基于SEER数据库的转移性结肠癌患者早期死亡预测列线图模型构建

Nomogram for Predicting Early Death in Patients with Metastatic Colon Cancer Based on SEER Database

目的构建预测转移性结肠癌(mCC)患者早期死亡的列线图模型。方法从SEER数据库中选择6669例符合条件的mCC患者。根据多因素Logistic回归中的危险因素构建列线图。通过C-index、校准曲线和临床决策曲线分析(DCA)评估列线图的预测性能。结果原发肿瘤位置、肿瘤分化、T分期、M分期、骨转移、脑转移、CEA、肿瘤大小、年龄和婚姻状态是mCC患者早期死亡的独立影响因素。基于这些变量构建列线图,C-index和校准曲线显示模型具有很好的预测能力,DCA曲线显示列线图可以使患者有较好的临床获益。结论该列线图具有良好的预测能力,能够帮助医生识别可能早期死亡的高危mCC患者,有助于制定个性化治疗策略。

Objective To construct a Nomogram model that can accurately predict early death of metastatic colon cancer(mCC).Methods A total of 6669 patients from the SEER database were identified using inclusion and exclusion criteria.Multivariate logistic regression was used to identify risk factors for early mortality and to construct a Nomogram.The predictive performance of the Nomogram was evaluated by C-index,calibration curve,and decision curve analysis(DCA).Results Primary tumor location,differentiation grade,T stage,M stage,bone metastases,brain metastases,CEA,tumor size,age and marital status were independent factors for early death in patients with mCC.A Nomogram was constructed based on these variables.The C-index and the calibration curve of the Nomogram showed the good predictive ability of the nomogram.DCA showed that the Nomogram had a superior clinical net benefit in predicting early death compared with TNM stage.Conclusion The developed Nomogram has good predictive ability and can help guide clinicians to identify patients with high-risk mCC for individualized diagnosis and treatment.