Related Experiment Video
Updated: Oct 25, 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 Improves Prognostic Stratification in Esophageal Squamous Cell Carcinoma Receiving Neoadjuvant
Jian Zheng1, Wenbin Shen2, Jianzhong Cao3
1Department of Radiation Oncology Tianjin Medical University Cancer Institute & Hospital National Clinical Research Center for Cancer State Key Laboratory of Druggability Evaluation and Systematic Translational Medicine Key Laboratory of Cancer Prevention and Therapy Tianjin's Clinical Research Center for Cancer Tianjin China.
Abstract:
Lymph nodes (LNs), principal sites of antitumor immunity, may undergo immune-mediated regression; whether neoadjuvant chemoimmunotherapy (NCIT)-induced regression indicates prognosis in esophageal squamous cell carcinoma (ESCC) remains unclear. We aimed to establish and validate a lymph node regression grade (LNRG) system for prognostic stratification. This multicenter, retrospective cohort study analyzed 965 patients receiving PD-1-based NCIT and surgery at three Chinese tertiary cancer centers. LNRG was the ratio of summed viable tumor area to summed bed area (residual viable plus regressed preexisting tumor) across all dissected LNs. Negative LNs were assigned LNRG 0. Survival and predictive performance were assessed using Kaplan-Meier/Cox regression, time-dependent area under the curve, Brier score, net reclassification improvement, and integrated discrimination improvement. Overall, 28,882 LNs were evaluated; patients were classified as LNRG 0-4 in 385 (39.9%), 150 (15.5%), 26 (2.7%), 141 (14.6%), and 263 (27.3%), respectively. LNRG independently predicted disease-free and overall survival, with Grades 1-2 conferring the most favorable outcomes and Grade 4 the poorest. A random survival forest model incorporating LNRG, tumor regression grade, ypAJCC stage, and perineural invasion predicted 2-year disease-free survival in training and external validation cohorts. LNRG is a novel, independent prognostic indicator after NCIT.