Related Experiment Video
Updated: Aug 26, 2026

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
Published on: April 18, 2025
Lymph node regression score and highest nodal metastatic station: refining prognostic stratification in
Zhenyu Xu1, Xuejing Wu2, Kunling Li3
1Department of Colorectal Surgery, Fujian Medical University Union Hospital, 29 Xinquan Road, Fuzhou, Fujian, 350001, PR China.
Abstract:
Rectal mucinous adenocarcinoma (MAC) is a distinct rectal cancer subtype with heterogeneous outcomes after neoadjuvant chemoradiotherapy (nCRT), and robust tools for prognostic stratification remains limited. We retrospectively analyzed 159 patients with rectal MAC treated with nCRT and pathologically assessed the lymph node regression sum score (LRG-sum) and the highest nodal metastatic station. Kaplan-Meier and Cox regression analyses were performed to identify prognostic factors for disease-free survival (DFS), and a nomogram was subsequently constructed and validated against conventional ypN staging. DFS decreased progressively with increasing LRG-sum, with the high-score group showing the poorest survival and the low-score group the most favorable outcome (P = 0.0018). Multivariable analysis identified LRG-sum (HR = 1.016, P = 0.008), apical nodal metastasis (HR = 3.968, P = 0.013), and perineural invasion (HR = 2.123, P = 0.010) as independent predictors of DFS. The LRG-based nomogram outperformed ypN staging, with 1-, 3-, and 5-year AUCs of 0.779, 0.733, and 0.718, respectively, and demonstrated good calibration. Among ypN0 patients, complete nodal regression was associated with a prognosis comparable to that of patients with uninvolved lymph nodes (P = 0.641). These findings indicate that LRG-sum and highest nodal metastatic station provide prognostic information beyond conventional staging for rectal MAC, and we recommend their integration in routine pathologic reporting to facilitate individualized management.