Development and evaluation of an explainable machine learning selection pipeline for predicting neoadjuvant chemoradiotherapy response in locally advanced rectal cancer
Yijun Xu, Wei Gong, Lei Ji, Zhongxu Xing, Zhiyu Zhu, Zhibo Jin, Jiayu Zhang, Xinyi Wang, Songbing Qin, Yang Jiao, Lili Wang · 2026
Read Development and evaluation of an explainable machine learning selection pipeline for predicting neoadjuvant chemoradiotherapy response in locally advanced rectal cancer by Yijun Xu, Wei Gong, Lei Ji, Zhongxu Xing, Zhiyu Zhu, Zhibo Jin, Jiayu Zhang, Xinyi Wang, Songbing Qin, Yang Jiao, Lili Wang (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/PMC13560250.txt.
Description
Yijun Xu and colleagues propose a six-stage pipeline for choosing machine learning models that clinicians can truly understand, demonstrated on rectal cancer treatment response. Their 2026 study applies the workflow to 128 patients with locally advanced rectal cancer treated with chemoradiotherapy before surgery. Four methods were screened under fixed rules that weighed accuracy against how openly each model reasons.
Decision trees struck the best balance. Using only pretreatment tumor markers, the chosen trees predicted complete pathological response with an accuracy of 0.82 in the reported evaluation, and tumor regression grade with 0.76 in the parallel task. Follow-up checks ranked two blood markers, CEA and CA19-9, as the strongest predictors, with lower starting levels favoring response. The pipeline ends with a clinical logic sanity check. The authors offer the framework for small clinical datasets and call for multicenter validation.
Catalog record
| CREATOR | Yijun Xu, Wei Gong, Lei Ji, Zhongxu Xing, Zhiyu Zhu, Zhibo Jin, Jiayu Zhang, Xinyi Wang, Songbing Qin, Yang Jiao, Lili Wang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 67572 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |