皮肤梭形细胞黑色素瘤患者生存预测模型的构建及验证

背景与目的：梭形细胞黑色素瘤（spindle cell melanoma,SCM）是一种罕见的黑色素瘤类型,有关SCM患者生存预后的研究较少。通过提取公共数据库中的SCM临床信息,构建并验证皮肤SCM患者5和10年癌症特异性生存率（cancer-specific survival,CSS）和总生存率（overall survival,OS）的生存预测模型。方法：从美国国立癌症研究所监测、流行病学和最终结果（Surveillance, Epidemiology, and End Results,SEER）数据库筛选出共1 445例患者,分成建模组（n=1 011）和验证组（n=434）。通过单因素和多因素COX回归分析确定独立预后影响因素,建立列线图预测模型。利用一致性指数（concordance index,C-index）、受试者工作特征（receiver operating characteristic,ROC）曲线和校准曲线评估模型的区分度和准确性,利用决策曲线分析（decision curve analysis,DCA）评估模型的临床实用性。结果：年龄、肿瘤部位、肿瘤厚度、溃疡、N分期、M分期及手术共7个独立预后影响因素纳入预测模型,CSS和OS预测模型在建模组中的C-index分别为0.778和0.753,在验证组中的C-index为0.749和0.712。建模组5和10年CSS的曲线下面积（area under curve,AUC）分别为0.815和0.825,5和10年OS的AUC分别为0.803和0.825,验证组5和10年CSS的AUC分别为0.777和0.836,5和10年OS的AUC分别为0.754和0.799。校准曲线与45°线贴合良好,DCA显示,列线图模型在较广泛阈概率范围内有临床净收益,具有良好的临床应用价值。结论：列线图对于皮肤SCM患者预后具有良好的预测能力和临床应用价值。

Construction and validation of the survival prediction model for patients with cutaneous spindle cell melanoma

Background and purpose: Spindle cell melanoma (SCM) is a rare type of melanoma with few studies on its survival prognosis. The nomogram for predicting 5- and 10-year cancer-specific survival (CSS) and overall survival (OS) of patients with cutaneous SCM was constructed and validated by extracting SCM clinical information from a public database. Methods: A total of 1 445 patients were screened from the Surveillance, Epidemiology, and End Results (SEER) database and divided into training cohort (n=1 011) and validation cohort (n=434). The nomogram was constructed based on these independent prognostic factors which were determined by univariate and multivariate COX regression analyses. The concordance index (C-index), receiver operating characteristic (ROC) curve and calibration curve were used to evaluate the discrimination and accuracy of the nomogram. Decision curve analysis (DCA) was used to evaluate the clinical utility of the model. Results: Age, tumor site, thickness, ulceration, N stage, M stage and surgery were included in the prediction model. The C-index of the nomogram was 0.778 (CSS) and 0.753 (OS) in the training cohort, and 0.749 (CSS) and 0.712 (OS) in the validation cohort, respectively. The area under curve (AUC) of 5- and 10-year CSS were 0.815 and the AUC of 5- and 10-year OS were 0.825, and the AUC of 5- and 10-year OS were 0.803 and 0.825 in the training cohort, respectively. The AUC of 5- and 10-year were 0.777 and 0.836, and 0.754 and 0.799 in the validation cohort, respectively. The calibration curve fitted well with the 45° line. DCA showed that the nomogram had the clinical net benefit in a wide range of threshold probabilities and had good clinical application value. Conclusion: The nomogram had good predictive ability and clinical application value for the prognosis of SCM patients.