Department of Clinical Research Center, Dazhou Central Hospital, Dazhou, Sichuan, China.
National Center for International Research of Biological Targeting Diagnosis and Therapy, Guangxi Key Laboratory of Biological Targeting Diagnosis and Therapy Research, Collaborative Innovation Center for Targeting Tumor Diagnosis and Therapy, Guangxi Medical University, Guangxi Zhuang Autonomous Region, Guangxi Zhuang Autonomous Region, China.
PeerJ. 2022 Apr 11;10:e13196. doi: 10.7717/peerj.13196. eCollection 2022.
Assessment of colorectal cancer (CRC) lymph node metastasis (LNM) is critical to the decision of surgery, prognosis, and therapy strategy. In this study, we aimed to develop and validate a multiple tumor marker nomogram for predicting LNM in CRC patients.
A total of 674 patients who met the inclusion criteria were collected and randomly divided into primary cohort and internal test cohort at a ratio of 7:3. An external test cohort enrolled 178 CRC patients from the West China Hospital. Clinicopathologic variables were obtained from electronic medical records. The least absolute shrinkage and selection operator (LASSO) and interquartile range analysis were carried out for variable dimensionality reduction and feature selection. Multivariate logistic regression analysis was conducted to develop predictive models of LNM. The performance of the established models was evaluated by the receiver operating characteristic (ROC) curve, calibration belt, and clinical usefulness.
Based on minimum criteria, 18 potential features were reduced to six predictors by LASSO and interquartile range in the primary cohort. The model demonstrated good discrimination and ROC curve (AUC = 0.721 in the internal test cohort, AUC = 0.758 in the external test cohort) in LNM assessment. Good calibration was shown for the probability of CRC LNM in the internal and external test cohorts. Decision curve analysis illustrated that multi-tumor markers nomogram was clinically useful.
The study proposed a reliable nomogram that could be efficiently and conveniently utilized to facilitate the assessment of individually-tailored LNM in patients with CRC, complementing imaging and biopsy tests.
结直肠癌（CRC）淋巴结转移（LNM）的评估对于手术决策、预后和治疗策略至关重要。本研究旨在开发和验证一种用于预测 CRC 患者 LNM 的多肿瘤标志物列线图。
共收集符合纳入标准的 674 例患者，并按 7:3 的比例随机分为初级队列和内部测试队列。外部测试队列纳入了来自华西医院的 178 例 CRC 患者。从电子病历中获取临床病理变量。采用最小绝对收缩和选择算子（LASSO）和四分位距分析进行变量降维和特征选择。采用多变量逻辑回归分析建立 LNM 的预测模型。通过接收者操作特征（ROC）曲线、校准带和临床实用性评估建立模型的性能。
基于最小标准，LASSO 和四分位距在初级队列中从 18 个潜在特征中减少到 6 个预测因子。该模型在 LNM 评估中表现出良好的区分度和 ROC 曲线（内部测试队列 AUC=0.721，外部测试队列 AUC=0.758）。内部和外部测试队列中均显示 CRC LNM 概率的良好校准。决策曲线分析表明，多肿瘤标志物列线图具有临床实用性。
本研究提出了一种可靠的列线图，可以有效地、方便地用于评估 CRC 患者个体化的 LNM，补充影像学和活检检查。
