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.

Predicting Infiltrative Hepatocellular Carcinoma Patient Outcome Post-TACE:MR Bias Field Correction Effect on 3D-quantitative Image Analysis

Background and Aims:To investigate the impact of MR bias field correction on response determination and survival prediction using volumetric tumor enhancement analysis in patients with infiltrative hepatocellular carcinoma,after transcatheter arterial chemoembolization(TACE).Methods:This study included 101 patients treated with conventional or drug-eluting beads TACE between the years of 2001 and 2013.Semi-automated 3D quantification software was used to segment and calculate the enhancing tumor volume(ETV)of the liver with and without bias-field correction on multi-phasic contrast-enhanced MRI before and 1-month after initial TACE.ETV(expressed as cm3)at baseline imaging and the relative change in ETV(as%change,ETV%)before and after TACE were used to predict response and survival,respectively.Statistical survival analyses included Kaplan-Meier curve generation and Cox proportional hazards modeling.Q statistics were calculated and used to identify the best cut-off value for ETV to separate responders and non-responders(ETV cm3).The difference in survival was evaluated between responders and non-responders using Kaplan-Meier and Cox models.Results:MR bias field correction correlated with improved response calculation from baseline MR as well as survival after TACE;using a 415 cm3 cut-off for ETV at baseline(hazard ratio:2.00,95%confidence interval:1.23-3.26,p=0.01)resulted in significantly improved response prediction(median survival in patients with baseline ETV<415 cm3:19.66 months vs.≥415 cm3:9.21 months,p<0.001,log-rank test).A≥41%relative decrease in ETV(hazard ratio:0.58,95%confidence interval:0.37-0.93,p=0.02)was significant in predicting survival(ETV≥41%:19.20 months vs.ETV<41%:8.71 months,p=0.008,log-rank test).Without MR bias field correction,response from baseline ETV could be predicted but survival after TACE could not.Conclusions:MR bias field correction improves both response assessment and accuracy of survival prediction using whole liver tumor enhancement analysis from baseline MR after initial TACE in patients with infiltrative hepatocellular carcinoma.

Diagnostic utility of N-terminal-proBNP in differentiating acute pulmonary embolism from heart failure in patients with acute dyspnea Diagnostic utility of N-terminal-proBNP in differentiating acute pulmonary embolism from heart failure in patients with acute dyspnea Diagnostic utility of N-terminal-proBNP in differentiating acute pulmonary embolism from heart failure in patients with acute dyspnea

Background The plasma N-terminal pro-B-type natriuretic peptide （NT-proBNP） level is frequently elevated in dyspnoeic patients and increasingly used in emergency departments to assess the cause of acute dyspnea.In this study we prospectively tested NT-proBNP levels in patients with congestive heart failure （CHF） and/or acute pulmonary embolism （APE） and determined the utility of NT-proBNP for discriminating APE from CHF.Methods A cohort of 177 dyspnoeic patients with a diagnosis of APE and/or CHF was prospectively studied between June 2010 and March 2013.NT-proBNP was measured by the electrochemiluminescence immunoassay （ECLIA）.All patients were evaluated with transthoracic echocardiography （TTE）.APE was diagnosed in the presence of thrombi signs in the pulmonary arteries with computed tomographic pulmonary angiography （CTPA） or a high-probability lung ventilation/ perfusion scan.Risk stratification was based on the evaluation on admission according to the ESC guidelines from 2008.The diagnosis of CHF was based on the guidelines of the American College of Cardiology/American Heart Association and the European Society of Cardiology.Two physicians independently reviewed the records to determine the final diagnosis.Results Fifty-nine patients met the criteria for dyspnea caused by APE,and 113 patients were diagnosed with CHF.Most of the APE patients （41,69.5%） were intermediate-risk.The symptoms and signs,such as orthopnea,paroxysmal nocturnal dyspnea and rales in the lungs,were more common in patients with CHF than in patients with APE （P 〈0.01）.Median NT-proBNP was significantly lower in patients with APE compared to those in patients with CHF （2 855.9 pg/ml vs.6 911.4 pg/ml,P 〈0.01）.We constructed the receiver operating characteristics （ROC） curve in predicting the diagnosis of APE.At a cut point=1 582.750 pg/ml,NT-proBNP provided a specificity of 93% and a true positive rate （sensitivity） of 17% for the diagnosis.At a cut point=3 390.000 pg/ml,NT-proBNP had a specificity of 83% and a sensitivity of 84% for the diagnosis of APE.At a cut point=6 486.500 pg/ml,they were 54% and 93% respectively.Conclusions NT-proBNP can assist in excluding CHF patients from those admitted to the emergency department with acute dyspnea and identifying patients with a high probability of APE,which would reduce the missed diagnosis of APE.Larger studies are necessary to validate these findings.