The best predictive model for hepatocellular carcinoma in patients with chronic hepatitis B infection

EASL Clinical Practice Guidelines on the management of hepatitis B virus infection

The updated EASL Clinical Practice Guidelines on the management of hepatitis B virus (HBV) infection provide comprehensive, evidence-based recommendations for its management. Spanning ten thematic sections, the guidelines address diagnostics, treatment goals, treatment indications, therapeutic options, hepatocellular carcinoma surveillance, management of special populations, HBV reactivation prophylaxis, post-transplant care, HBV prevention strategies, and finally address open questions and future research directions. Chronic HBV remains a global health challenge, with over 250 million individuals affected and significant mortality due to cirrhosis and hepatocellular carcinoma. These guidelines emphasise the importance of early diagnosis, risk stratification based on viral and host factors, and tailored antiviral therapy. Attention is given to simplified algorithms, vaccination, and screening to support global HBV elimination targets. The guidelines also discuss emerging biomarkers and evolving definitions of functional and partial cure. Developed through literature review, expert consensus, and a Delphi process, the guidelines aim to equip healthcare providers across disciplines with practical tools to optimise HBV care and outcomes worldwide.

Machine Learning-Based Model Used for Predicting the Risk of Hepatocellular Carcinoma in Patients with Chronic Hepatitis B

Object

Currently, predictive models that effectively stratify the risk levels for hepatocellular carcinoma (HCC) are insufficient. Our study aimed to assess the 10-year cumulative risk of HCC among patients suffering from chronic hepatitis B (CHB) by employing an artificial neural network (ANN).

Methods

This research involved 1717 patients admitted to Beijing Ditan Hospital of Capital Medical University and the People's Liberation Army Fifth Medical Center. The training group included 1309 individuals from Beijing Ditan Hospital of Capital Medical University, whereas the validation group contained 408 individuals from the People's Liberation Army Fifth Medical Center. By performing a univariate analysis, we pinpointed factors that had an independent impact on the development of HCC, which were subsequently employed to create the ANN model. To evaluate the ANN model, we analyzed its predictive accuracy, discriminative performance, and clinical net benefit through measures including the area under the receiver operating characteristic curve (AUC), concordance index (C-index), and calibration curves.

Results

The cumulative incidence rates of HCC over a decade were observed to be 3.59% in the training cohort and 4.41% in the validation cohort. We incorporated nine distinct independent risk factors into the ANN model's development. Notably, in the training group, the area under the receiver operating characteristic (AUROC) curve for the ANN model was reported as 0.929 (95% CI 0.910-0.948), and the C-index was 0.917 (95% CI 0.907-0.927). These results were significantly superior to those of the mREACHE-B(0.700, 95% CI 0.639-0.761), mPAGE-B(0.800, 95% CI 0.757-0.844), HCC-RESCUE(0.787, 95% CI 0.732-0.837), CAMD(0.760, 95% CI 0.708-0.812), REAL-B(0.767, 95% CI 0.719-0.816), and PAGE-B(0.760, 95% CI 0.712-0.808) models (p < 0.001). The ANN model proficiently categorized patients into low-risk and high-risk groups based on their 10-year projections. In the training cohort, the positive predictive value (PPV) for the incidence of liver cancer in low-risk individuals was 92.5% (95% CI 0.921-0.939), whereas the negative predictive value (NPV) stood at 88.2% (95% CI 0.870-0.894). Among high-risk patients, the PPV reached 94.6% (95% CI 0.936-0.956) and the NPV was 90.2% (95% CI 0.897-0.917). These results were also confirmed in the independent validation cohort.

Conclusion

The model utilizing artificial neural networks demonstrates strong performance in personalized predictions and could assist in assessing the likelihood of a 10-year risk of HCC in patients suffering from CHB.

The insight to history and trends of transient elastography for assessing liver fibrosis-a bibliometric analysis

Background

Transient elastography (TE) has become a prominent technique for the detection of fibrosis, owing to its non-invasive nature, rapid execution, safety, and ease of repetition. This study aims to conduct a bibliometric analysis of the historical development and trends in the application of TE for the assessment of liver fibrosis.

Methods

In the Web of Science (Core Collection database), we selected the Science Citation Index Expanded database to search for relevant literature from 1 January 1983 to 20 November 2023. We performed a search using the following topic words: transient elastography, liver fibrosis. After screening according to the title, abstract and keyword and removing the repetition, the literature included in the study was finally determined, and full records were downloaded. Bibliometric analysis was performed using VOSviewer and CiteSpace.

Results

Through the bibliometric visualization analysis of 577 articles, it was found that since TE was first reported for the measurement of liver fibrosis in 2003, the number of publications in this field has generally shown an upward trend, and the distribution of publications has shown a bimodal distribution, with peaks in 2010 and 2019. France and China have shown a high contribution in this field with a high number of publications. In terms of contributions from individual research centers, Yonsei University stands out prominently. Throughout the history of research in this field, early studies focused on chronic viral hepatitis, by comparing TE and Fibrosis-4, aspartate aminotransferase to platelet ratio index, FibroTest, liver biopsy and other liver fibrosis detection indicators to verify its diagnostic efficacy. Subsequently, the focus of research gradually shifted to non-alcoholic fatty liver disease and other liver diseases, and the scope of research extended to the establishment of prediction models and efficacy evaluation through TE.

Conclusions

The application scope of TE is gradually expanding, and its safety, simplicity, rapidity, high accuracy, quantitative results, repeatability and good tolerance make it popular in clinical practice. Nowadays, the application of TE is not limited to the diagnosis of liver fibrosis, but has been extended to the establishment of prognostic models and efficacy evaluation of various liver diseases. To explore the deeper value of TE through new research methods such as machine learning models, radiate the advantages of TE to more liver diseases, and combine TE with a variety of non-invasive detection indicators to improve its application value, may be the future development and application prospect of TE in the field of liver fibrosis.

Development and validation of an interpretable machine learning model for predicting the risk of hepatocellular carcinoma in patients with chronic hepatitis B: a case-control study

BACKGROUND

The aim of this study was to develop and internally validate an interpretable machine learning (ML) model for predicting the risk of hepatocellular carcinoma (HCC) in patients with chronic hepatitis B (CHB) infection.

METHODS

We retrospectively collected clinical data from patients with HCC and CHB treated at the Fourth Affiliated Hospital of Guangxi Medical University from January 2022 to December 2022, including demographics, comorbidities, and laboratory parameters. The datasets were randomly divided into a training set (361 cases) and a validation set (155 cases) in a 7:3 ratio. Variables were screened using Least Absolute Shrinkage and Selection Operator (LASSO) and multifactor logistic regression. The prediction model of HCC risk in CHB patients was constructed based on five machine learning models, including logistic regression (LR), K-nearest neighbour (KNN), support vector machine (SVM), random forest (RF) and artificial neural network (ANN). Receiver operating characteristic (ROC) curve, calibration curve and decision curve analysis (DCA) were used to evaluate the predictive performance of the model in terms of identification, calibration and clinical application. The SHapley Additive exPlanation (SHAP) method was used to rank the importance of the features and explain the final model.

RESULTS

Among the five ML models constructed, the RF model has the best performance, and the RF model predicts the risk of HCC in patients with CHB in the training set [AUC: 0.996, 95% confidence interval (CI) (0.991-0.999)] and internal validation set [AUC: 0.993, 95% CI (0.986-1.000)]. It has high AUC, specificity, sensitivity, F1 score and low Brier score. Calibration showed good agreement between observed and predicted risks. The model yielded higher positive net benefits in DCA than when all participants were considered to be at high or low risk, indicating good clinical utility. In addition, the SHAP plot of the RF showed that age, basophil/lymphocyte ratio (BLR), D-Dimer, aspartate aminotransferase/alanine aminotransferase (AST/ALT), γ-glutamyltransferase (GGT) and alpha-fetoprotein (AFP) can help identify patients with CHB who are at high or low risk of developing HCC.

CONCLUSION

ML models can be used as a tool to predict the risk of HCC in patients with CHB. The RF model has the best predictive performance and helps clinicians to identify high-risk patients and intervene early to reduce or delay the occurrence of HCC. However, the model needs to be further improved through large sample studies.

Baseline Viral Load and On-Treatment Hepatocellular Carcinoma Risk in Chronic Hepatitis B: A Multinational Cohort Study

BACKGROUND & AIMS

Hepatocellular carcinoma (HCC) risk persists in patients with chronic hepatitis B (CHB) despite antiviral therapy. The relationship between pre-treatment baseline hepatitis B virus (HBV) viral load and HCC risk during antiviral treatment remains uncertain.

METHODS

This multinational cohort study aimed to investigate the association between baseline HBV viral load and on-treatment HCC risk in 20,826 noncirrhotic, hepatitis B e antigen (HBeAg)-positive and HBeAg-negative patients with baseline HBV DNA levels ≥2000 IU/mL (3.30 log10 IU/mL) who initiated entecavir or tenofovir treatment. The primary outcome was on-treatment HCC incidence, stratified by baseline HBV viral load as a categorical variable.

RESULTS

In total, 663 patients developed HCC over a median follow-up of 4.1 years, with an incidence rate of 0.81 per 100 person-years (95% confidence interval [CI], 0.75-0.87). Baseline HBV viral load was significantly associated with HCC risk in a non-linear parabolic pattern, independent of other factors. Patients with baseline viral load between 6.00 and 7.00 log10 IU/mL had the highest on-treatment HCC risk (adjusted hazard ratio, 4.28; 95% CI, 2.15-8.52; P < .0001) compared with those with baseline viral load ≥8.00 log10 IU/mL, who exhibited the lowest HCC risk.

CONCLUSION

Baseline viral load showed a significant, non-linear, parabolic association with HCC risk during antiviral treatment in noncirrhotic patients with CHB. Early initiation of antiviral treatment based on HBV viral load may help prevent irreversible HCC risk accumulation in patients with CHB.

AI in Hepatology: Revolutionizing the Diagnosis and Management of Liver Disease

The integration of artificial intelligence (AI) into hepatology is revolutionizing the diagnosis and management of liver diseases amidst a rising global burden of conditions like metabolic-associated steatotic liver disease (MASLD). AI harnesses vast datasets and complex algorithms to enhance clinical decision making and patient outcomes. AI's applications in hepatology span a variety of conditions, including autoimmune hepatitis, primary biliary cholangitis, primary sclerosing cholangitis, MASLD, hepatitis B, and hepatocellular carcinoma. It enables early detection, predicts disease progression, and supports more precise treatment strategies. Despite its transformative potential, challenges remain, including data integration, algorithm transparency, and computational demands. This review examines the current state of AI in hepatology, exploring its applications, limitations, and the opportunities it presents to enhance liver health and care delivery.

Viral Load-Based Prediction of Hepatocellular Carcinoma Risk in Noncirrhotic Patients With Chronic Hepatitis B : A Multinational Study for the Development and External Validation of a New Prognostic Model

BACKGROUND

A nonlinear association between serum hepatitis B virus (HBV) DNA levels and hepatocellular carcinoma (HCC) risk has been suggested in patients with chronic hepatitis B (CHB).

OBJECTIVE

To develop and externally validate a prognostic model for HCC risk in noncirrhotic adult patients with CHB and no notable alanine aminotransferase (ALT) elevation.

DESIGN

Multinational cohort study.

SETTING

A community-based cohort in Taiwan (REVEAL-HBV [Risk Evaluation of Viral Load Elevation and Associated Liver Disease/Cancer-Hepatitis B Virus]; REACH-B [Risk Estimation for HCC in CHB] model cohort) and 8 hospital-based cohorts from Korea and Hong Kong (GAG-HCC [Guide with Age, Gender, HBV DNA-HCC] and CU-HCC [Chinese University-HCC] cohorts).

PARTICIPANTS

Model development: 6949 patients with CHB from a Korean hospital-based cohort. External validation: 7429 patients with CHB combined from the Taiwanese cohort and 7 cohorts from Korea and Hong Kong.

MEASUREMENTS

Incidence of HCC.

RESULTS

Over median follow-up periods of 10.0 and 12.2 years, the derivation and validation cohorts identified 435 and 467 incident HCC cases, respectively. Baseline HBV DNA level was one of the strongest predictors of HCC development, demonstrating a nonlinear parabolic association in both cohorts, with moderate viral loads (around 6 log10 IU/mL) showing the highest HCC risk. Additional predictors included in the new model (Revised REACH-B) were age, sex, platelet count, ALT levels, and positive hepatitis B e antigen result. The model exhibited satisfactory discrimination and calibration, with c-statistics of 0.844 and 0.813 in the derivation and validation cohorts with multiple imputation, respectively. The model yielded a greater positive net benefit compared with other strategies in the 0% to 18% threshold.

LIMITATION

Validation in cohorts of other races and receiving antiviral treatment was lacking.

CONCLUSION

Our new prognostic model, based on the nonlinear association between HBV viral loads and HCC risk, provides a valuable tool for predicting and stratifying HCC risk in noncirrhotic patients with CHB who are not currently indicated for antiviral treatment.

PRIMARY FUNDING SOURCE

Korean government.

Risk predictive model for the development of hepatocellular carcinoma before initiating long-term antiviral therapy in patients with chronic hepatitis B virus infection

It is generally acknowledged that antiviral therapy can reduce the incidence of hepatitis B virus (HBV)-related hepatocellular carcinoma (HCC), there remains a subset of patients with chronic HBV infection who develop HCC despite receiving antiviral treatment. This study aimed to develop a model capable of predicting the long-term occurrence of HCC in patients with chronic HBV infection before initiating antiviral therapy. A total of 1450 patients with chronic HBV infection, who received initial antiviral therapy between April 2006 and March 2023 and completed long-term follow-ups, were nonselectively enrolled in this study. Least absolute shrinkage and selection operator (LASSO) and Cox regression analysis was used to construct the model. The results were validated in an external cohort (n = 210) and compared with existing models. The median follow-up time for all patients was 60 months, with a maximum follow-up time of 144 months, during which, 32 cases of HCC occurred. The nomogram model for predicting HCC based on GGT, AFP, cirrhosis, gender, age, and hepatitis B e antibody (TARGET-HCC) was constructed, demonstrating a good predictive performance. In the derivation cohort, the C-index was 0.906 (95% CI = 0.869-0.944), and in the validation cohort, it was 0.780 (95% CI = 0.673-0.886). Compared with existing models, TARGET-HCC showed promising predictive performance. Additionally, the time-dependent feature importance curve indicated that gender consistently remained the most stable predictor for HCC throughout the initial decade of antiviral therapy. This simple predictive model based on noninvasive clinical features can assist clinicians in identifying high-risk patients with chronic HBV infection for HCC before the initiation of antiviral therapy.

Similar recurrence after curative treatment of HBV-related HCC, regardless of HBV replication activity

BACKGROUND AND AIMS

Antiviral therapy (AVT) is required in patients with newly diagnosed hepatitis B virus (HBV)-related hepatocellular carcinoma (HCC), if HBV DNA is detectable. We compared the risk of recurrence according to HBV replication activity at the curative treatment of HBV-related HCC.

METHODS

Patients with HBV-related HCC who underwent surgical resection or radiofrequency ablation between 2013 and 2018 were enrolled in this retrospective cohort study. Patients were categorized into two groups according to HBV replication activity at the curative treatment of HBV-related HCC (group 1: patients who met the AVT indication for HBV-related HCC due to detectable HBV DNA but did not meet the AVT indication if without HCC; group 2: patients who met the AVT indication, regardless of HCC).

RESULTS

In the entire cohort (n = 911), HCC recurred in 303 (33.3%) patients during a median follow-up of 4.7 years. After multivariate adjustment, group 2 showed a statistically similar risk of HCC recurrence (adjusted hazard ratio [aHR] = 1.18, P = 0.332) compared to that of group 1. In addition, group 2 showed statistically similar risks of early (< 2 years; aHR = 1.31) and late (≥ 2 years; aHR = 0.83) recurrence than that of group 1 (all P>0.05). Propensity score matching and inverse probability of treatment weighting analysis also yielded similar risks of HCC recurrence between the two groups (all P>0.05, log-rank tests).

CONCLUSIONS

The risk of HCC recurrence in patients who received curative treatment for newly diagnosed HBV-related HCC was similar regardless of HBV replication activity, if AVT was properly initiated.

Prediction of glypican-3 expression in hepatocellular carcinoma using multisequence magnetic resonance imaging-based histology nomograms

Background

Hepatocellular carcinoma (HCC) is often associated with the overexpression of multiple proteins and genes. For instance, patients with HCC and a high expression of the glypican-3 (GPC3) gene have a poor prognosis, and noninvasive assessment of GPC3 expression before surgery is helpful for clinical decision-making. Therefore, our primary aim in this study was to develop and validate multisequence magnetic resonance imaging (MRI) radiomics nomograms for predicting the expression of GPC3 in individuals diagnosed with HCC.

Methods

We conducted a retrospective analysis of 143 patients with HCC, including 123 cases from our hospital and 20 cases from The Cancer Genome Atlas (TCGA) or The Cancer Imaging Archive (TCIA) public databases. We used preoperative multisequence MRI images of the patients for the radiomics analysis. We extracted and screened the imaging histologic features using fivefold cross-validation, Pearson correlation coefficient, and the least absolute shrinkage and selection operator (LASSO) analysis method. We used logistic regression (LR) to construct a radiomics model, developed nomograms based on the radiomics scores and clinical parameters, and evaluated the predictive performance of the nomograms using receiver operating characteristic (ROC) curves, calibration curves, and decision curves.

Results

Our multivariate analysis results revealed that tumor morphology (P=0.015) and microvascular (P=0.007) infiltration could serve as independent predictors of GPC3 expression in patients with HCC. The nomograms integrating multisequence radiomics radiomics score, tumor morphology, and microvascular invasion had an area under the curve (AUC) value of 0.989. This approach was superior to both the radiomics model (AUC 0.979) and the clinical model (AUC 0.793). The sensitivity, specificity, and accuracy of 0.944, 0.800, and 0.913 for the test set, respectively, and the model's calibration curve demonstrated good consistency (Brier score =0.029). The decision curve analysis (DCA) indicated that the nomogram had a higher net clinical benefit for predicting the expression of GPC3. External validation of the model's prediction yielded an AUC value of 0.826.

Conclusions

Our study findings highlight the close association of multisequence MRI imaging and radiomic features with GPC3 expression. Incorporating clinical parameters into nomograms can offer valuable preoperative insights into tailoring personalized treatment plans for patients diagnosed with HCC.

PAGE-B incorporating moderate HBV DNA levels predicts risk of HCC among patients entering into HBeAg-positive chronic hepatitis B

BACKGROUND & AIMS

Recent studies reported that moderate HBV DNA levels are significantly associated with hepatocellular carcinoma (HCC) risk in hepatitis B e antigen (HBeAg)-positive, non-cirrhotic patients with chronic hepatitis B (CHB). We aimed to develop and validate a new risk score to predict HCC development using baseline moderate HBV DNA levels in patients entering into HBeAg-positive CHB from chronic infection.

METHODS

This multicenter cohort study recruited 3,585 HBeAg-positive, non-cirrhotic patients who started antiviral treatment with entecavir or tenofovir disoproxil fumarate at phase change into CHB from chronic infection in 23 tertiary university-affiliated hospitals of South Korea (2012-2020). A new HCC risk score (PAGED-B) was developed (training cohort, n = 2,367) based on multivariable Cox models. Internal validation using bootstrap sampling and external validation (validation cohort, n = 1,218) were performed.

RESULTS

Sixty (1.7%) patients developed HCC (median follow-up, 5.4 years). In the training cohort, age, gender, platelets, diabetes and moderate HBV DNA levels (5.00-7.99 log10 IU/ml) were independently associated with HCC development; the PAGED-B score (based on these five predictors) showed a time-dependent AUROC of 0.81 for the prediction of HCC development at 5 years. In the validation cohort, the AUROC of PAGED-B was 0.85, significantly higher than for other risk scores (PAGE-B, mPAGE-B, CAMD, and REAL-B). When stratified by the PAGED-B score, the HCC risk was significantly higher in high-risk patients than in low-risk patients (sub-distribution hazard ratio = 8.43 in the training and 11.59 in the validation cohorts, all p <0.001).

CONCLUSIONS

The newly established PAGED-B score may enable risk stratification for HCC at the time of transition into HBeAg-positive CHB.

IMPACT AND IMPLICATIONS

In this study, we developed and validated a new risk score to predict hepatocellular carcinoma (HCC) development in patients entering into hepatitis B e antigen (HBeAg)-positive chronic hepatitis B (CHB) from chronic infection. The newly established PAGED-B score, which included baseline moderate HBV DNA levels (5-8 log10 IU/ml), improved on the predictive performance of prior risk scores. Based on a patient's age, gender, diabetic status, platelet count, and moderate DNA levels (5-8 log10 IU/ml) at the phase change into CHB from chronic infection, the PAGED-B score represents a reliable and easily available risk score to predict HCC development during the first 5 years of antiviral treatment in HBeAg-positive patients entering into CHB. With a scoring range from 0 to 12 points, the PAGED-B score significantly differentiated the 5-year HCC risk: low <7 points and high ≥7 points.

Hepatocellular Carcinoma Risk Scores from Modeling to Real Clinical Practice in Areas Highly Endemic for Hepatitis B Infection

Hepatocellular carcinoma (HCC) accounts for the majority of primary liver cancers and represents a global health challenge. Liver cancer ranks third in cancer-related mortality with 830,000 deaths and sixth in incidence with 906,000 new cases annually worldwide. HCC most commonly occurs in patients with underlying liver disease, especially chronic hepatitis B virus (HBV) infection in highly endemic areas. Predicting HCC risk based on scoring models for patients with chronic liver disease is a simple, effective strategy for identifying and stratifying patients to improve the early diagnosis rate and prognosis of HCC. We examined 23 HCC risk scores published worldwide in CHB patients with (n=10) or without (n=13) antiviral treatment. We also described the characteristics of the risk score's predictive performance and application status. In the future, higher predictive accuracy could be achieved by combining novel technologies and machine learning algorithms to develop and update HCC risk score models and integrated early warning and diagnosis systems for HCC in hospitals and communities.

NamiRNA-mediated high expression of KNSTRN correlates with poor prognosis and immune infiltration in hepatocellular carcinoma

Introduction

Mutations of kinetochore-localized astrin/sperm-associated antigen 5 (KNSTRN) can interfere with chromatid cohesion, increase aneuploidy in tumours, and enhance tumourigenesis. However, the role of the KNSTRN-binding protein in hepatocellular carcinoma (HCC) remains unclear.

Material and methods

Using The Cancer Genome Atlas databases, we investigated the potential oncogenic functions of KNSTRN in HCC along with R and various computational tools.

Results

Detailed results revealed that elevated expression of KNSTRN was considerably associated with poor overall survival (HR = 1.48, 95% CI: 1.05-2.09, p = 0.027) and progress-free interval (HR = 1.41, 95% CI: 1.05-1.89, p = 0.021) in HCC. Gene ontology/Kyoto Encyclopedia of Genes and Genomes functional enrichment analysis showed that KNSTRN is closely related to organelle fission, chromosomal region, tubulin binding, and cell cycle signalling pathway. TIMER database analysis showed the correlations between KNSTRN expression and tumour-infiltrating immune cells, biomarkers of immune cells, and immune checkpoint expression. Moreover, the KNSTRN level was significantly positively associated with immunosuppressive cells in the tumour microenvironment, including regulatory T-cells, myeloid-derived suppressor cells, and cancer-associated fibrocytes. Finally, a possible nuclear activating miRNA (NamiRNA)-enhancer network of hsa-miR-107, which activates the KNSTRN expression in liver hepatocellular carcinoma, was constructed by correlation analysis.

Conclusions

NamiRNA-mediated upregulation of KNSTRN correlated with poor prognosis and tumour immune infiltration in HCC. KNSTRN could serve as an effective biomarker for the diagnosis and prognosis of HCC and support the development of novel therapeutic strategies.

Hepatocellular carcinoma surveillance - utilization, barriers and the impact of changing aetiology

Hepatocellular carcinoma (HCC) is the third leading cause of cancer death worldwide. Surveillance for HCC is critical for early detection and treatment, but fewer than one-quarter of individuals at risk of HCC undergo surveillance. Multiple failures across the screening process contribute to the underutilization of surveillance, including limited disease awareness among patients and health-care providers, knowledge gaps, and difficulty recognizing patients who are at risk. Non-alcoholic fatty liver disease and alcohol-associated liver disease are the fastest-rising causes of HCC-related death worldwide and are associated with unique barriers to surveillance. In particular, more than one-third of patients with HCC related to non-alcoholic fatty liver disease do not have cirrhosis and therefore lack a routine indication for HCC surveillance on the basis of current practice guidelines. Semi-annual abdominal ultrasound with measurement of α-fetoprotein levels is recommended for HCC surveillance, but the sensitivity of this approach for early HCC is limited, especially for patients with cirrhosis or obesity. In this Review, we discuss the current status of HCC surveillance and the remaining challenges, including the changing aetiology of liver disease. We also discuss strategies to improve the utilization and quality of surveillance for HCC.

Prediction model of hepatitis B virus-related hepatocellular carcinoma in patients receiving antiviral therapy

Chronic hepatitis B virus (HBV) infection, which ultimately leads to liver cirrhosis, hepatic decompensation, and hepatocellular carcinoma (HCC), remains a significant disease burden worldwide. Despite the use of antiviral therapy (AVT) using oral nucleos(t)ide analogs (NUCs) with high genetic barriers, the risk of HCC development cannot be completely eliminated. Therefore, bi-annual surveillance of HCC using abdominal ultrasonography with or without tumor markers is recommended for at-risk populations. For a more precise assessment of future HCC risk at the individual level, many HCC prediction models have been proposed in the era of potent AVT with promising results. It allows prognostication according to the risk of HCC development, for example, low-vs. intermediate-vs. high-risk groups. Most of these models have the advantage of high negative predictive values for HCC development, allowing exemption from biannual HCC screening. Recently, non-invasive surrogate markers for liver fibrosis, such as vibration-controlled transient elastography, have been introduced as integral components of the equations, providing better predictive performance in general. Furthermore, beyond the conventional statistical methods that primarily depend on multi-variable Cox regression analyses based on the previous literature, newer techniques using artificial intelligence have also been applied in the design of HCC prediction models. Here, we aimed to review the HCC risk prediction models that were developed in the era of potent AVT and validated among independent cohorts to address the clinical unmet needs, as well as comment on future direction to establish the individual HCC risk more precisely.

A machine learning model for predicting hepatocellular carcinoma risk in patients with chronic hepatitis B

BACKGROUND

Machine learning (ML) algorithms can be used to overcome the prognostic performance limitations of conventional hepatocellular carcinoma (HCC) risk models. We established and validated an ML-based HCC predictive model optimized for patients with chronic hepatitis B (CHB) infections receiving antiviral therapy (AVT).

METHODS

Treatment-naïve CHB patients who were started entecavir (ETV) or tenofovir disoproxil fumarate (TDF) were enrolled. We used a training cohort (n = 960) to develop a novel ML model that predicted HCC development within 5 years and validated the model using an independent external cohort (n = 1937). ML algorithms consider all potential interactions and do not use predefined hypotheses.

RESULTS

The mean age of the patients in the training cohort was 48 years, and most patients (68.9%) were men. During the median 59.3 (interquartile range 45.8-72.3) months of follow-up, 69 (7.2%) patients developed HCC. Our ML-based HCC risk prediction model had an area under the receiver-operating characteristic curve (AUC) of 0.900, which was better than the AUCs of CAMD (0.778) and REAL B (0.772) (both p < .05). The better performance of our model was maintained (AUC = 0.872 vs. 0.788 for CAMD and 0.801 for REAL B) in the validation cohort. Using cut-off probabilities of 0.3 and 0.5, the cumulative incidence of HCC development differed significantly among the three risk groups (p < .001).

CONCLUSIONS

Our new ML model performed better than models in terms of predicting the risk of HCC development in CHB patients receiving AVT.

Hepatocellular carcinoma prediction model performance decreases with long-term antiviral therapy in chronic hepatitis B patients

BACKGROUND/AIMS

Existing hepatocellular carcinoma (HCC) prediction models are derived mainly from pretreatment or early on-treatment parameters. We reassessed the dynamic changes in the performance of 17 HCC models in patients with chronic hepatitis B (CHB) during long-term antiviral therapy (AVT).

METHODS

Among 987 CHB patients administered long-term entecavir therapy, 660 patients had 8 years of follow-up data. Model scores were calculated using on-treatment values at 2.5, 3, 3.5, 4, 4.5, and 5 years of AVT to predict threeyear HCC occurrence. Model performance was assessed with the area under the receiver operating curve (AUROC). The original model cutoffs to distinguish different levels of HCC risk were evaluated by the log-rank test.

RESULTS

The AUROCs of the 17 HCC models varied from 0.51 to 0.78 when using on-treatment scores from years 2.5 to 5. Models with a cirrhosis variable showed numerically higher AUROCs (pooled at 0.65-0.73 for treated, untreated, or mixed treatment models) than models without (treated or mixed models: 0.61-0.68; untreated models: 0.51-0.59). Stratification into low, intermediate, and high-risk levels using the original cutoff values could no longer reflect the true HCC incidence using scores after 3.5 years of AVT for models without cirrhosis and after 4 years of AVT for models with cirrhosis.

CONCLUSION

The performance of existing HCC prediction models, especially models without the cirrhosis variable, decreased in CHB patients on long-term AVT. The optimization of existing models or the development of novel models for better HCC prediction during long-term AVT is warranted.

CAGE-B and SAGE-B models better predict the hepatitis B virus-related hepatocellular carcinoma after 5-year entecavir treatment than PAGE-B

OBJECTIVES

The PAGE-B model consists of variables at the initiation of antiviral therapy (AVT), whereas the SAGE-B and CAGE-B models consist of variables after 5 years of AVT. We aimed to compare the predictive accuracy of three risk prediction models for hepatocellular carcinoma (HCC) development after 5 years of AVT in patients with chronic hepatitis B (CHB).

METHODS

A total of 1335 patients who initiated entecavir (ETV) treatment between 2006 and 2011 and were followed up for more than 5 years were enrolled in the study.

RESULTS

At ETV initiation, the median age was 49 years and the median score of the PAGE-B model was 14. After 5 years of ETV treatment, the median SAGE-B and CAGE-B scores were 6 and 6. During the study period, 93 (7.0%) patients developed HCC after 5-year treatment. In multivariate analysis, PAGE-B (hazard ratio [HR] 1.151, 95% confidence interval [CI] 1.087-1.219), SAGE-B (HR 1.340, 95% CI 1.228-1.463), and CAGE-B (HR 1.327, 95% CI 1.223-1.440) models independently predicted HCC development after 5 years of treatment (all P < 0.001). The high-risk groups of the three risk prediction models showed a significantly higher risk of HCC development compared to the medium- and low-risk groups (both P < 0.05). The AUROC of the SAGE-B (0.772-0.844) and CAGE-B (0.785-0.838) models was significantly higher than those of the PAGE-B model (0.696-0.745) in predicting HCC development after 5 years of treatment (both P < 0.05).

CONCLUSION

The SAGE-B and CAGE-B models might be better than the PAGE-B model in predicting HCC development after 5 years of ETV treatment.

Comparable outcomes between immune-tolerant and active phases in noncirrhotic chronic hepatitis B: a meta-analysis

BACKGROUND

Antiviral therapy is not indicated for patients with chronic hepatitis B (CHB) in the immune-tolerant (IT) phase. We compared the outcomes between the untreated IT phase and the treated immune-active (IA) phase in noncirrhotic HBeAg-positive CHB patients.

METHODS

We systematically searched 4 databases, including PubMed, Medline, Embase, and Cochrane, until August 2021. The pooled incidence rates of HCC and mortality in the IT and IA cohorts and phase change in the IT cohort were investigated. Studies that included patients with liver cirrhosis were excluded.

RESULTS

Thirteen studies involving 11,903 patients were included. The overall median of the median follow-up period was 62.4 months. The pooled 5-year and 10-year incidence rates of HCC were statistically similar between the IT and IA cohorts (1.1%, 95% CI: 0.4%-2.8% vs. 1.1%, 95% CI: 0.5%-2.3%, and 2.7%, 95% CI: 1.0%-7.3% vs. 3.6%, 95% CI: 2.4%-5.5%, respectively, all p>0.05). The pooled 5-year odds ratio of HCC between IT and IA cohorts was 1.05 (95% CI: 0.32-3.45; p=0.941). The pooled 5-year incidence rate of mortality was statistically similar between the IT and IA cohorts (1.9%, 95% CI: 1.1%-3.4% vs. 1.0%, 95% CI: 0.3%-2.9%, p=0.285). Finally, the pooled 5-year incidence rate of phase change in the IT cohort was 36.1% (95% CI: 29.5%-43.2%).

CONCLUSION

The pooled incidence rates of HCC and mortality were comparable between the untreated IT and the treated IA phases in noncirrhotic HBeAg-positive CHB patients.

A new model predicts hepatocellular carcinoma in patients with HBV-related decompensated liver cirrhosis and long-term antiviral therapy: a prospective study

Background

We aimed to evaluate the prediction values of non-invasive models for hepatocellular carcinoma (HCC) development in patients with HBV-related liver cirrhosis (LC) and long-term NA treatment.

Methods

Patients with compensated or decompensated cirrhosis (DC), who achieved long-term virological response, were enrolled. DC and its stages were defined by the complications including ascites, encephalopathy, variceal bleeding, or renal failure. Prediction accuracy of several risk scores, including ALBI, CAMD, PAGE-B, mPAGE-B and aMAP, was compared.

Results

The median follow-up duration was 37 (28-66) months. Among the 229 patients, 9 (9.57%) patients in the compensated LC group and 39 (28.89%) patients in the DC group developed HCC. The incidence of HCC was higher in the DC group ( X ² = 12.478, P < 0.01). The AUROC of ALBI, aMAP, CAMD, PAGE-B and mPAGE-B scores were 0.512, 0.667, 0.638, 0.663, 0.679, respectively. There was no significant difference in AUROC between CAMD, aMAP, PAGE-B and mPAGE-B (all P > 0.05). Univariable analysis showed that age, DC status and platelet were associated with HCC development, and multivariable analysis showed that age and DC status (both P < 0.01) were independent risk factors for HCC development, then Model (Age_DC) was developed and its AUROC was 0.718. Another model, Model (Age_DC_PLT_TBil) consisting of age, DC stage, PLT, TBil was also developed, and its AUROC was larger than that of Model (Age_DC) (0.760 vs. 0.718). Moreover, AUROC of Model (Age_DC_PLT_TBil) was larger than the other five models (all P < 0.05). With an optimal cut-off value of 0.236, Model (Age_DC_PLT_TBil) achieved 70.83% sensitivity, 76.24% specificity.

Conclusion

There is a lack of non-invasive risk scores for HCC development in HBV-related DC, and a new model consisting of age, DC stage, PLT, TBil may be an alternative.

Development of a nomogram to predict the risk of hepatocellular carcinoma in patients with hepatitis B-related cirrhosis on antivirals

Objective

Patients with compensated hepatitis B-related cirrhosis receiving antivirals are at the risk of hepatocellular carcinoma (HCC). This study aimed to develop and validate a nomogram for predicting the incidence of HCC in patients with hepatitis-B related cirrhosis.

Design

A total of 632 patients with compensated hepatitis-B related cirrhosis treated with entecavir or tenofovir between August 2010 and July 2018 were enrolled. Cox regression analysis was used to identify independent risk factors for HCC and a nomogram was developed using these factors. The area under the receiver operating characteristic curve (AUC), calibration curve, and decision curve analyses were used to evaluate the nomogram performance. The results were validated in an external cohort (n = 324).

Results

In the multivariate analysis, age per 10 years, neutrophil-lymphocyte ratio > 1.6, and platelet count < 86×10⁹/L were independent predictors of HCC occurrence. A nomogram was developed to predict HCC risk using these three factors (ranging from 0 to 20). The nomogram showed better performance (AUC: 0.83) than that of the established models (all P < 0.05). The 3-year cumulative HCC incidences in the low- (scores < 4), medium- (4-10), and high-risk (> 10) subgroups were 0.7%, 4.3%, and 17.7%, respectively, in the derivation cohort, and 1.2%, 3.9%, and 17.8%, respectively, in the validation cohort.

Conclusion

The nomogram showed good discrimination and calibration in estimating HCC risk in patients with hepatitis-B related cirrhosis on antivirals. High-risk patients with a score > 10 points require close surveillance.

Suboptimal Performance of Hepatocellular Carcinoma Prediction Models in Patients with Hepatitis B Virus-Related Cirrhosis

This study aimed to evaluate the predictive performance of pre-existing well-validated hepatocellular carcinoma (HCC) prediction models, established in patients with HBV-related cirrhosis who started potent antiviral therapy (AVT). We retrospectively reviewed the cases of 1339 treatment-naïve patients with HBV-related cirrhosis who started AVT (median period, 56.8 months). The scores of the pre-existing HCC risk prediction models were calculated at the time of AVT initiation. HCC developed in 211 patients (15.1%), and the cumulative probability of HCC development at 5 years was 14.6%. Multivariate Cox regression analysis revealed that older age (adjusted hazard ratio [aHR], 1.023), lower platelet count (aHR, 0.997), lower serum albumin level (aHR, 0.578), and greater LS value (aHR, 1.012) were associated with HCC development. Harrell’s c-indices of the PAGE-B, modified PAGE-B, modified REACH-B, CAMD, aMAP, HCC-RESCUE, AASL-HCC, Toronto HCC Risk Index, PLAN-B, APA-B, CAGE-B, and SAGE-B models were suboptimal in patients with HBV-related cirrhosis, ranging from 0.565 to 0.667. Nevertheless, almost all patients were well stratified into low-, intermediate-, or high-risk groups according to each model (all log-rank p < 0.05), except for HCC-RESCUE (p = 0.080). Since all low-risk patients had cirrhosis at baseline, they had unneglectable cumulative incidence of HCC development (5-year incidence, 4.9−7.5%). Pre-existing risk prediction models for patients with chronic hepatitis B showed suboptimal predictive performances for the assessment of HCC development in patients with HBV-related cirrhosis.