Related Experiment Video
Updated: Apr 15, 2026
Author Spotlight: Investigating Immune Cell Dynamics in the Tumor Microenvironment — Challenges and Innovations in Cancer Prognosis
Published on: April 12, 2024
Use of Machine Learning in Predicting the Risk of Cirrhosis in Autoimmune Hepatitis Based on Clinical and
Nazugum Ashimova1,2, Aigul Raissova1,2, Elmira Kuantay1,2
1Department of Gastroenterology, Asfendiyarov Kazakh National Medical University, Almaty 050012, Kazakhstan.
Insights
Autoimmune hepatitis (AIH) in Kazakhstan often presents late, with women disproportionately affected. Machine learning models using routine biomarkers can effectively detect liver fibrosis in AIH patients.
Area of Science:
- Hepatology
- Immunology
- Data Science
Background:
- Autoimmune hepatitis (AIH) is a chronic liver disease with limited data from Central Asia.
- Prompt diagnosis and treatment are crucial to prevent cirrhosis and liver failure.
Purpose of the Study:
- Characterize the clinical profile of AIH in a Kazakhstani cohort.
- Assess the timeliness of AIH diagnosis.
- Develop a machine learning model for liver fibrosis detection using routine parameters.
Main Methods:
- Retrospective observational study of 240 adult AIH patients (2015-2025).
- Data collection included demographic, laboratory, instrumental, and histological information.
- Random Forest and SHAP analyses were employed for model development and interpretation.
Main Results:
- The cohort comprised 87.1% women with a mean age of 49.3 years.
- The Random Forest model achieved an ROC-AUC of 0.803, demonstrating good predictive performance for fibrosis.
- Key predictors for fibrosis included platelet count, age, INR, disease duration, bilirubin, and albumin levels.
Conclusions:
- Kazakhstani AIH patients frequently present with late diagnoses and advanced disease.
- High rates of overlapping autoimmune liver diseases and comorbidities were observed.
- Interpretable machine learning models using routine biomarkers show promise for fibrosis detection and risk factor identification in AIH.
Abstract:
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.
