Tumor burden score and alpha-fetoprotein level predict prognosis of patients with unresectable hepatocellular carcinoma treated with tyrosine kinase inhibitor and anti-PD-1 antibody

Background:Tyrosine kinase inhibitors(TKIs)and anti-PD-1 antibodies in combination provide survival benefits for patients with unresectable hepatocellular carcinoma(uHCC).However,the tool used to determine which patients likely benefit most from this treatment strategy has not been reported.We sought to develop a prognostic scoring system based on tumor burden score(TBS)and alpha-fetoprotein(AFP)to predict the long-term prognosis of uHCC treated with TKIs and anti-PD-1 antibodies.Methods:Data on patients with uHCC treated with TKIs and anti-PD-1 antibodies from multiple centers were collected.The prognostic accuracy of TBS,AFP,Barcelona Clinic Liver Cancer(BCLC),and CTA(Combined TBS and AFP)for 2-year progression-free survival(PFS)and overall survival(OS)was evaluated.Results:Overall,278 patients with uHCC treated with TKIs and anti-PD-1 antibodies were enrolled,including 48 BCLC-B and 230 BCLC-C HCC patients.CTA(AUC?0.721 and 0.683)outperformed TBS(AUC?0.680 and 0.621),AFP(AUC?0.606 and 0.594),and BCLC staging(AUC?0.551 and 0.555)in predicting PFS and OS.The 2-year PFS and OS for low CTA(low TBS/low AFP)were 65.7%and 94.4%,respectively,which were significantly higher than 21.6%and 44.9%(p<0.001 and p?0.002),respectively,for intermediate CTA(low TBS/high AFP or high TBS/low AFP)and 8.7%and 12.1%(both p<0.001),respectively,for high CTA(high TBS/high AFP).Multivariable Cox regression analysis indicated that CTA grading was an independent prognostic factor for PFS and OS(referent:low CTA;intermediate CTA,HR 2.87 and 7.17;high CTA,HR 5.52 and 10.31,respectively).Conclusions:CTA grading is an accurate tool for stratifying the prognosis of uHCC treated with TKIs and anti-PD-1 antibodies and may help determine which patients may benefit more from this treatment strategy.

Development of a machine learning model to predict early recurrence for hepatocellular carcinoma after curative resection

Background:Early recurrence is common for hepatocellular carcinoma(HCC)after surgical resection,being the leading cause of death.Traditionally,the COX proportional hazard(CPH)models based on linearity assumption have been used to predict early recurrence,but predictive performance is limited.Machine learning models offer a novel methodology and have several advantages over CPH models.Hence,the purpose of this study was to compare random survival forests(RSF)model with CPH models in prediction of early recurrence for HCC patients after curative resection.Methods:A total of 4,758 patients undergoing curative resection from two medical centers were included.Fifteen features including age,gender,etiology,platelet count,albumin,total bilirubin,AFP,tumor size,tumor number,microvascular invasion,macrovascular invasion,Edmondson-Steiner grade,tumor capsular,satellite nodules and liver cirrhosis were used to construct the RSF model in training cohort.Discrimination,calibration,clinical usefulness and overall performance were assessed and compared with other models.Results:Five hundred survival trees were used to generate the RFS model.The five highest Variable Importance(VIMP)were tumor size,macrovascular invasion,microvascular invasion,tumor number and AFP.In training,internal and external validation cohort,the C-index of RSF model were 0.725[standard errors(SE)=0.005],0.762(SE=0.011)and 0.747(SE=0.016),respectively;the Gönen&Heller’s K of RSF model were 0.684(SE=0.005),0.711(SE=0.008)and 0.697(SE=0.014),respectively;the time-dependent AUC(2 years)of RSF model were 0.818(SE=0.008),0.823(SE=0.014)and 0.785(SE=0.025),respectively.The RSF model outperformed early recurrence after surgery for liver tumor(ERASL)model,Korean model,American Joint Committee on Cancer tumor-node-metastasis(AJCC TNM)stage,Barcelona Clinic Liver Cancer(BCLC)stage and Chinese stage.The RSF model is capable of stratifying patients into three different risk groups(low-risk,intermediate-risk,high-risk groups)in the training and two validation cohorts(all P<0.0001).A web-based prediction tool was built to facilitate clinical application(https://recurrenceprediction.shinyapps.io/surgery_predict/).Conclusions:The RSF model is a reliable tool to predict early recurrence for patients with HCC after curative resection because it exhibited superior performance compared with other models.This novel model will be helpful to guide postoperative follow-up and adjuvant therapy.

Impact of pathological response after preoperative transcatheter arterial chemoembolization(TACE)on incidences of microvascular invasion and early tumor recurrence in hepatocellular carcinoma:a multicenter propensity score matching analysis

Background:To study the influence of pathological responses(PR)after transcatheter arterial chemoembolization(TACE)on incidences of microvascular invasion(MVI)and early recurrence in hepatocellular carcinoma(HCC)patients.Methods:Between 2013 to 2015,consecutive HCC patients who underwent liver resection with“curative”intent at three hospitals were enrolled in this study.Patients with different areas of PR after preoperative TACE were compared with those without preoperative TACE on the incidences of MVI,early recurrence rates and patterns of recurrence before and after propensity score matching(PSM).Results:Of 1,970 patients,737 patients who received preoperative TACE were divided into three groups according to the areas of PR:≥90%(n=226),60-90%(n=447),and<60%(n=64).PR≥90%was an independent protective factor of incidences of MVI[odds ratio(OR),0.144;95%confidence interval(CI),0.082-0.245,P<0.001)and early recurrence(HR,0.742;95%CI,0.561-0.963,P=0.032);while PR<60%was an independent risk factor of incidences of MVI(OR,6.076;95%CI,3.004-11.728,P<0.001)and early recurrence(HR,1.428;95%CI,1.095-1.929;P=0.009).Furthermore,patients with PR<60%were significantly more likely to develop multiple intrahepatic recurrences involving multiple hepatic segments when compared with patients without preoperative TACE.Conclusions:This study indicated the area of PR after TACE was closely associated with the incidences of MVI and early tumor recurrence.Patients with PR<60%were at significantly higher risks of having more MVI,early and multiple tumor recurrences.