【摘要】 目的构建并验证基于术前炎症生物标志物的预测模型，评估其对不可切除肝癌患者行TACE治疗的预后预测能力。方法 回顾性收集2007年1月至2020年12月在六家医疗机构接受TACE作为初始治疗的544例患者，并拆分为训练集和验证集。使用LASSO算法和Cox回归筛选独立影响因素并建模。从区分度、校准度和临床适用性对模型进行验证，绘制Kaplan-Meier风险分层曲线确定组间预后差异，计算模型的似然比卡方值、R2值、AIC值、C指数以及AUROC值评估模型的准确性和效能。结果 训练集和验证集分别为376例和168例。多因素分析显示BCLC分级、肿瘤大小、肿瘤数量、中性粒细胞和预后营养指数（prognostic nutritional index,PNI）是患者术后总生存期（OS）的独立影响因素（P<0.05）;BCLC分级、肿瘤大小、肿瘤数量、NLR、PNI和PS评分是患者无进展生存期（PFS）的独立影响因素（P<0.05）。OS和PFS模型的C指数分别为0.735(95%CI:0.708～0.762)和0.736(95%CI:0.711～0.761)，外部验证为0.721(95%CI:0.680～0.762)和0.693(95%CI:0.656～0.730)。列线图的时间依赖性C指数、时间依赖性ROC曲线和时间依赖性AUC曲线均显示出理想的区分能力。校准曲线与理想标准线明显重合，表明模型稳定性高，过拟合程度低。决策曲线分析揭示了更大范围的阈值概率，可以增加净收益。KaplanMeier曲线显示不同风险组患者的预后差异显著（P<0.000 1）。模型的似然比卡方值、R2值、AIC值、C指数以及AUROC值均优于目前临床常用的其他模型。结论 基于术前炎症标志物所构建的列线图在预测TACE预后方面表现出优秀的准确性和出色的预测效率，可以作为指导个体化治疗和预测预后的有效工具。更多还原

【Abstract】 Objective To construct and validate a predictive model based on preoperative inflammatory biomarkers, and to evaluate its ability in predicting the prognosis of patients with unresectable hepatocellular carcinoma(HCC) after receiving transcatheter arterial chemoembolization(TACE). Methods A total of 544 patients with HCC, who received TACE as the initial treatment at six medical institutions between January 2007 and December 2020, were retrospectively collected. The patients were divided into training cohort(n=376) and validation cohort(n=168). LASSO algorithm and Cox regression analysis were used to screen out the independent influencing factors and to make modelling. The model was validated based on the discrimination, calibration and clinical applicability, and the Kaplan-Meier risk stratification curves were plotted to determine the prognostic differences between groups. The likelihood ratio chi-square value, R2value,akaike information criterion(AIC) value, C-index and AUROC value of the model were calculated to determine its accuracy and efficiency. Results The training cohort and validation cohort had 376 participants and 168participants respectively. Multivariate analysis indicated that BCLC, tumor size, number of tumor lesions,neutrophil and prognostic nutritional index(PNI) were the independent influencing factors for postoperative overall survival(OS), with all P being<0.05; the BCLC grade, tumor size, number of tumor lesions, NLR, PNI and PS score were the independent influencing factors for progression-free survival(PFS), with all P being<0.05.The C-indexes of the OS and PFS models were 0.735(95%CI=0.708-0.762) and 0.736(95%CI=0.711-0.761)respectively, and the external validation was 0.721(95%CI=0.680-0.762) and 0.693(95%CI=0.656-0.730)respectively. Ideal discrimination ability of the nomogram was exhibited in time-dependent C-index, time-dependent ROC, and time-dependent AUC. The calibration curves significantly coincided with the ideal standard lines, indicating that the model had high stability and low over-fitting level. Decision curve analysis revealed that there was a wider range of threshold probabilities and it could augment net benefits. The KaplanMeier curves for risk stratification indicated that the prognosis of patients varied dramatically between risk categories(P<0.000 1). The Kaplan-Meier curves for risk stratification indicated that the prognosis of patients varied dramatically among different risk groups(P<0.000 1). The likelihood ratio chi-square value, R2value,AIC value, C-index and AUROC value of the model were better than those of other models commonly used in clinical practice. Conclusion The newly-developed prognostic nomogram based on preoperative inflammatory indicators has excellent accuracy as well as excellent prediction effect in predicting the prognosis of patients with unresectable HCC after receiving TACE, therefore, it can be used as an effective tool for guiding individualized treatment and for predicting prognosis.(J Intervent Radiol, 2024, 33: 245-258)更多还原