Comparison of patients with hepatitis B virus-associated hepatocellular carcinoma:Data from two hospitals from Turkey and China

Aims:There are many studies on the incidence of hepatitis B virus(HBV)-associated hepatocellular carcinoma(HCC),but very little is known about the HCC features in different populations.The study aimed to compare characteristics in two cohorts of patients with HBV-associated hepatocellular carcinoma from Turkey and China.Methods:Data on patients with HBV-associated HCC diagnosed by imaging or liver biopsy were retrospectively collected from Shandong Provincial Hospital(n=578)and Inonu University Hospital(n=359)between January 2002 and December 2020,and the liver function and HCC characteristics were compared.Continuous variables were compared using Student's t-test or Mann-Whitney U test and categorical variables were compared using the χ^(2) test or Fisher's exact test.Results:The patients in the Turkish cohort had significantly worse Child-Pugh scores(Child-Pugh A:38.3%vs.87.9%;Child-Pugh B:40.3%vs.11.1%;Child-Pugh C:21.4%vs.1.0%;p<0.001)and significantly higher levels of aspartate aminotransferase(66.5[38.0−126.0]vs.36.0[27.0-50.0]IU/L;p<0.001),alanine aminotransferase(47.5[30.0−87.3]vs.33.0[24.0−45.0]IU/L;p<0.001),total bilirubin(20.8[13.7−39.3]vs.17.9[13.8−24.0]mg/dL;p<0.001),and lower albumin levels(32.0[26.0-39.0]vs.40.0[36.1-43.8]g/L;p<0.001)than patients in Chinese cohort.The tumor characteristics showed the Barcelona Clinic Liver Cancer(BCLC)score(BCLC 1:5.1%vs.71.8%;BCLC 2:48.7%vs.24.4%;BCLC 3:24.4%vs.3.8%;BCLC 4:21.8%vs.0;all p<0.001),maximum tumor diameter(5.0[3.0-9.0]vs.3.5[2.5−6.0]cm;p<0.001),alpha-fetoprotein values(27.7 vs.13.2 ng/mL;p<0.001),and percentage of patients with portal vein tumor thrombus(33%vs.6.1%;p<0.001)were all significantly worse in the Turkish cohort compared with Chinese cohort.Conclusions:HBV-associated HCC from the Turkish cohort had worse liver function and more aggressive clinical characteristics than patients from the Chinese cohort.

A K-nearest Neighbor Model to Predict Early Recurrence of Hepatocellular Carcinoma After Resection

Background and Aims:Patients with hepatocellular carci-noma(HCC)surgically resected are at risk of recurrence;however,the risk factors of recurrence remain poorly un-derstood.This study intended to establish a novel machine learning model based on clinical data for predicting early re-currence of HCC after resection.Methods:A total of 220 HCC patients who underwent resection were enrolled.Clas-sification machine learning models were developed to predict HCC recurrence.The standard deviation,recall,and preci-sion of the model were used to assess the model’s accura-cy and identify efficiency of the model.Results:Recurrent HCC developed in 89(40.45%)patients at a median time of 14 months from primary resection.In principal compo-nent analysis,tumor size,tumor grade differentiation,por-tal vein tumor thrombus,alpha-fetoprotein,protein induced by vitamin K absence or antagonist-II(PIVKA-II),aspartate aminotransferase,platelet count,white blood cell count,and HBsAg were positive prognostic factors of HCC recurrence and were included in the preoperative model.After compar-ing different machine learning methods,including logistic re-gression,decision tree,naïve Bayes,deep neural networks,and k-nearest neighbor(K-NN),we choose the K-NN model as the optimal prediction model.The accuracy,recall,preci-sion of the K-NN model were 70.6%,51.9%,70.1%,respec-tively.The standard deviation was 0.020.Conclusions:The K-NN classification algorithm model performed better than the other classification models.Estimation of the recurrence rate of early HCC can help to allocate treatment,eventually achieving safe oncological outcomes.