[摘要] 目的：建立基于放射学特征和临床实验室数据构建肝细胞癌(HCC)患者发生微血管侵犯(MVI)的预测模型，探讨HCC患者术前甲胎蛋白(AFP)和γ -谷氨酰转肽酶(GGT)的临床应用价值。方法: 回顾性地收集了南京医科大学第一附属医院479名HCC手术切除患者的临床数据，研究潜在相关因素对MVI的影响，并评估了血清AFP和GGT对提高模型预测性能的益处。采用单因素和多因素logistics回归分析来选择最终预测模型的变量，绘制了列线图nomogram。绘制了受试者工作特征曲线（ROC），通过ROC曲线下面积（AUC）、校准曲线和决策曲线分析（DCA）来评估模型的预测性能。通过敏感度、特异度和准确度分析进行预测性能比较。应用Kaplan-Meier曲线来评估患者的生存概率。结果: 在多因素分析中，肿瘤大小、肿瘤的边界不清楚、肿瘤是外生性的生长、AFP和GGT是HCC患者发生MVI的独立危险因素。模型中AFP (OR=1.001, 95%置信区间1.001-1.002, P < 0.001)和GGT (OR=1.002, 95%置信区间1.001-1.003, P = 0.033)用于构建预测模型。在两个队列中，有AFP和GGT的模型A比没有的模型B表现出更好的预测性能，AUC分别为0.902(0.872-0.932)和0.876(0.842-0.909)。分析评估模型临床净收益的DCA显示出模型A略好于模型B，都具有良好的临床应用价值。模型在队列中显示出良好的识别能力，预测的概率与实际观测具有较好的一致性。在生存分析中发现， AFP和GGT升高患者的预后明显差于未升高的患者。结论:我们建立了HCC患者发生MVI的预测模型，研究证实了血清AFP和GGT的临床应用价值。
Objective: To establish a risk model for microvascular invasion (MVI) in patients with hepatocellular carcinoma (HCC) based on radiological characteristics and clinical laboratory data, and to explore the clinical application of preoperative alpha-fetoprotein (AFP) and gamma-glutamyl transferase (GGT) in HCC patients. Methods: Clinical data from 479 patients with surgically resected HCC at the First Affiliated Hospital of Nanjing Medical University were retrospectively collected to investigate the effects of potentially relevant factors on MVI and to assess the benefits of serum AFP and GGT on improving model predictive performance. Univariate and multivariate logistic regression analyses were used to select variables for the final prediction model, and the predictive performance of the model was assessed by area under the ROC curve (AUC), calibration curve, and decision curve analysis (DCA). Predictive performance was compared by sensitivity, specificity and accuracy analyses. Kaplan-Meier curves were applied to assess the probability of patient survival. RESULTS: In a multifactorial analysis, tumor size, borders of the tumor, exophytic growth, AFP and GGT were independent predictors for the development of MVI in HCC patients. AFP (OR=1.001, 95% confidence interval 1.001-1.002, P < 0.001) and GGT (OR=1.002, 95% confidence interval 1.001-1.003, P = 0.033) were used in the model to construct the prediction model. Two models were constructed using with AFP, GGT and without, respectively. In both cohorts, model A with AFP and GGT showed better predictive performance than model B without, with AUCs of 0.902 (0.872-0.932) and 0.876 (0.842-0.909), respectively. Two models showed good discrimination, and the predicted probabilities were in good agreement with the observed probabilities. Analysis of the DCA assessing the net clinical benefit of the models showed that model A was slightly better than model B, both with good clinical application. In the subgroup analysis, AFP and GGT could well predict the prognosis of HCC patients. Conclusion: We developed a predictive model for the development of MVI in patients with HCC, and the study confirmed the clinical predictive value of serum AFP and GGT.