检验医学与临床2025，Vol.22Issue(18)：2481-2487,7.DOI:10.3969/j.issn.1672-9455.2025.18.006
基于术前指标构建肝细胞癌微血管侵犯预测模型
Prediction model for microvascular invasion in hepatocellular carcinoma based on preoperative indicators
摘要
Abstract
Objective To develop a prediction model for microvascular invasion(MVI)in hepatocellular carcinoma(HCC)based on preoperative clinical and laboratory parameters.Methods A retrospective analysis was performed on clinical data from 415 HCC patients who underwent hepatectomy at Peking University Shenzhen Hospital from Janu-ary 2016 to September 2024.Patients were chronologically assigned to the training cohort and validation cohort.The training cohort was further stratified into MVI-positive and MVI-negative subgroups.Clinical parameters were com-pared across all groups.Multivariate Logistic regression analysis identified independent predictors of MVI and estab-lished a prediction model.Model performance was evaluated using receiver operating characteristic(ROC)curve and calibration curve.Results Uric acid(UA)level,proportions of diabetes comorbidity,hepatitis B/C virus(HBV/HCV)infection,and AFP ≥400 μg/L were significantly higher in the MVI-positive group in the training cohort than those in the MVI-negative group,while the lymphocyte-to-monocyte ratio(LMR)was significantly lower than that in the MVI-negative group,and the differences were statistically significant(P＜0.05).HBV/HCV infection,AFP ≥400μg/L,diabetes comorbidity,elevated UA level,and reduced LMR were identified as independent risk factors for MVI in HCC patients(P＜0.05).The prediction model was developed based on multivariate Logistic regression analysis.The area under the ROC curve(AUC)for MVI prediction was 0.883 in the training cohort,with a sensitivity of 89.5％and specificity of 69.2％.In the validation cohort,the AUC was 0.861,with sensitivity of 90.9％and specificity of 71.7％.Conclusion The prediction model developed from routine clinical laboratory parameters demonstrates valuable predictive utility for preoperative MVI in HCC patients,facilitating optimized clinical decision-making.关键词
微血管侵犯/肝细胞癌/预测模型/危险因素/甲胎蛋白Key words
microvascular invasion/hepatocellular carcinoma/prediction model/risk factor/alpha-fetopro-tein分类
医药卫生引用本文复制引用
林雨,冯敏旋,夏勇,熊丹..基于术前指标构建肝细胞癌微血管侵犯预测模型[J].检验医学与临床,2025,22(18):2481-2487,7.基金项目
广东省深圳市科技创新委员会课题(JCYJ20220531093816038). （JCYJ20220531093816038）
