In Clinical and molecular hepatology
Inflammation is the key driver of liver fibrosis progression in nonalcoholic fatty liver disease (NAFLD). Unfortunately, it is often challenging to assess inflammation in NAFLD due to its dynamic nature and poor correlation with liver biochemical markers. Liver histology keeps its role as the standard tool, yet it is well-known for substantial sampling, intraobserver and interobserver variability. Serum proinflammatory cytokines and apoptotic markers namely cytokeratin-18 (CK-18) are well studied with reasonable accuracy; whereas serum metabolomics and lipidomics have been adopted in some commercially available diagnostic models. Ultrasound and computed tomography (CT) imaging techniques are attractive because of their wide availability; yet their accuracies may not be comparable with magnetic resonance imaging (MRI)-based tools. Machine learning and deep learning models, be they supervised or unsupervised learning, are promising tools to identify various subtypes of NAFLD, including those with dominating liver inflammation, contributing to sustainable care pathways for NAFLD.
Yip Terry Cheuk-Fung, Lyu Fei, Lin Huapeng, Li Guanlin, Yuen Pong-Chi, Wong Vincent Wai-Sun, Wong Grace Lai-Hung
2022-Dec-12
Cytokeratin-18, deep learning, fatty liver, hepatic steatosis, liver cancer, machine learning, necroinflammation
