A CT-based nomogram for preoperative prediction of metastatic enlarged regional lymph nodes after neoadjuvant immunochemotherapy in esophageal squamous cell carcinoma

CHEN Jiahui; GAO Yingying; NING Ziyu; LI Xinming; HAN Lujun; XIE Chenyi; HU Yihuai; LIU Zaiyi

doi:10.19300/j.2026.L22593

Abstract：Objective To develop a nomogram based on subjective features from contrast-enhanced CT and to evaluate its ability to predict the metastatic risk of enlarged regional lymph nodes after neoadjuvant immunochemotherapy(nICT)in patients with esophageal squamous cell carcinoma(ESCC).Methods This retrospective multicenter study enrolled 60 patients with locally advanced ESCC who underwent nICT followed by surgical resection at three medical centers.A total of 81 radiologically enlarged regional lymph nodes identified on post-nICT CT scans with matched pathological results were analyzed.Long-axis diameter(LAD),short-axis diameter(SAD),and multiple radiologic features of lymph nodes were evaluated.Univariate and multivariate logistic regression analyses were performed to identify independent predictors of nodal metastasis and to construct a nomogram.Model performance was assessed using receiver operating characteristic(ROC)curves and the area under the curve(AUC),with DeLong's test used for comparisons.Internal validation was conducted using bootstrap resampling.Model discrimination,calibration,and clinical utility were evaluated using the concordance index(C-index),calibration curves,and decision curve analysis(DCA),respectively.Results Multivariate analysis identified a smaller percentage change in LAD(ΔLAD),the presence of radiologic extranodal extension(iENE),and loss of kidney-shaped morphology as independent predictors of lymph node metastasis.The nomogram demonstrated excellent predictive performance,with a C-index of 0.903 and a bootstrap-corrected C-index of 0.893.The AUC of the nomogram was 0.903,with a sensitivity of 90.0%and specificity of 78.7%,significantly outperforming any single imaging feature alone(all P<0.05).Calibration curves showed good agreement between predicted probabilities and observed outcomes.DCA indicated that the combined model provided a higher net benefit across a wide range of threshold probabilities(0.10-0.75).In addition,a ΔLAD cutoff value greater than 27%effectively differentiated reactive nodal enlargement from metastatic nodes,with a sensitivity of 75.0%and specificity of 63.9%.Conclusion The CT-based nomogram developed in this study enables reliable preoperative prediction of metastatic status in enlarged regional lymph nodes after nICT in ESCC patients.This model may serve as a practical imaging tool to distinguish immune-related pseudoprogression from true nodal metastasis and to facilitate individualized treatment planning.