Zhang Qi, Liu Zehan, Liu Shuangqing, Wang Ming, Li Xinye, Xun Jing, Wang Xiangyu, Yang Qin, Wang Ximo, Zhang Dapeng
Tianjin Key Laboratory of Acute Abdomen Disease Associated Organ Injury and ITCWM Repair, Tianjin Nankai Hospital, Tianjin Medical University, Tianjin, China.
Integrated Chinese and Western Medicine Hospital, Tianjin University, Tianjin, China.
Front Surg. 2023 Jan 6;9:965401. doi: 10.3389/fsurg.2022.965401. eCollection 2022.
To construct a reliable nomogram available online to predict the postoperative survival of patients with perihilar cholangiocarcinoma.
Data from 1808 patients diagnosed with perihilar cholangiocarcinoma between 2004 and 2015 were extracted from the National Cancer Institute Surveillance, Epidemiology, and End Results (SEER) database. They were randomly divided into training and validation sets. The nomogram was established by machine learning and Cox model. The discriminant ability and prediction accuracy of the nomogram were evaluated by concordance index (C-index), receiver operator characteristic (ROC) curve and calibration curve. Kaplan-Meier curves show the prognostic value of the associated risk factors and classification system.
Machine learning and multivariate Cox risk regression model showed that sex, age, tumor differentiation, primary tumor stage(T), lymph node metastasis(N), TNM stage, surgery, radiation, chemotherapy, lymph node dissection were associated with the prognosis of perihilar cholangiocarcinoma patients relevant factors ( < 0.05). A novel nomogram was established. The calibration plots, C-index and ROC curve for predictions of the 1-, 3-, and 5-year OS were in excellent agreement. In patients with stage T1 and N0 perihilar cholangiocarcinoma, the prognosis of ≥4 lymph nodes dissected was better than that of 1- 3 lymph nodes dissected ( < 0.01).
The nomogram prognostic prediction model can provide a reference for evaluating the prognosis and survival rate of patients with perihilar cholangiocarcinoma. Patients with stage T1 and N0 perihilar cholangiocarcinoma have more benefits by increasing the number of lymph node dissection.
构建一个可在线获取的可靠列线图，以预测肝门部胆管癌患者的术后生存率。
从美国国立癌症研究所监测、流行病学和最终结果（SEER）数据库中提取2004年至2015年间诊断为肝门部胆管癌的1808例患者的数据。将他们随机分为训练集和验证集。通过机器学习和Cox模型建立列线图。通过一致性指数（C-index）、受试者操作特征（ROC）曲线和校准曲线评估列线图的判别能力和预测准确性。Kaplan-Meier曲线显示相关危险因素和分类系统的预后价值。
机器学习和多变量Cox风险回归模型显示，性别、年龄、肿瘤分化程度、原发肿瘤分期（T）、淋巴结转移（N）、TNM分期、手术、放疗、化疗、淋巴结清扫与肝门部胆管癌患者的预后相关因素（P＜0.05）。建立了一种新的列线图。预测1年、3年和5年总生存期的校准图、C-index和ROC曲线具有良好的一致性。在T1期和N0期肝门部胆管癌患者中，清扫≥4枚淋巴结的预后优于清扫1-3枚淋巴结的患者（P＜0.01）。
列线图预后预测模型可为评估肝门部胆管癌患者的预后和生存率提供参考。T1期和N0期肝门部胆管癌患者通过增加淋巴结清扫数量获益更多。
