Johns Hopkins Detects Liver Disease Using Fragmentome

Researchers at Johns Hopkins Kimmel Cancer Center report March 4 in Science Translational Medicine that an AI-based liquid biopsy analyzing genome-wide cell-free DNA fragmentation patterns and repeat landscapes detected early liver fibrosis and cirrhosis in a study of 1,576 people. The team analyzed roughly 40 million fragments per sample and trained machine-learning classifiers to identify disease-specific signatures; the assay is a prototype requiring further validation before clinical use.