algorithms competed across six sorting tasks, from healthy versus benign to early versus late cancer.
A boosted-tree model won overall and became the final tool. Feature counts differed by task, with the widest set used to separate healthy people from benign cases. Accuracy soared for some contrasts and stayed modest for benign versus early cancer, the hardest call. An explanation method ranked which lab values drove each judgement for clinicians.
Catalog record
| CREATOR | Jie Wu, Lu Zhang, Zheng Zhang, Shuo Gao, Seng Wang, Xuewen Zheng, Xuejing Xu, Hai Ding, Han Shen, Hong Yan |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 31544 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |