Establishment of a Dynamic Nomogram for Predicting the Risk of Lymph Node Metastasis in T1 Stage Colorectal Cancer

Zitao Liu; Chao Huang; Huakai Tian; Yu Liu; Yongshan Huang; Zhengming Zhu

doi:10.3389/fsurg.2022.845666

Establishment of a Dynamic Nomogram for Predicting the Risk of Lymph Node Metastasis in T1 Stage Colorectal Cancer

Front Surg. 2022 Mar 21:9:845666. doi: 10.3389/fsurg.2022.845666. eCollection 2022.

Authors

Zitao Liu¹, Chao Huang¹, Huakai Tian¹, Yu Liu¹, Yongshan Huang¹, Zhengming Zhu¹

Affiliation

¹ Department of Gastrointestinal Surgery, The Second Affiliated Hospital of Nanchang University, Nanchang, China.

Abstract

Background: Accurate prediction of the risk of lymph node metastasis in patients with stage T1 colorectal cancer is crucial for the formulation of treatment plans for additional surgery and lymph node dissection after endoscopic resection. The purpose of this study was to establish a predictive model for evaluating the risk of LNM in patients with stage T1 colorectal cancer.

Methods: The clinicopathological and imaging data of 179 patients with T1 stage colorectal cancer who underwent radical resection of colorectal cancer were collected. LASSO regression and a random forest algorithm were used to screen the important risk factors for LNM, and a multivariate logistic regression equation and dynamic nomogram were constructed. The C index, Calibration curve, and area under the ROC curve were used to evaluate the discriminant and prediction ability of the nomogram. The net reclassification index (NRI), comprehensive discriminant improvement index (IDI), and clinical decision curve (DCA) were compared with traditional ESMO criteria to evaluate the accuracy, net benefit, and clinical practicability of the model.

Results: The probability of lymph node metastasis in patients with T1 colorectal cancer was 11.17% (20/179). Multivariate analysis showed that the independent risk factors for LNM in T1 colorectal cancer were submucosal invasion depth, histological grade, CEA, lymphovascular invasion, and imaging results. The dynamic nomogram model constructed with independent risk factors has good discrimination and prediction capabilities. The C index was 0.914, the corrected C index was 0.890, the area under the ROC curve was 0.914, and the accuracy, sensitivity, and specificity were 93.3, 80.0, and 91.8%, respectively. The NRI, IDI, and DCA show that this model is superior to the ESMO standard.

Conclusion: This study establishes a dynamic nomogram that can effectively predict the risk of lymph node metastasis in patients with stage T1 colorectal cancer, which will provide certain help for the formulation of subsequent treatment plans for patients with stage T1 CRC after endoscopic resection.

Keywords: LASSO regression algorithm; T1 stage colorectal cancer; dynamic nomogram; lymph node metastasis (LNM); random forest.