Background/Objectives: Autoimmune hepatitis (AIH) is a chronic immune-mediated inflammatory liver disease that, if not diagnosed and treated promptly, leads to cirrhosis and liver failure. Data on AIH in Central Asia, including Kazakhstan, remain limited. The aim of this study was to characterize the clinical profile of AIH in a Kazakhstani patient cohort, determine the timeliness of diagnosis, and develop an interpretable machine learning model for detecting liver fibrosis based on routine clinical and laboratory parameters. Methods: A retrospective observational study of adult patients with a diagnosis of AIH between 2015 and 2025 was conducted. Demographic, laboratory, instrumental, and histological data of patients with AIH were extracted from medical records. All statistical analyses were performed using SPSS 22.0. Results: The study included 240 patients with a mean age of 49.3 ± 14.3 years; 87.1% of patients were women. The Random Forest model showed the best results: ROC-AUC of 0.803 ± 0.057, PR-AUC of 0.868 ± 0.044, Brier of 0.180 ± 0.017, sensitivity of 0.816, and specificity of 0.641. SHAP analysis confirmed that platelet count, age, INR, disease duration, and bilirubin and albumin levels made the greatest contribution to the prognosis. Conclusions: This retrospective observational study of AIH in Kazakhstan identified a patient population characterized by late diagnosis and advanced disease stages at presentation, a high frequency of overlapping autoimmune liver diseases, and a significant burden of metabolic and extrahepatic autoimmune comorbidities. The results demonstrate that an interpretable machine learning model based on routine biomarkers can effectively detect fibrosis and provide clinically interpretable risk factors.

Primary biliary cholangitis (PBC, formerly known as primary biliary cirrhosis) is one of the most significant diseases that is predominantly verified in women. The prevalence of PBC is 1.9-40.2 per 100,000 population. Antimitochondrial antibodies (AMA) are of major importance for the diagnosis of primary biliary cirrhosis (PBC), and it has also been suggested that they may be involved in the pathogenesis of the disease. Objective: The aim of this study was to characterize the clinical, biochemical parameters and response to UDCA (Paris I criteria) PBC patients depending on AMA status in the Republic of Kazakhstan. Material and methods. The study was conducted on the basis of the Research Institute of Cardiology and Internal Diseases from 2014 to 2019. A total of 212 patients with primary biliary cholangitis were recorded. Results. Among 212 patients, 171 (80.7%) were AMA-positive and 41(19,3%) - AMA-negative. Vast majority of patients in both groups were Asian (179; 84.4%) and female (206; 97.2%). Severe disease (F3/4) was revealed in 108 (63.2%) AMA-positive and in 18 (43.9 %) AMA-negative patients (p>0.05). AMA-positive and AMA-negative PBC were associated with autoimmune hepatitis in 88 (51.5%) and 10 (24.4%) cases (p0.05). Response to ursodeoxycholic acid (UDCA) treatment according to Paris I criteria was noted in 24 out of 81 (29.6%) AMA-positive and in 9 out of 22 (40.9%) AMA-negative patients (p>0.05). Conclusion. In patients with AMA-positive PBC compared with AMA-negative, there is a statistically significant high value of autoimmune hepatitis and autoimmune thyroiditis. Whereas, response to UDCA treatment according to Paris I criteria is higher in AMA-negative PBC.

Introduction: Direct-acting antiviral therapy achieves high cure rates in chronic hepatitis C; however, a minority of patients do not achieve a sustained virologic response. The aim of this study was to evaluate clinical, demographic, and virologic factors associated with failure to achieve a sustained virologic response among patients with chronic hepatitis C treated in the Turkestan Region of Kazakhstan. Methods: We performed a retrospective case-control study of 168 adults treated with direct-acting antivirals between January 2018 and December 2022. The control group comprised 126 patients who achieved a sustained virologic response, and the case group comprised 42 patients without a sustained virologic response. Demographic characteristics, disease duration, treatment duration, adherence, hepatitis C virus genotype, pretreatment alanine aminotransferase level, liver elastography, and fibrosis stage were analyzed. Results: Patients without a sustained virologic response had higher pretreatment alanine aminotransferase levels (p=0.03), higher liver stiffness values on elastography (p=0.007), and a longer duration of chronic hepatitis C before treatment (p<0.0001). Genotype 3 was more frequent among cases than controls (59.5% vs 24.6%; p<0.0001), and F4 fibrosis was also more common (40.5% vs 10.3%; p<0.0001). Treatment duration greater than 12 weeks (p=0.02) and lower treatment adherence (p<0.0001) were more frequent in the case group. Age, sex, ethnicity, and previous pegylated interferon/ribavirin therapy did not differ significantly between groups. Conclusion: Failure to achieve a sustained virologic response was associated with greater biochemical activity, more advanced liver fibrosis, longer disease duration, genotype 3 infection, and lower treatment adherence. Adherence represents a potentially modifiable factor that may be addressed through structured follow-up and patient counseling.

Background/Objectives: Autoimmune hepatitis (AIH) is a chronic immune-mediated liver disease that may progress to cirrhosis and liver failure if not diagnosed early. Although liver biopsy remains the reference standard for fibrosis assessment, its invasive nature limits routine use. This study aimed to compare the diagnostic performance of ultrasound-based microvascular imaging (MVI), transient elastography (TE), and serum fibrosis indices (APRI and FIB-4) in patients with biopsy-confirmed AIH. Methods: Fifty-five patients with probable or definite AIH according to IAIHG criteria were included in the study. All patients underwent liver biopsy, and fibrosis stage was assessed using the METAVIR system. TE and MVI examinations were performed, and APRI and FIB-4 scores were calculated. Diagnostic performance was evaluated using AUROC, sensitivity, and specificity. Spearman correlation and logistic regression analyses were additionally performed. Results: The mean age of the patients was 49.2 years, and most patients were women. Cirrhosis was present in 58.2% of the cohort. TE demonstrated high diagnostic accuracy, whereas FIB-4 showed moderate performance and APRI demonstrated limited utility. MVI achieved the highest diagnostic performance, with AUROC values of 0.99 for significant fibrosis and 0.97 for cirrhosis. MVI showed the strongest correlation with histological fibrosis stage (r = 0.916, p < 0.001), followed by TE (r = 0.907, p < 0.001). MVI was strongly associated with histologically confirmed cirrhosis (OR 16.7, 95% CI 2.36–118.2, p = 0.004). Conclusions: MVI demonstrates diagnostic performance comparable to TE and may represent a promising adjunctive non-invasive imaging biomarker for fibrosis assessment in AIH. Larger multicenter studies are required for external validation before routine clinical implementation.

Drug-induced liver injury (DILI) is one of the types of adverse reactions to drugs that occur as a result of their hepatotoxic effect. The pathogenesis of drug-induced autoimmune hepatitis (LIAH) is based on the production of autoantibodies to neoantigens, which are proteins of the cytochrome P450 system, which are the result of the reaction of drug metabolites. A clinically relevant problem, such as drug-induced liver damage, affects 1-1.5 million patients almost every year. The annual incidence of DILI ranges from 2.3-13.9 per 100,000 population in population studies from Europe. The Icelandic population study recorded the highest rates of 19.1 per 100,000 population per year. And in the only study based on the US population, it was found that DILI is approximately 3 per 100,000 population. Acute hepatitis is currently a well-known manifestation, and accounts for more than 90% of liver damage caused by medications. According to studies, 2.9 - 8.8% of DILI and 2 - 18% of AIH are associated with drug-induced autoimmune hepatitis. The incidence of drug-induced liver damage with the presence of antibodies (antibodies to nuclear antigen, smooth muscle and soluble liver antigen) to AIH is 83% for nitrofurantoin, 74% for minocycline, 60% for methyldopa and 43% for hydralazine.

Background: Autoimmune hepatitis (AIH) is a chronic immune-mediated liver disease that may progress to cirrhosis. This study aimed to develop and externally validate interpretable machine-learning models for the classification of prevalent cirrhosis in patients with AIH. Methods: The development cohort included 55 patients with biopsy-confirmed AIH. Cirrhosis was defined histologically as F4, whereas F0–F3 was classified as non-cirrhosis. Logistic Regression with L2 regularization, Random Forest, and XGBoost were evaluated. The original stratified 70/30 hold-out analysis was retained, and repeated stratified five-fold cross-validation with 20 repeats was additionally performed to assess internal stability. Primary external validation was performed in an independent histology-matched cohort of 42 patients. Models were applied without refitting, recalibration, or threshold optimization. Discrimination, probabilistic accuracy, calibration, and threshold-dependent classification metrics were evaluated. Results: In the original held-out test set, AUROC was 0.900 for Logistic Regression with L2 regularization, 0.830 for Random Forest, and 0.890 for XGBoost. In repeated cross-validation, mean AUROC was 0.878 ± 0.021, 0.914 ± 0.015, and 0.896 ± 0.015, respectively. In the primary external validation cohort, Random Forest showed the highest numerical discrimination (AUROC 0.810; 95% CI, 0.653–0.933), followed by XGBoost (0.728; 95% CI, 0.566–0.878) and Logistic Regression with L2 regularization (0.716; 95% CI, 0.545–0.875). Random Forest also had the lowest Brier score (0.188). However, confidence intervals were wide and overlapping. Elastography stage alone achieved an AUROC of 0.745, and the numerical improvement of the full Random Forest model was not statistically clear. Conclusions: Machine-learning models integrating routinely available clinical, biochemical, immunological, and elastography-related variables showed preliminary external transportability for the classification of prevalent cirrhosis in AIH. However, the small development and validation cohorts, uncertainty in calibration, and lack of a clearly demonstrated incremental advantage over elastography alone indicate that larger prospective multicenter studies are required before clinical implementation.