Abstract            Volume:14  Issue-7  Year-2026         Original Research Articles

Online ISSN : 2347 - 3215 Issues : 12 per year Publisher : Excellent Publishers Email : editorijcret@gmail.com

Liver cirrhosis and hepatic abscess are major causes of global morbidity and mortality, posing significant challenges in early diagnosis and clinical management due to their heterogeneous presentation and progressive nature. Conventional diagnostic approaches, including biochemical investigations, imaging modalities, and histopathological examination, are effective but are often limited by invasiveness, inter-observer variability, delayed detection, and reduced diagnostic accuracy during the early stages of disease. Recent advances in artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL), have transformed the landscape of hepatology by enabling automated, accurate, and non-invasive diagnosis of liver diseases. This review comprehensively examines the epidemiology, pathophysiology, and conventional diagnostic strategies for liver cirrhosis and hepatic abscess while highlighting the emerging role of ML-based predictive models in improving disease detection and clinical decision-making. The review discusses widely used supervised learning algorithms, including Logistic Regression, Support Vector Machine, Random Forest, Decision Tree, Extreme Gradient Boosting (XGBoost), Artificial Neural Networks, and ensemble learning techniques, alongside deep learning architectures such as Convolutional Neural Networks for liver image analysis. Furthermore, the importance of medical imaging, radiomics, data preprocessing, feature selection, model optimization, performance evaluation, explainable artificial intelligence (XAI), and external clinical validation is critically evaluated. Current challenges, including limited multicenter datasets, model interpretability, algorithmic bias, ethical concerns, and regulatory issues, are also discussed. The review concludes that integrating machine learning with multimodal clinical, laboratory, and imaging data has the potential to significantly enhance early diagnosis, prognostic assessment, and personalized management of hepatic diseases. Future research should prioritize explainable, clinically validated, and ethically governed AI frameworks to facilitate their safe translation into routine hepatology practice and precision medicine.

Download this article as