Predictive models and early postoperative recurrence evaluation for hepatocellular carcinoma based on gadoxetic acid-enhanced MR imaging

Background The prognosis of hepatocellular carcinoma (HCC) is still poor largely due to the high incidence of recurrence. We aimed to develop and validate predictive models of early postoperative recurrence for HCC using clinical and gadoxetic acid-enhanced magnetic resonance (MR) imaging-based findings. Methods In this retrospective case-control study, 209 HCC patients, who underwent gadoxetic acid-enhanced MR imaging before curative-intent resection, were enrolled. Boruta algorithm and backward stepwise selection with Akaike information criterion (AIC) were used for variables selection Random forest, Gradient-Boosted decision tree and logistic regression model analysis were used for model development. The area under the receiver operating characteristic curve (AUC), calibration plots, and decision curve analysis were used to evaluate model’s performance. Results One random forest model with Boruta algorithm (RF-Boruta) was developed consisting of preoperative serum ALT and AFP levels and six MRI findings, while preoperative serum AST and AFP levels and four MRI findings were included in one logistic regression model with backward stepwise selection method (Logistic-AIC).The two predictive models demonstrated good discrimination performance in both the training set (RF-Boruta: AUC, 0.820; Logistic-AIC: AUC, 0.853), internal validation set (RF-Boruta: AUC, 0.857, Logistic-AIC: AUC, 0.812) and external validation set(RF-Boruta: AUC, 0.805, Logistic-AIC: AUC, 0.789). Besides, in both the internal validation and external validation sets, the RF-Boruta model outperformed Barcelona Clinic Liver Cancer (BCLC) stage ( p < 0.05). Conclusions The RF-Boruta and Logistic-AIC models with good prediction performance for early postoperative recurrence may lead to optimal and comprehensive treatment approaches, and further improve the prognosis of HCC after resection.