ABSTRACT
BACKGROUND: Chronic hepatitis C (CHC) increases the risk of liver cirrhosis (LC) and hepatocellular carcinoma (HCC). This nationwide cohort study assessed the effectiveness of viral eradication of CHC. METHODS: The Taiwanese chronic hepatitis C cohort and Taiwan hepatitis C virus (HCV) registry are nationwide HCV registry cohorts incorporating data from 23 and 53 hospitals in Taiwan, respectively. This study included 27,577 individuals from these cohorts that were given a diagnosis of CHC and with data linked to the Taiwan National Health Insurance Research Database. Patients received either pegylated interferon and ribavirin or direct-acting antiviral agent therapy for > 4 weeks for new-onset LC and liver-related events. RESULTS: Among the 27,577 analyzed patients, 25,461 (92.3%) achieved sustained virologic response (SVR). The mean follow-up duration was 51.2 ± 48.4 months, totaling 118,567 person-years. In the multivariable Cox proportional hazard analysis, the hazard ratio (HR) for incident HCC was 1.39 (95% confidence interval [CI]: 1.00-1.95, p = 0.052) among noncirrhotic patients without SVR compared with those with SVR and 1.82 (95% CI 1.34-2.48) among cirrhotic patients without SVR. The HR for liver-related events, including HCC and decompensated LC, was 1.70 (95% CI 1.30-2.24) among cirrhotic patients without SVR. Patients with SVR had a lower 10-year cumulative incidence of new-onset HCC than those without SVR did (21.7 vs. 38.7% in patients with LC, p < 0.001; 6.0 vs. 18.4% in patients without LC, p < 0.001). CONCLUSION: HCV eradication reduced the incidence of HCC in patients with and without LC and reduced the incidence of liver-related events in patients with LC.
ABSTRACT
BACKGROUND AND AIM: Understanding the dynamics of serum Mac-2 binding protein glycosylation isomer (M2BPGi) remains pivotal for hepatitis C virus (HCV) patients' post-sustained virologic response (SVR12) through direct-acting antivirals (DAAs). METHODS: We compared areas under receiver operating characteristic curves (AUROCs) of M2BPGi, FIB-4, and APRI and assess M2BPGi cutoff levels in predicting fibrosis stages of ≥F3 and F4 utilizing transient elastography in 638 patients. Variations in M2BPGi levels from pretreatment to SVR12 and their association with pretreatment alanine transaminase (ALT) levels and fibrosis stage were investigated. RESULTS: The AUROCs of M2BPGi were comparable to FIB-4 in predicting ≥F3 (0.914 vs 0.902, P = 0.48) and F4 (0.947 vs 0.915, P = 0.05) but were superior to APRI in predicting ≥F3 (0.914 vs 0.851, P = 0.001) and F4 (0.947 vs 0.857, P < 0.001). Using M2BPGi cutoff values of 2.83 and 3.98, fibrosis stages of ≥F3 and F4 were confirmed with a positive likelihood ratio ≥10. The median M2BPGi change was -0.55. Patients with ALT levels ≥5 times ULN or ≥F3 demonstrated more pronounced median decreases in M2BPGi level compared to those with ALT levels 2-5 times ULN and <2 times ULN (-0.97 vs -0.68 and -0.44; P < 0.001) or with < F3 (-1.52 vs -0.44; P < 0.001). CONCLUSIONS: Serum M2BPGi is a reliable marker for advanced hepatic fibrosis. Following viral clearance, there is a notable M2BPGi decrease, with the extent of reduction influenced by ALT levels and fibrosis stage.
ABSTRACT
BACKGROUND AND AIMS: Risk stratification for patients with a higher risk of hepatocellular carcinoma (HCC) is crucial. We aimed to investigate the role of the Fibrosis-4 (FIB-4) index in predicting chronic hepatitis C (CHC)-related HCC. METHODS: A retrospective cohort study consecutively included treatment-naive CHC patients receiving longitudinal follow-up at the National Taiwan University Hospital from 1986 to 2014. The clinical data were collected and traced for HCC development. Multivariable Cox proportional hazard regression analysis was used to investigate the predictors for HCC. RESULTS: A total of 1285 patients in the ERADICATE-C cohort were included. The median age was 54, 56% were females, and 933 had HCV viremia. There were 33%, 38%, and 29% of patients having FIB-4 index <1.45, 1.45-3.25, and ≥3.25, respectively. After a median of 9-year follow-up, 186 patients developed HCC. Multivariable analysis revealed that older age, AFP≥20 ng/mL, cirrhosis, and a higher FIB-4 index were independent predictors for HCC. Compared with patients with FIB-4 index <1.45, those with FIB-4 1.45-3.25 had a 5.51-fold risk (95% confidence interval [CI]: 2.65-11.46), and those with FIB-4 ≥ 3.25 had 7.45-fold risk (95% CI: 3.46-16.05) of HCC. In CHC patients without viremia, FIB-4 index 1.45-3.25 and FIB-4 ≥ 3.25 increased 6.78-fold and 16.77-fold risk of HCC, respectively, compared with those with FIB-4 < 1.45. CONCLUSION: The baseline FIB-4 index can stratify the risks of HCC in untreated CHC patients, even those without viremia. The FIB-4 index should thus be included in the management of CHC.
ABSTRACT
Longitudinal analysis of antibody responses following three-dose COVID-19 vaccination in patients with chronic liver disease (CLD) has been limited. From August 2021 to February 2023, sequential anti-SARS-CoV-2 spike IgG titers were determined in 45 patients with CLD who received two or three doses of COVID-19 vaccine. The geometric mean of anti-spike IgG at four weeks after the second and third doses were 1313.16 BAU/mL and 3042.29 BAU/mL, respectively, and it decreased significantly from four to 24 weeks after the second (1313.16 vs. 198.42 BAU/mL, p = 0.002) and the third (3042.29 vs. 636.71 BAU/mL, p < 0.001) dose. The anti-spike IgG titers in participants receiving prime-boost homologous mRNA vaccines (BNT162b2 or mRNA-1273) were comparable between participants with and those without significant liver fibrosis at each follow-up time point. This study demonstrated a notable decrease in anti-spike IgG after completion of the vaccination schedule in patients with CLD, highlighting the importance of additional booster doses.
ABSTRACT
INTRODUCTION: The prevalence of metabolic dysfunction-associated steatotic liver disease (MASLD) is increasing among the chronic hepatitis B (CHB) population. This study aimed to explore the impact of metabolic dysfunction (MD) on cirrhosis and cirrhotic complication risks in CHB. METHODS: Patients with CHB were consecutively recruited between 2006 and 2021. The presence of MD was based on the 5 cardiometabolic criteria specified in the MASLD definition. Patients were categorized into MD/non-MD groups based on these criteria. RESULTS: Eleven thousand five hundred two treatment-naive noncirrhotic patients with CHB were included with a median follow-up of 5.3 years. Patients in the MD group (n = 7,314) were older and had lower hepatitis B virus DNA levels than non-MD patients (n = 4,188). After adjustment for clinical and viral factors, MD patients had significantly higher risks of cirrhosis (adjusted hazard ratio [aHR]: 1.82, 95% confidence interval [CI]: 1.40-2.37, P < 0.001) and cirrhotic complications (aHR: 1.30 per MD, 95% CI: 1.03-1.63, P = 0.025) in a dose-dependent manner. Furthermore, new-onset diabetes mellitus during the follow-up aggravated the risk of cirrhotic complications (aHR: 2.87, 95% CI: 1.34-6.11, P = 0.006). Hepatic steatosis was associated with lower risks of cirrhosis (aHR: 0.57 within 5 years, 95% CI: 0.44-0.74, P < 0.001) and cirrhotic complications (aHR: 0.45, 95% CI 0.23-0.88, P = 0.020). Among individuals with hepatic steatosis, patients with MASLD exhibited a higher cirrhosis risk than non-MD patients. DISCUSSION: Concurrent and new-onset MDs increase the risks of cirrhosis and cirrhotic complications in patients with CHB, independent of hepatic steatosis. Proactively investigating metabolic comorbidities in CHB is critical to stratify the risk of liver disease progression.
ABSTRACT
Comparison of diagnostic accuracy for commercial hepatitis C virus (HCV) genotyping (Abbott RealTime HCV Genotyping II, Roche Cobas Genotyping) and investigational Abbott HCV Genotype plus RUO assays designed to discriminate genotype (GT)-1a, 1b or 6 in cases of ambiguous GT from the Abbott commercial assay remains limited. 743 HCV-viremic samples were subjected to analysis using Abbott and Roche commercial as well as Abbott HCV Genotype plus RUO assays. Next-generation sequencing (NGS) targeting core region was employed as the reference standard. Diagnostic accuracy was reported as the number of participants (percentages) along with 95% confidence intervals (CIs). Using NGS, 741 samples (99.7%) yielded valid genotyping results. The diagnostic accuracies were 97.6% (95% CI: 96.1%-98.5%) and 95.3% (95% CI: 93.4%-96.6%) using Abbott and Roche commercial assays (p = 0.0174). Abbott commercial assay accurately diagnosed HCV GT-6a and 6w, whereas Roche commercial assay accurately diagnosed HCV GT-6a. Both assays demonstrated low accuracies for HCV GT-6b, 6e, 6g, and 6n. Abbott HCV Genotype plus RUO assay discriminated 13 of the 14 samples (92.9%; 95% CI: 64.2%-99.6%) that yielded ambiguous GT. Both assays were capable of diagnosing mixed HCV infections when the minor genotype comprised >8.4% of the viral load. The diagnostic performance of commercial HCV genotyping assays is commendable. Abbott assay demonstrated superior performance compared to Roche assay in diagnosing HCV GT-6. Abbott HCV Genotype plus RUO assay aids in discriminating ambiguous GT. Both commercial assays are proficient in diagnosing mixed HCV infections at a cut-off viral load of 8.4% in minor genotype.
Subject(s)
Genotype , Genotyping Techniques , Hepacivirus , Hepatitis C , High-Throughput Nucleotide Sequencing , Humans , Hepacivirus/genetics , Hepacivirus/classification , Hepacivirus/isolation & purification , Genotyping Techniques/methods , High-Throughput Nucleotide Sequencing/methods , Hepatitis C/diagnosis , Hepatitis C/virology , Molecular Diagnostic Techniques/methods , Sensitivity and Specificity , Reagent Kits, Diagnostic/standards , Female , Male , Middle Aged , AdultABSTRACT
Early confirmation of sustained virologic response (SVR) or viral relapse after direct-acting antivirals (DAAs) for hepatitis C virus (HCV) infection is essential based on public health perspectives, particularly for patients with high risk of nonadherence to posttreatment follow-ups. A total of 1011 patients who achieved end-of-treatment virologic response, including 526 receiving fixed-dose pangenotypic DAAs, and 485 receiving other types of DAAs, who had available off-treatment weeks 4 and 12 serum HCV RNA data to confirm SVR at off-treatment week 12 (SVR12) or viral relapse were included. The positive predictive value (PPV) and negative predictive value (NPV) of SVR4 to predict patients with SVR12 or viral relapse were reported. Furthermore, we analyzed the proportion of concordance between SVR12 and SVR24 in 943 patients with available SVR24 data. The PPV and NPV of SVR4 to predict SVR12 were 98.5% (95% confidence interval [CI]: 98.0-98.9) and 100% (95% CI: 66.4-100) in the entire population. The PPV of SVR4 to predict SVR12 in patients receiving fixed-dose pangenotypic DAAs was higher than those receiving other types of DAAs (99.8% [95% CI: 98.9-100] vs. 97.1% [95% CI: 96.2-97.8], p < 0.001). The NPVs of SVR4 to predict viral relapse were 100%, regardless of the type of DAAs. Moreover, the concordance between SVR12 and SVR24 was 100%. In conclusion, an off-treatment week 4 serum HCV RNA testing is sufficient to provide an excellent prediction power of SVR or viral relapse at off-treatment week 12 among patients with HCV who are treated with fixed-dose pangenotypic DAAs.
Subject(s)
Antiviral Agents , Hepacivirus , Hepatitis C, Chronic , RNA, Viral , Sustained Virologic Response , Humans , Antiviral Agents/therapeutic use , Antiviral Agents/administration & dosage , Male , Female , Middle Aged , Hepacivirus/genetics , Hepacivirus/drug effects , Aged , Adult , RNA, Viral/blood , Hepatitis C, Chronic/drug therapy , Hepatitis C, Chronic/virology , Recurrence , Follow-Up Studies , Treatment Outcome , Hepatitis C/drug therapy , Hepatitis C/virologyABSTRACT
BACKGROUND/AIMS: Chronic hepatitis C (CHC) patients who failed antiviral therapy are at increased risk for hepatocellular carcinoma (HCC). This study assessed the potential role of metformin and statins, medications for diabetes mellitus (DM) and hyperlipidemia (HLP), in reducing HCC risk among these patients. METHODS: We included CHC patients from the T-COACH study who failed antiviral therapy. We tracked the onset of HCC 1.5 years post-therapy by linking to Taiwan's cancer registry data from 2003 to 2019. We accounted for death and liver transplantation as competing risks and employed Gray's cumulative incidence and Cox subdistribution hazards models to analyze HCC development. RESULTS: Out of 2,779 patients, 480 (17.3%) developed HCC post-therapy. DM patients not using metformin had a 51% increased risk of HCC compared to non-DM patients, while HLP patients on statins had a 50% reduced risk compared to those without HLP. The 5-year HCC incidence was significantly higher for metformin non-users (16.5%) versus non-DM patients (11.3%; adjusted sub-distribution hazard ratio [aSHR]=1.51; P=0.007) and metformin users (3.1%; aSHR=1.59; P=0.022). Statin use in HLP patients correlated with a lower HCC risk (3.8%) compared to non-HLP patients (12.5%; aSHR=0.50; P<0.001). Notably, the increased HCC risk associated with non-use of metformin was primarily seen in non-cirrhotic patients, whereas statins decreased HCC risk in both cirrhotic and non-cirrhotic patients. CONCLUSION: Metformin and statins may have a chemopreventive effect against HCC in CHC patients who failed antiviral therapy. These results support the need for personalized preventive strategies in managing HCC risk.
Subject(s)
Antiviral Agents , Carcinoma, Hepatocellular , Hepatitis C, Chronic , Hydroxymethylglutaryl-CoA Reductase Inhibitors , Liver Neoplasms , Metformin , Humans , Carcinoma, Hepatocellular/prevention & control , Carcinoma, Hepatocellular/etiology , Carcinoma, Hepatocellular/epidemiology , Hepatitis C, Chronic/complications , Hepatitis C, Chronic/drug therapy , Male , Liver Neoplasms/prevention & control , Liver Neoplasms/epidemiology , Liver Neoplasms/etiology , Metformin/therapeutic use , Female , Middle Aged , Hydroxymethylglutaryl-CoA Reductase Inhibitors/therapeutic use , Antiviral Agents/therapeutic use , Taiwan/epidemiology , Incidence , Aged , Adult , Risk Factors , Proportional Hazards Models , Diabetes MellitusABSTRACT
BACKGROUND: Information on the dynamics of metabolic dysfunction-associated steatotic liver disease (MASLD) among hepatitis C virus patients achieving sustained virologic response (SVR12) with direct-acting antivirals (DAAs) is limited. METHODS: We enrolled 1512 eligible participants in this prospective study. MASLD was defined by a controlled attenuation parameter (CAP) of ≥248 dB/m utilizing vibration-controlled transient elastography in conjunction with presence of ≥1 cardiometabolic risk factor. The distribution of MASLD and the changes in CAP were evaluated before treatment and at SVR12. Forward stepwise logistic regression analyses were performed to determine factors significantly associated with the regression or emergence of MASLD. RESULTS: The prevalence of MASLD decreased from 45.0% before treatment to 36.1% at SVR12. Among 681 participants with MASLD before treatment, 144 (21%) exhibited MASLD regression at SVR12. Conversely, among 831 participants without MASLD before treatment, 9 (1.1%) developed MASLD at SVR12. Absence of type 2 diabetes (T2D) [odds ratio (OR): 1.73, 95% confidence interval (CI): 1.13-2.65, p = 0.011], age > 50 years (OR: 1.73, 95% CI: 1.11-2.68, p = 0.015), and alanine transaminase (ALT) ≤ 2 times the upper limit of normal (ULN) (OR: 1.56; 95% CI: 1.03-2.37, p = 0.035) were associated with the regression of MASLD. Presence of T2D was associated with the emergence of MASLD (OR: 5.83, 95% CI: 1.51-22.56, p = 0.011). CONCLUSIONS: The prevalence of MASLD decreased after achieving SVR12 with DAAs. Patients with pre-existing T2D showed a diminished probability of MASLD regression and a heightened risk of MASLD emergence post-SVR12.
Subject(s)
Antiviral Agents , Fatty Liver , Hepatitis C, Chronic , Sustained Virologic Response , Humans , Middle Aged , Antiviral Agents/therapeutic use , Female , Male , Prospective Studies , Aged , Hepatitis C, Chronic/drug therapy , Hepatitis C, Chronic/complications , Elasticity Imaging Techniques , Adult , Prevalence , Risk Factors , Diabetes Mellitus, Type 2/complications , Diabetes Mellitus, Type 2/drug therapyABSTRACT
INTRODUCTION: Eight-week glecaprevir/pibrentasvir (GLE/PIB) is indicated for treatment-naïve (TN) patients with chronic hepatitis C (CHC), with or without compensated cirrhosis. Given that the Taiwanese government is committed to eliminating hepatitis C virus (HCV) by 2025, this study aimed to measure real-world evidence for TN patients using 8-week GLE/PIB in the Taiwan HCV Registry (TACR). METHODS: The data of patients with CHC treated with 8-week GLE/PIB were retrieved from TACR, a nationwide registry program organized by the Taiwan Association for the Study of the Liver (TASL). Treatment efficacy, defined as a sustained virologic response at posttreatment week 12 (SVR12), was assessed in the modified intention-to-treat (mITT) population, which excluded patients who were lost to follow-up or lacked SVR12 data. The safety profile of the ITT population was assessed. RESULTS: A total of 7246 (6897 without cirrhosis; 349 with cirrhosis) patients received at least one dose of GLE/PIB (ITT), 7204 of whom had SVR12 data available (mITT). The overall SVR12 rate was 98.9% (7122/7204) among all patients, 98.9% (6780/6856) and 98.3% (342/348) among patients without and with cirrhosis, respectively. For the selected subgroups, which included patients with genotype 3 infection, diabetes, chronic kidney disease, people who injected drugs, and those with human immunodeficiency virus coinfection, the SVR12 rates were 95.1% (272/286), 98.9% (1084/1096), 99.0% (1171/1183), 97.4% (566/581), and 96.1% (248/258), respectively. Overall, 14.1% (1021/7246) of the patients experienced adverse events (AEs). Twenty-two patients (0.3%) experienced serious AEs, and 15 events (0.2%) resulted in permanent drug discontinuation. Only one event was considered treatment drug related. CONCLUSION: Eight-week GLE/PIB therapy was effective and well tolerated in all TN patients, regardless of cirrhosis status.
ABSTRACT
INTRODUCTION: Complete viral suppression with nucleos(t)ide analogs (NAs) has led to a profound reduction in hepatocellular carcinoma and mortality among patients with chronic hepatitis B. Finite therapy yields higher rates of functional cure; however, initial hepatitis B virus (HBV) DNA and alanine aminotransferase (ALT) elevations are almost certain after treatment interruption. We aimed to analyze off-treatment outcomes beyond 12 months after NA cessation. METHODS: Patients with well-suppressed chronic hepatitis B who were hepatitis B e antigen-negative at NA cessation and remained off treatment without hepatitis B surface antigen (HBsAg) loss at 12 months were included (n = 945). HBV DNA and ALT fluctuations were allowed within the first 12 months. We used Kaplan-Meier methods to analyze outcomes beyond 12 months. Sustained remission was defined as HBV DNA <2,000 IU/mL and ALT <2× upper limit of normal (ULN) and an ALT flare as ALT ≥5× ULN. RESULTS: Cumulative probability of sustained remission was 29.7%, virological relapse was 65.2% with a mean peak HBV DNA of 5.0 ± 1.5 log 10 IU/mL, an ALT flare was 15.6% with a median peak ALT × ULN of 8.3 (5.7-11.3), HBsAg loss was 9.9% and retreatment was 34.9% at 48 months after NA cessation. A single occurrence of virological relapse or an ALT flare within the first 12 months off-treatment were associated with significantly lower rates of sustained remission beyond 12 months. DISCUSSION: Despite allowing for HBV DNA and ALT fluctuations within the first 12 months off-treatment, most patients without HBsAg loss did not maintain a sustained response thereafter. The best candidates for NA withdrawal are patients with low HBsAg levels at NA cessation, and those without profound or recurrent virological and biochemical relapses in the first off-treatment year.
ABSTRACT
End-stage liver disease (ESLD) is a life-threatening clinical syndrome and when complicated with infection the mortality is markedly increased. In patients with ESLD, bacterial or fungal infection can induce or aggravate the occurrence or progression of liver decompensation. Consequently, infections are among the most common complications of disease deterioration. There is an overwhelming need for standardized protocols for early diagnosis and appropriate management for patients with ESLD complicated by infections. Asia Pacific region has the largest number of ESLD patients, due to hepatitis B and the growing population of alcohol and NAFLD. Concomitant infections not only add to organ failure and high mortality but also to financial and healthcare burdens. This consensus document assembled up-to-date knowledge and experience from colleagues across the Asia-Pacific region, providing data on the principles as well as evidence-based current working protocols and practices for the diagnosis and treatment of patients with ESLD complicated by infections.
Subject(s)
Consensus , End Stage Liver Disease , Humans , Bacterial Infections/diagnosis , Bacterial Infections/complications , End Stage Liver Disease/complications , End Stage Liver Disease/diagnosis , Mycoses/diagnosis , Mycoses/complicationsABSTRACT
BACKGROUND: Tenofovir disoproxil fumarate (TDF) and entecavir (ETV) reduce the risk of hepatocellular carcinoma (HCC) in patients of hepatitis B. This study compared the difference between ETV and TDF on risk of HCC recurrence and mortality in patients with HBV-related HCC after curative intent treatment. METHODS: Patients with HBV-related HCC who received HCC treatment (surgery or radiofrequency ablation [RFA]) and underwent long-term ETV or TDF therapy were retrospectively included. Baseline characteristics including age, sex, antiviral therapy, liver reserve, HCC stages, pathology reports and treatment modality were obtained. The risk of tumor recurrence, all-cause mortality, HCC-related mortality, and liver function were compared. RESULTS: We identified 390 HBV-related HCC patients with curative intent treatment for HCC and treated with ETV (n = 328) or TDF (n = 62) between January 2011 and December 2020. The median age was 60 years, and 90.7% patients were males. After a median follow-up of 29 months, 186 patients developed recurrent HCC and 111 died. The baseline characteristics were comparable except more ALBI grade 3 patients in TDF group (76% vs. 48%, P < 0.001). Compared to ETV group, TDF users had lower all-cause mortality (adjusted hazard ratio [aHR]: 0.38, P = 0.003), and HCC-related mortality (aHR: 0.23, P = 0.005). Lower recurrence rate was noticed in TDF users after inverse probability of treatment weighting (IPTW). TDF users had improved ALBI grade and FIB-4 index compared with ETV groups. CONCLUSION: TDF therapy is associated with a reduced risk of HCC-related outcomes among patients with HBV-related HCC after curative intent treatment compared with ETV usage.
Subject(s)
Antiviral Agents , Carcinoma, Hepatocellular , Guanine , Liver Neoplasms , Neoplasm Recurrence, Local , Tenofovir , Humans , Carcinoma, Hepatocellular/mortality , Carcinoma, Hepatocellular/virology , Male , Female , Liver Neoplasms/mortality , Liver Neoplasms/virology , Middle Aged , Tenofovir/therapeutic use , Retrospective Studies , Guanine/analogs & derivatives , Guanine/therapeutic use , Antiviral Agents/therapeutic use , Aged , Hepatitis B, Chronic/complications , Hepatitis B, Chronic/drug therapy , Hepatitis B, Chronic/mortality , Taiwan/epidemiology , Hepatitis B virus , AdultABSTRACT
BACKGROUND/AIMS: Despite the high efficacy of direct-acting antivirals (DAAs), approximately 1-3% of hepatitis C virus (HCV) patients fail to achieve a sustained virological response. We conducted a nationwide study to investigate risk factors associated with DAA treatment failure. Machine-learning algorithms have been applied to discriminate subjects who may fail to respond to DAA therapy. METHODS: We analyzed the Taiwan HCV Registry Program database to explore predictors of DAA failure in HCV patients. Fifty-five host and virological features were assessed using multivariate logistic regression, decision tree, random forest, eXtreme Gradient Boosting (XGBoost), and artificial neural network. The primary outcome was undetectable HCV RNA at 12 weeks after the end of treatment. RESULTS: The training (n=23,955) and validation (n=10,346) datasets had similar baseline demographics, with an overall DAA failure rate of 1.6% (n=538). Multivariate logistic regression analysis revealed that liver cirrhosis, hepatocellular carcinoma, poor DAA adherence, and higher hemoglobin A1c were significantly associated with virological failure. XGBoost outperformed the other algorithms and logistic regression models, with an area under the receiver operating characteristic curve of 1.000 in the training dataset and 0.803 in the validation dataset. The top five predictors of treatment failure were HCV RNA, body mass index, α-fetoprotein, platelets, and FIB-4 index. The accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of the XGBoost model (cutoff value=0.5) were 99.5%, 69.7%, 99.9%, 97.4%, and 99.5%, respectively, for the entire dataset. CONCLUSION: Machine learning algorithms effectively provide risk stratification for DAA failure and additional information on the factors associated with DAA failure.