Inflammatory phenotyping by latent class analysis and machine learning-based prediction of postoperative complications in pediatric appendicitis: a retrospective cohort study
Yanhui Wang, Fengguang Ye, Xiangxin Zeng, Songbin Lin, Weicheng Huang, Yuexian Yang, Wenyou Chen · 2026
Read Inflammatory phenotyping by latent class analysis and machine learning-based prediction of postoperative complications in pediatric appendicitis: a retrospective cohort study by Yanhui Wang, Fengguang Ye, Xiangxin Zeng, Songbin Lin, Weicheng Huang, Yuexian Yang, Wenyou Chen (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/PMC13328021.txt.
Description
Yanhui Wang and co-authors sort children with appendicitis into inflammation types in a 2026 cohort study. Single blood markers miss how varied the body's response can be, so the team applied latent class analysis to nine indicators in 402 children who had keyhole appendix removal. Learning models then forecast complications after surgery.
Three types appeared: low inflammation at 29.4 percent, moderate at 40.8 percent, and high at 29.9 percent of the group, differing in markers, perforation, stay length, and complications, which hit 17.4 percent overall. Perforation alone independently predicted trouble, with an odds ratio of 3.03 in their model, while the XGBoost model forecast complications with an AUC of 0.911 on held-back cases. Phenotype plus algorithm could guide watch intensity.
Catalog record
| CREATOR | Yanhui Wang, Fengguang Ye, Xiangxin Zeng, Songbin Lin, Weicheng Huang, Yuexian Yang, Wenyou Chen |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 34081 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |