Machine learning for individualized prediction of hepatocellular carcinoma development after the eradication of hepatitis C virus with antivirals.

BACKGROUND AND AIMS: Accurate risk stratification for hepatocellular carcinoma (HCC) after achieving a sustained viral response (SVR) is necessary for optimal surveillance. We aimed to develop and validate a machine learning (ML) model to predict the risk of HCC after achieving an SVR in individual patients. METHODS: In this multicenter cohort study, 1742 patients with chronic hepatitis C who achieved an SVR were enrolled. Five ML models were developed including DeepSurv, gradient boosting survival analysis, random survival forest (RSF), survival support vector machine, and a conventional Cox proportional hazard model. Model performance was evaluated using Harrel' c-index and was externally validated in an independent cohort (977 patients). RESULTS: During the mean observation period of 5.4 years, 122 patients developed HCC (83 in the derivation cohort and 39 in the external validation cohort). The RSF model showed the best discrimination ability using seven parameters at the achievement of an SVR with a c-index of 0.839 in the external validation cohort and a high discriminative ability when the patients were categorized into three risk groups (P <0.001). Furthermore, this RSF model enabled the generation of an individualized predictive curve for HCC occurrence for each patient with an app available online. CONCLUSIONS: We developed and externally validated an RSF model with good predictive performance for the risk of HCC after an SVR. The application of this novel model is available on the website. This model could provide the data to consider an effective surveillance method. Further studies are needed to make recommendations for surveillance policies tailored to the medical situation in each country. IMPACT AND IMPLICATIONS: A novel prediction model for HCC occurrence in patients after hepatitis C virus eradication was developed using machine learning algorithms. This model, using seven commonly measured parameters, has been shown to have a good predictive ability for HCC development and could provide a personalized surveillance system.

Steroid administration for ischemic complications after radiofrequency ablation: A retrospective study.

AIM: The aim of this study was to evaluate the effects of steroids on ischemic complications after radiofrequency ablation. METHODS: A total of 58 patients with ischemic complications were divided into two groups according to corticosteroid use or non-use. RESULTS: A total of 13 patients who were administered steroids had a shorter duration of fever than those who were not administered steroids (median 6.0 vs. 2.0 days; p < 0.001). Linear regression analysis showed that steroid administration was associated with a reduction of 3.9 days in the duration of fever (p = 0.008). CONCLUSIONS: Steroid administration for ischemic complications after radiofrequency ablation may reduce the risk of fatal outcomes by blocking systemic inflammatory reactions.

Clinical utility of postablation liver tumor biopsy and possibility of gene mutation analysis.

AIM: Radiofrequency ablation (RFA) is regarded as a first-line treatment for hepatocellular carcinoma (HCC) at an early stage. When treated with RFA, tumor biopsy may not be performed due to the risk of neoplastic seeding. We previously revealed that the risk of neoplastic seeding is significantly reduced by performing biopsies after RFA. In this study, we investigated the possibility of pathological evaluation and gene mutation analysis of post-RFA tumor specimens. METHODS: Radiofrequency ablation was undertaken on diethylnitrosamine-induced mouse liver tumor, and tumor samples with or without RFA were subjected to whole exome sequencing. Post-RFA human liver tumor specimens were used for detection of TERT promoter mutations and pathological assessment. RESULTS: The average somatic mutation rate, sites of mutation, and small indels and base transition patterns were comparable between the nontreated and post-RFA tumors. We identified 684 sites of nonsynonymous somatic substitutions in the nontreated tumor and 704 sites of nonsynonymous somatic substitutions in the post-RFA tumor, with approximately 85% in common. In the human post-RFA samples, the TERT promoter mutations were successfully detected in 40% of the cases. Pathological evaluation was possible with post-RFA specimens, and in one case, the diagnosis of adenocarcinoma was made. CONCLUSION: Our findings suggest that post-RFA liver tumor biopsy is a useful and safe method for obtaining tumor samples that can be used for gene mutation analysis and for pathological assessment.

Hepatocellular carcinoma recurrence after direct-acting antiviral therapy: an individual patient data meta-analysis.

OBJECTIVE: The benefit of direct-acting antivirals (DAAs) against HCV following successful treatment of hepatocellular carcinoma (HCC) remains controversial. This meta-analysis of individual patient data assessed HCC recurrence risk following DAA administration. DESIGN: We pooled the data of 977 consecutive patients from 21 studies of HCV-related cirrhosis and HCC, who achieved complete radiological response after surgical/locoregional treatments and received DAAs (DAA group). Recurrence or death risk was expressed as HCC recurrence or death per 100 person-years (100PY). Propensity score-matched patients from the ITA.LI.CA. cohort (n=328) served as DAA-unexposed controls (no-DAA group). Risk factors for HCC recurrence were identified using random-effects Poisson. RESULTS: Recurrence rate and death risk per 100PY in DAA-treated patients were 20 (95% CI 13.9 to 29.8, I2=74.6%) and 5.7 (2.5 to 15.3, I2=54.3), respectively. Predictive factors for recurrence were alpha-fetoprotein logarithm (relative risk (RR)=1.11, 95% CI 1.03 to 1.19; p=0.01, per 1 log of ng/mL), HCC recurrence history pre-DAA initiation (RR=1.11, 95% CI 1.07 to 1.16; p<0.001), performance status (2 vs 0, RR=4.35, 95% CI 1.54 to 11.11; 2 vs 1, RR=3.7, 95% CI 1.3 to 11.11; p=0.01) and tumour burden pre-HCC treatment (multifocal vs solitary nodule, RR=1.75, 95% CI 1.25 to 2.43; p<0.001). No significant difference was observed in RR between the DAA-exposed and DAA-unexposed groups in propensity score-matched patients (RR=0.64, 95% CI 0.37 to 1.1; p=0.1). CONCLUSION: Effects of DAA exposure on HCC recurrence risk remain inconclusive. Active clinical and radiological follow-up of patients with HCC after HCV eradication with DAA is justified.

Radiofrequency Ablation of Liver Tumors in Patients on Antithrombotic Therapy: A Case-Control Analysis of over 10,000 Treatments.

PURPOSE: To evaluate the safety of radiofrequency ablation (RFA) for liver tumors in patients on antithrombotic therapy. MATERIALS AND METHODS: A total of 10,653 consecutive RFA treatments in 3,485 patients with liver tumors were analyzed. The incidence of complications was analyzed on a treatment basis. The treatments for patients who had received antithrombotic medication up to 1 week prior to RFA comprised the antithrombotic therapy group (n = 806), and the others comprised the control group (n = 9,847). Antithrombotic agents were ceased prior to RFA (aspirin, ticlopidine, clopidogrel, and prasugrel ceased 7 days before RFA; cilostazol, 2 or 3 days before RFA; warfarin, 3 days before RFA; and direct oral anticoagulants, 1 day before RFA) and resumed as soon as possible after RFA. Logistic regression analysis was performed to assess whether the antithrombotic therapy increased the risk of hemorrhagic complications. RESULTS: Hemorrhagic complications were diagnosed after 6 treatments (0.7%) in the antithrombotic group and 48 (0.5%) in the control group, and there was no significant difference between the groups (P = .30). In 3 treatments, hemorrhage was diagnosed on or after 8 days of RFA, all of which were in the antithrombotic group. Thrombotic complications were diagnosed after 2 treatments (0.2%) in the antithrombotic group and after 5 (0.1%) in the control group. In a multivariate analysis, receiving antithrombotic therapy was not an independent risk factor for hemorrhagic complications (adjusted odds ratio, 1.52; 95% confidence interval, 0.60-3.87; P = .38). CONCLUSIONS: RFA of liver tumors in patients on antithrombotic therapy is generally safe with appropriate cessation and resumption. Late-onset hemorrhage should be noted in the patients on antithrombotic therapy.

Impact of direct-acting antivirals on early recurrence of HCV-related HCC: Comparison with interferon-based therapy.

BACKGROUND & AIMS: It remains controversial whether direct-acting antivirals (DAAs) accelerate the recurrence of hepatitis C-related hepatocellular carcinoma (HCC) after curative therapy. This study aimed to evaluate HCC recurrence after DAA treatment of chronic hepatitis C. METHODS: We enrolled patients with a history of successful radiofrequency ablation treatment for hepatitis C-related HCC who received antiviral therapy with DAAs (DAA group: 147 patients) or with interferon (IFN)-based therapy (IFN group: 156 patients). We assessed HCC recurrence rates from the initiation of antiviral therapy using the Kaplan-Meier method and evaluated risk factors for HCC recurrence by multivariate Cox proportional hazard regression analysis. The recurrence pattern was categorized as follows: intrahepatic recurrence with a single tumor <2 cm (stage 0), a single tumor or up to 3 tumors ≤3 cm (stage A), multinodular (stage B), and extrahepatic metastasis or macrovascular invasion (stage C). RESULTS: The recurrence rates at 1 and 2 years were 39% and 61% in the IFN group and 39% and 60% in the DAA group, respectively (p = 0.43). Multivariate analysis identified higher lens culinaris agglutinin-reactive fraction of alpha-fetoprotein level, a history of multiple HCC treatments, and a shorter interval between HCC treatment and initiation of antiviral therapy as independent risk factors for HCC recurrence. HCC recurrence in stage 0, A, B, and C was found in 56 (41%), 60 (44%), 19 (14%), and 1 (0.7%) patients in the IFN group and 35 (44%), 32 (40%), 11 (14%), and 2 (2.5%) patients in the DAA group, respectively (p = 0.70). CONCLUSIONS: HCC recurrence rates and patterns after initiation of antiviral therapy did not differ between patients who received IFN-based therapy and DAA therapy. LAY SUMMARY: We detected no significant difference in early hepatocellular carcinoma (HCC) recurrence rates and patterns between patients who received interferon-based and direct-acting antiviral therapy after HCC treatment. High lens culinaris agglutinin-reactive fraction of alpha-fetoprotein level, short recurrence-free period, and a history of multiple HCC treatments were independent risk factors for early HCC recurrence after the initiation of antiviral therapy.

Sustained virologic response to direct-acting antiviral therapy in patients with chronic hepatitis C and hepatocellular carcinoma: A systematic review and meta-analysis.

BACKGROUND & AIMS: The effect of hepatocellular carcinoma (HCC) on the response to interferon-free direct-acting antiviral (DAA) therapy in patients with chronic hepatitis C (CHC) infection remains unclear. Using a systematic review and meta-analysis approach, we aimed to investigate the effect of DAA therapy on sustained virologic response (SVR) among patients with CHC and either active, inactive or no HCC. METHODS: PubMed, Embase, Web of Science, and the Cochrane Central Register of Controlled Trials were searched from 1/1/2013 to 9/24/2018. The pooled SVR rates were computed using DerSimonian-Laird random-effects models. RESULTS: We included 49 studies from 15 countries, comprised of 3,341 patients with HCC and 35,701 without HCC. Overall, the pooled SVR was lower in patients with HCC than in those without HCC (89.6%, 95% CI 86.8-92.1%, I2 = 79.1% vs. 93.3%, 95% CI 91.9-94.7%, I2 = 95.0%, p = 0.0012), translating to a 4.8% (95% CI 0.2-7.4%) SVR reduction by meta-regression analysis. The largest SVR reduction (18.8%) occurred in patients with active/residual HCC vs. inactive/ablated HCC (SVR 73.1% vs. 92.6%, p = 0.002). Meanwhile, patients with HCC who received a prior liver transplant had higher SVR rates than those who did not (p <0.001). Regarding specific DAA regimens, patients with HCC treated with ledipasvir/sofosbuvir had lower SVR rates than patients without HCC (92.6%, n = 884 vs. 97.8%, n = 13,141, p = 0.026), but heterogeneity was high (I2 = 84.7%, p <0.001). The SVR rate was similar in patients with/without HCC who were treated with ombitasvir/paritaprevir/ritonavir ±â€¯dasabuvir (n = 101) (97.2% vs. 94.8%, p = 0.79), or daclatasvir/asunaprevir (91.7% vs. 89.8%, p = 0.66). CONCLUSION: Overall, SVR rates were lower in patients with HCC, especially with active HCC, compared to those without HCC, though heterogeneity was high. Continued efforts are needed to aggressively screen, diagnose, and treat HCC to ensure higher CHC cure rates. LAY SUMMARY: There are now medications (direct-acting antivirals or "DAAs") that can "cure" hepatitis C virus, but patients with hepatitis C and liver cancer may be less likely to achieve cure than those without liver cancer. However, patients with liver cancer are also more likely to have advanced liver disease and risk factors that can decrease cure rates, so better controlled studies are needed to confirm these findings.

Ischemic complications after percutaneous radiofrequency ablation of liver tumors: Liver volume loss and recovery.

AIM: The liver regrows after acute liver injury and liver resection. However, it is not clear whether the liver regenerates in advanced cirrhosis. This study aimed to evaluate the clinical course of, and liver volume change after, ischemic liver complications caused by radiofrequency ablation (RFA) of hepatocellular carcinoma (HCC). METHODS: We enrolled 35 patients with ischemic complications after RFA. Ischemic complications were defined as rapid elevation of aspartate aminotransferase (AST) to over 500 U/L, with typical radiological findings. Patient characteristics and the ischemic liver volume were investigated. Long-term liver volume changes at 3-8 months after ischemic complications were also assessed in 32 patients. We also assessed the overall survival rate after ischemic complications. RESULTS: The median value of peak AST was 798 U/L (range, 531-4096 U/L). The median ischemic liver volume relative to the functional liver volume before RFA was 13% (range, 3.1-46.5%). There was a strong correlation between the peak AST value and the ischemic liver volume (r = 0.84, P < 0.001). The liver volume recovered to some extent in 18 of 32 (56%) patients after ischemic complications. The survival rate after ischemic complications was 45.7% at 5 years and correlated with the functional liver volume after ischemic complications (P = 0.02). CONCLUSIONS: Ischemic complications after RFA can lead to massive liver parenchymal loss. Although the liver volume recovered to some extent in the majority of our patients, ischemic liver complications after RFA should be avoided to improve the overall survival rate.

Liver stiffness measurements in chronic hepatitis C: Treatment evaluation and risk assessment.

BACKGROUND AND AIM: Liver stiffness (LS), measured by transient elastography, has been validated as a non-invasive surrogate for liver fibrosis. METHODS: We investigated the long-term predictive ability of LS for hepatocellular carcinoma (HCC) development and overall survival in 1146 patients with chronic hepatitis C by using LS value at enrollment. We also investigated chronological changes in LS based on antiviral therapy and its outcome in 752 patients. RESULTS: During the mean follow-up period of 6.6 years, 190 patients developed HCC. Cumulative HCC incidence rates at 5 years were clearly stratified as 1.7% in the ≤ 5 kPa, 3.3% in 5.1-10 kPa, 16.7% in 10.1-15 kPa, 24.4% in 15.1-20 kPa, 36.3% in 20.1-25 kPa, and 43.7% in > 25 kPa subgroups (P < 0.001). Overall survival was also stratified: 10-year survival rates were 99.3% in the ≤ 5 kPa, 95.4% in 5.1-10 kPa, 81.4% in 10.1-15 kPa, 79.5% in 15.1-20 kPa, 66.1% in 20.1-25 kPa, and 49.1% in > 25 kPa subgroups (P < 0.001). LS decreased at a rate of 8.1% per year in those who achieved sustained virological responses, but increased at 0.1% per year in those who could not achieve sustained virological response instead of antiviral therapy, and increased at 3.7% per year in those who did not undergo antiviral therapy. CONCLUSIONS: Liver stiffness measurements can be useful in the prediction of HCC development and overall survival and in the evaluation of chronological changes in liver fibrosis grade during and after antiviral therapy.

Impact of serum ferritin level on hepatocarcinogenesis in chronic hepatitis C patients.

AIM: To elucidate the impact of the serum ferritin level, a surrogate indicator of hepatic iron accumulation, on hepatocarcinogenesis in chronic hepatitis C patients. METHODS: Serum ferritin was measured in 487 chronic hepatitis C patients without history of hepatocellular carcinoma (HCC) after excluding patients in phlebotomy, those with overt chronic gastrointestinal bleeding and those who achieved sustained virological response before enrollment. Patients were divided into four groups (G1-G4) by quartile points of serum ferritin, with sexes separated. RESULTS: The serum ferritin level was positively correlated with total bilirubin, aspartate aminotransferase, alanine aminotransferase (ALT), γ-glutamyltransferase, hemoglobin and AFP, and inversely correlated with prothrombin activity in both sexes. A significant difference in HCC incidence was observed only in male patients; the incidence was higher in G1 (≤80 ng/mL, n = 54) and G4 (≥323 ng/mL, n = 54) compared with that of G2 (81-160 ng/mL, n = 54) and G3 (161-322 ng/mL, n = 52). The spline curve indicating the relationship between the hazard ratio and serum ferritin level took the form of a J-shape for male patients. In multivariate analysis, G1 and G4 showed higher incidence of HCC among men with a hazard ratio of 2.19 (95% confidence interval, 1.02-4.70; P = 0.045) compared with G2 and G3, together with older age, lower serum albumin and ALT above the normal upper limit. CONCLUSION: The serum ferritin level is an independent risk factor for HCC development in male patients with chronic hepatitis C when the level is extremely high or low.

Sarcopenia, intramuscular fat deposition, and visceral adiposity independently predict the outcomes of hepatocellular carcinoma.

BACKGROUND & AIMS: Obesity defined by body mass index (BMI) significantly increases the risk of hepatocellular carcinoma (HCC). In contrast, not only obesity but also underweight is associated with poor prognosis in patients with HCC. Differences in body composition rather than BMI were suggested to be true determinants of prognosis. However, this hypothesis has not been demonstrated conclusively. METHODS: We measured skeletal muscle index (SMI), mean muscle attenuation (MA), visceral adipose tissue index, subcutaneous adipose tissue index, and visceral to subcutaneous adipose tissue area ratios (VSR) via computed tomography in a large-scale retrospective cohort of 1257 patients with different stages of HCC, and comprehensively analyzed the impact of body composition on the prognoses. RESULTS: Among five body composition components, low SMI (called sarcopenia), low MA (called intramuscular fat [IMF] deposition), and high VSR (called visceral adiposity) were significantly associated with mortality, independently of cancer stage or Child-Pugh class. A multivariate analysis revealed that sarcopenia (hazard ratio [HR], 1.52; 95% confidence interval [CI], 1.18-1.96; p=0.001), IMF deposition (HR, 1.34; 95% CI, 1.05-1.71; p=0.020), and visceral adiposity (HR, 1.35; 95% CI, 1.09-1.66; p=0.005) but not BMI were significant predictors of survival. The prevalence of poor prognostic body composition components was significantly higher in underweight and obese patients than in normal weight patients. CONCLUSIONS: Sarcopenia, IMF deposition, and visceral adiposity independently predict mortality in patients with HCC. Body composition rather than BMI is a major determinant of prognosis in patients with HCC.

Slight elevation of high-sensitivity C-reactive protein to predict recurrence and survival in patients with early stage hepatitis C-related hepatocellular carcinoma.

AIM: Hepatocellular carcinoma (HCC) is associated with chronic inflammation derived from various origins. We investigated whether high-sensitivity C-reactive protein (hsCRP) could predict recurrence and survival after curative treatment for early stage hepatitis C virus-related HCC (C-HCC). METHODS: We enrolled 387 patients with three or fewer C-HCC nodules, none of which exceeded 3 cm, and of Child-Pugh class A or B who underwent radiofrequency ablation. We divided the patients into high and low hsCRP groups based on the optimal cut-off value for recurrence using a split-sample method and maximally selected rank statistics. Differences in recurrence and survival rates were evaluated by the Kaplan-Meier method and the log-rank test. Hazard ratios of hsCRP were adjusted with confounding factors using a multiple Cox regression model. We also assessed the correlations between hsCRP levels and clinical parameters. RESULTS: The optimal hsCRP cut-off value was 0.08 mg/dL. The cumulative recurrence rates after 5 years in the high and low hsCRP groups were 90.0% and 82.2%, respectively (P = 0.028), and the corresponding survival rates were 50.9% and 71.8%, respectively (P < 0.001). Higher hsCRP was an independent predictor for recurrence (adjusted hazard ratio [aHR], 1.32; 95% confidence interval [CI], 1.03-1.67; P = 0.026) and survival (aHR, 1.59; 95% CI, 1.14-2.22; P = 0.007). hsCRP was correlated with central obesity as well as tumor burden and liver dysfunction. CONCLUSION: Slight elevation of the hsCRP level, even within the normal range, can predict recurrence and survival after curative treatment among patients with early stage C-HCC.

Comparison of improved prognosis between hepatitis B- and hepatitis C-related hepatocellular carcinoma.

AIM: Treatment strategies for hepatocellular carcinoma (HCC) have been advanced. The aim of this study was to compare the change of the prognosis between hepatitis B-related HCC (B-HCC) and hepatitis C-related HCC (C-HCC) in the last two decades. METHODS: We enrolled 166 B-HCC patients who underwent percutaneous ablation between 1990 and 2009. Patients were divided into three groups according to the treatment time period: 1990-1995 (cohort 1, n = 19), 1996-2002 (cohort 2, n = 49) and 2003-2009 (cohort 3, n = 98). We enrolled 1219 C-HCC patients who underwent percutaneous ablation during the same period (n = 190, 413 and 616, respectively.). Interferon and nucleoside/nucleotide analog use was investigated. Prognosis was evaluated for each cohort using the Kaplan-Meier method and a multivariate Cox proportional hazard regression model. RESULTS: Two (11%), 24 (49%) and 80 (82%) B-HCC patients received nucleoside/nucleotide analogs during the follow-up period in cohorts 1-3, respectively. Among them 1, 18 and 62 patients achieved viral remission, respectively. Thirty-four (18%), 35 (8%) and 84 (14%) C-HCC patients received interferon therapy, respectively. The 5-year B-HCC (P < 0.001) survival rates were 52.6%, 61.1% and 81.6% for cohorts 1-3, respectively. However, the survival rates were 55.6%, 58.8% and 61.1% for C-HCC (P = 0.12), respectively. The B-HCC prognosis improved dramatically (P < 0.001) over time, whereas the prognosis of C-HCC improved moderately (P = 0.01). CONCLUSION: The prognosis of B-HCC has improved dramatically over time, whereas that of C-HCC has improved moderately.

Tumor markers are more useful in patients undergoing surveillance for hepatocellular carcinoma with unreliable results by ultrasonography.

AIM: The objectives of this study was to evaluate the utility of tumor markers in hepatocellular carcinoma (HCC) surveillance based on the reliability of ultrasonography. METHODS: We analyzed 313 patients with HCC detected through a surveillance program using ultrasonography combined with three tumor markers from February 2000 to December 2010. The patients were categorized into two groups based on the triggering event: the US group (n = 281) in which a tumor was first detected using ultrasonography and the TM group (n = 32) in which elevated tumor markers led to the diagnosis of a tumor that was undetected using ultrasonography. The reliability of ultrasonography was scored on a 4-point scale based on three items (coarseness of liver parenchyma, patient obesity and liver atrophy). Additionally, patient survival was assessed using the Kaplan-Meier method and log-rank test. RESULTS: The median tumor size was 20 mm (interquartile range, 15-24). The reliability of ultrasonography was evaluated as good in 208 (66.5%), satisfactory in 80 (8.0%), poor in 21 (6.7%) and unsatisfactory in four (1.2%) patients. The proportion of patients in the TM group increased significantly according to the score, from 7.2% to 25.0% (P = 0.01). The survival rates of patients at 3 and 5 years were 83.7% and 57.2% in the US group, and 79.3% and 59.4% in the TM group, respectively (P = 0.98). CONCLUSION: Tumor markers may play a diagnostic role in patients with unreliable ultrasonography results. The survival of patients diagnosed by elevated tumor markers was not significantly different from those diagnosed by ultrasonography.

Impact of serum levels of interleukin-6 and adiponectin on all-cause, liver-related, and liver-unrelated mortality in chronic hepatitis C patients.

BACKGROUND AND AIM: Various inflammatory cytokines and adipokines have been implicated in hepatitis C virus (HCV)-mediated liver disease, and interleukin-6 (IL-6) and adiponectin may play key roles. In addition, these factors may be associated with chronic hepatitis C (CHC)-induced extrahepatic manifestations. However, little data are available on the role of these factors on future outcomes of CHC patients. This study aims to evaluate the impact of serum levels of IL-6 and adiponectin on all-cause mortality, liver-related mortality, and liver-unrelated mortality. METHODS: A long-term follow-up study was conducted, consisting of 325 CHC patients, for which we previously reported positive associations between these factors (Serum levels of IL-6 and adiponectin) and hepatocellular carcinoma (HCC) development. RESULTS: During the follow-up period (mean, 13.0 year), there were 92 events consisting of 91 deaths (liver related, 72; liver unrelated, 19) and 1 liver transplantation due to liver failure. High IL-6 and adiponectin levels, defined as being higher than each median value at baseline, were associated with significantly higher incidences of not only HCC development but also all-cause mortality. Interestingly, high IL-6 was strongly associated with only liver-related mortality, whereas high-serum adiponectin was associated with not only liver-related, but also liver-unrelated mortality. Multivariate analysis identified high IL-6 as an independent risk factor for liver-related mortality and high adiponectin as an independent risk factor for liver-unrelated mortality. CONCLUSION: High serum levels of IL-6 and adiponectin were associated with higher all-cause and liver-related mortality in CHC patients. In addition, high adiponectin was associated with liver-unrelated mortality. The measurement of these factors may provide information useful for predicting future outcomes in CHC patients.

Spontaneous clearance of serum hepatitis C virus RNA during the clinical course of hepatocellular carcinoma in patients with chronic hepatitis C.

AIM: Spontaneous clearance of serum hepatitis C virus (HCV) RNA in chronic HCV carriers is assumed to be rare especially after development of hepatocellular carcinoma (HCC). We analyzed patients with chronic hepatitis C who spontaneously resolved serum HCV RNA after the treatment for HCC. METHODS: A database search was performed to identify patients with HCC in whom serum HCV RNA was positive before the treatment for HCC and became negative during the clinical course. Those who received interferon therapy were excluded. RESULTS: A total of 1145 patients with HCC who had not received interferon therapy were positive for HCV RNA before the treatment. Among them, five patients (M/F = 4/1) spontaneously resolved viremia during the clinical course, with the incidence rate of at least 0.11%/person-year (95% confidence interval: 0.05%-0.26%). The mean age at the time of negative test for HCV RNA was 77 (range: 52-84). Three and two were infected with HCV genotype 1 and 2, respectively. The mean initial viral load was 9.0 K IU/mL (range: 1.6-31.6). The alanine aminotransferase level decreased to within the normal range in all patients after the clearance of serum HCV RNA. Fibrosis grade of background liver, evaluated according to METAVIR classification, was F1 in 1, F2 in 1, F4 in 2, and unknown in 1. All patients survived more than 7 years after the initial treatment for HCC. CONCLUSION: Spontaneous clearance of serum HCV RNA after HCC development possibly occurs even in elderly patients. The prognosis was good probably due to improved inflammation in the liver.

Development of a transformer model for predicting the prognosis of patients with hepatocellular carcinoma after radiofrequency ablation.

INTRODUCTION: Radiofrequency ablation (RFA) is a widely accepted, minimally invasive treatment modality for patients with hepatocellular carcinoma (HCC). Accurate prognosis prediction is important to identify patients at high risk for cancer progression/recurrence after RFA. Recently, state-of-the-art transformer models showing improved performance over existing deep learning-based models have been developed in several fields. This study was aimed at developing and validating a transformer model to predict the overall survival in HCC patients with treated by RFA. METHODS: We enrolled a total of 1778 treatment-naïve HCC patients treated by RFA as the first-line treatment. We developed a transformer-based machine learning model to predict the overall survival in the HCC patients treated by RFA and compared its predictive performance with that of a deep learning-based model. Model performance was evaluated by determining the Harrel's c-index and validated externally by the split-sample method. RESULTS: The Harrel's c-index of the transformer-based model was 0.69, indicating its better discrimination performance than that of the deep learning model (Harrel's c-index, 0.60) in the external validation cohort. The transformer model showed a high discriminative ability for stratifying the external validation cohort into two or three different risk groups (p < 0.001 for both risk groupings). The model also enabled output of a personalized cumulative recurrence prediction curve for each patient. CONCLUSIONS: We developed a novel transformer model for personalized prediction of the overall survival in HCC patients after RFA treatment. The current model may offer a personalized survival prediction schema for patients with HCC undergoing RFA treatment.