目的 探讨甲胎蛋白（AFP）阴性肝细胞癌（HCC）患者预后相关因素，构建列线图以预测患者生存时间。 方法 回顾性分析监测、流行病学和最终结果（SEER）数据库提取的2 064例AFP阴性HCC患者数据，将所有患者按7∶3比例随机分为训练集和内部验证集，以湖南省中西医结合医院101例AFP阴性HCC患者作为外部验证集。将单因素Cox回归分析结果纳入多因素分析，采用多因素Cox分析获得AFP阴性HCC患者的独立危险因素，构建AFP阴性HCC患者癌症特异生存（CSS）预后列线图。采用时间依赖受试者工作特征曲线（ROC）、校准图和决策曲线分析（DCA）评估列线图的预测效能和临床实用性。将列线图所得总分进行风险分层，比较列线图和美国癌症联合委员会（AJCC）分期系统的风险区分程度。 结果 采用多因素Cox回归分析筛选出10个独立危险因素，构建AFP阴性HCC患者3、4和5年CSS预后列线图，包括患者年龄、病理分级、手术情况、放疗情况、化疗情况、肺转移情况、肿瘤大小、肿瘤T分期、肿瘤M分期和婚姻状况。3、4和5年时间依赖ROC曲线下面积（AUC），训练集分别为0.807（95%CI：0.786~0.828）、0.804（95%CI：0.782~0.826）和0.813（95%CI：0.790~0.835），内部验证集分别为0.776（95%CI：0.743~0.810）、0.772（95%CI：0.737~0.808）和0.789（95%CI：0.752~0.826），外部验证集分别为0.773（95%CI：0.677~0.868）、0.746（95%CI：0.620~0.872）和0.736（95%CI：0.577~0.895）。校准图验证列线图能够很好地拟合到完美曲线上。DCA曲线显示列线图在某特定概率阈值上的净收益明显高于AJCC分期在某特定概率时净收益。与AJCC分期比较，列线图具有较好的识别高风险人群的能力。 结论 血清中AFP表达是HCC患者的预后指标之一，对于部分血清中AFP阴性表达的HCC患者应区别对待，基于多个风险因素建立的列线图模型有望成为临床评估AFP阴性HCC患者CSS的有效工具。

Objective To discuss the factors related to the prognosis in the alpha fetoprotein （AFP） negative hepatocellular carcinoma （HCC） patients，and to construct the nomogram for predicting the survival time of the patients. Methods The retrospective analysis on data of 2 064 cases of AFP negative HCC patients extracted from the Surveillance， Epidemiology， and End Results （SEER） Database was conducted， and all the patients were divided into training cohort and internal validation cohort at a ratio of 7∶3， and 101 AFP negative HCC patients from the Integrated Traditional Chinese and Western Medicine Hospital in Hunan Province were regarded as the external validation cohort.The univariate Cox regression analysis results were incorporated into the multivariate analysis， and the independent risk factors for the AFP negative HCC patients were obtained by multivariate Cox analysis to build a cancer specific survival （CSS） prognosis nomogram for the AFP negative HCC patients. The predictive efficacy and clinical utility of the nomogram were evaluated by time-dependent receiver operating characteristic curve （ROC）， calibration plots， and decision curve analysis （DCA）. The total score obtained from the nomogram was used for the risk stratification to compare the degree of risk discrimination between the nomogram and the American Joint Committee on Cancer （AJCC） staging system. Results Ten independent risk factors were selected by multivariate Cox regression analysis to construct 3-year， 4-year， and 5-year CSS prognostic nomograms for the AFP negative HCC patients， including the patient’s age， pathological grade， surgical status， radiotherapy status， chemotherapy status， lung metastasis status， tumor size， tumor T stage， tumor M stage， and marital status. The area under curve （AUC） for the 3-year， 4-year， and 5-year time-dependent ROC in the training cohort were 0.807 （95% CI： 0.786－0.828）， 0.804 （95% CI： 0.782－0.826）， and 0.813 （95% CI： 0.790－0.835）， respectively. In the internal validation cohort， they were 0.776 （95% CI： 0.743－0.810）， 0.772 （95% CI： 0.737－0.808）， and 0.789 （95% CI： 0.752－0.826）， and in the external validation cohort， they were 0.773 （95% CI： 0.677－0.868）， 0.746 （95% CI： 0.620－0.872）， and 0.736 （95% CI： 0.577－0.895）. The calibration plots verified that the nomogram fitted well with the perfect line.The DCA curve revealed that the net benefit of the nomogram was significatly higer than that of the AJCC staging system at certain probability thresholds compared with AJCC staging， the nomogram had a better ability to identify high-risk individuals. Conclusion The serum AFP expression is one of the prognostic markers for the HCC patients. For those patients with AFP negative expression in serum， different considerations should be taken. The nomogram model based on multiple risk factors is a promising clinical tool for assessing the CSS in the AFP negative HCC patients.