Artificial intelligence in metabolic dysfunction-associated steatotic liver disease: Machine learning for non-invasive diagnosis and risk stratification

Core Tip

Core Tip: Artificial intelligence (AI), machine learning and deep learning, holds transformative potential for the non-invasive diagnosis and risk stratification of metabolic dysfunction-associated steatotic liver disease (MASLD). These AI models utilize readily available clinical data, biomarkers, and imaging modalities (ultrasound, computed tomography, magnetic resonance imaging) to detect steatosis, predict disease risk, and stage fibrosis with greater accuracy than conventional scoring systems such as fibrosis-4. Despite their promising performance, several challenges hinder widespread clinical adoption, including the need for data standardization, rigorous prospective validation, model interpretability, and seamless integration into existing healthcare workflows. Overcoming these barriers is essential to fully harness AI potential in improving MASLD diagnosis and management.