AI-Powered Liquid Biopsy Detects Early Liver Disease and Signals of Chronic Illness

Researchers at the Johns Hopkins Kimmel Cancer Center have developed an artificial intelligence (AI)-based liquid biopsy test that can detect early liver fibrosis and cirrhosis, and may also reveal signals of broader chronic disease burden. The test utilizes genome-wide cell-free DNA (cfDNA) fragmentation patterns and repeat landscapes, representing a significant advancement in non-invasive disease detection.

A Novel Approach to Liquid Biopsies

Published on March 4, 2026, in Science Translational Medicine, the findings mark the first time this “fragmentome” technology – initially studied in cancer detection – has been systematically applied to chronic noncancer conditions. Johns Hopkins Kimmel Cancer Center investigators used whole-genome sequencing to analyze cfDNA fragmentomes from 1,576 individuals with liver disease and other comorbidities.

The analysis examined fragment size and distribution across the genome, including previously uncharacterized repetitive regions, to identify disease indicators. Roughly 40 million fragments spanning thousands of genomic regions were evaluated in each analysis – a scale exceeding that of most other liquid biopsy tests. Machine-learning algorithms were then employed to identify disease-specific fragmentation signatures.

How the Technology Works

“This builds directly on our earlier fragmentome work in cancer, but now using AI and genome-wide fragmentation profiles of cell-free DNA to focus on chronic diseases,” says Victor Velculescu, M.D., Ph.D., co-director of the cancer genetics and epigenetics program at the Sidney Kimmel Comprehensive Cancer Center and co-senior author of the study. “For many of these illnesses, early detection could make a profound difference, and liver fibrosis and cirrhosis are important examples. Liver fibrosis is reversible in early its stages, but if left undetected, it can progress to cirrhosis and ultimately increase the risk of liver cancer.”

Unlike liquid biopsies that search for cancer-related gene mutations, the fragmentome analyzes how DNA pieces are cut, packaged, and distributed across the genome. This approach is applicable to a wider range of diseases, including those that can eventually lead to cancer development.

“The fact that we are not looking for individual mutations is what makes this study so powerful,” says first author Akshaya Annapragada, an M.D./Ph.D. Student working in the Velculescu lab. “We are analyzing the entire fragmentome, which contains a tremendous amount of information about a person’s physiologic state. The scale of these data, coupled with machine learning, enables development of specific classifiers for many different health conditions.”

Impact and Future Directions

An estimated 100 million people in the United States have liver conditions that increase their risk for cirrhosis and cancer, according to Velculescu. However, existing blood-based markers for fibrosis have limited sensitivity, particularly in early disease stages. Current blood testing often misses early fibrosis, and imaging tools like ultrasound or MRI may not be readily accessible to all patients.

“Many individuals at risk don’t realize they have liver disease,” Velculescu says. “If we can intervene earlier – before fibrosis progresses to cirrhosis or cancer – the impact could be substantial.”

The study also developed a fragmentation comorbidity index that distinguished individuals with high versus low Charlson Comorbidity Index scores, a tool used to estimate how other health conditions may affect a person’s risk for death. This index independently predicted overall survival and, in some cases, proved more specific than traditional inflammatory markers.

Researchers also detected fragmentomic signals associated with cardiovascular, inflammatory, and neurodegenerative conditions, suggesting broader applicability of the technology. However, they note that further research is needed to develop disease-specific classifiers for these conditions.

Current Status and Next Steps

The liver fibrosis assay described in the study is currently a prototype and not yet available as a clinical test. The research team plans to continue developing and validating the liver disease classifier and explore fragmentome signatures in additional chronic conditions. The origins of the study trace back to a 2023 liver cancer fragmentome study, where subtle disease-related changes were observed in individuals with fibrosis or cirrhosis.