Researchers at the Johns Hopkins Kimmel Cancer Center have developed an artificial intelligence (AI)-driven liquid biopsy approach that may enable earlier detection of liver fibrosis and cirrhosis, while also identifying signals associated with broader chronic disease conditions. The findings, published on March 4 in Science Translational Medicine, highlight how advanced genomic analysis combined with machine learning could expand the clinical use of liquid biopsies beyond cancer detection to chronic disease monitoring.
The study introduces a novel AI-based test that analyzes genome-wide patterns of cell-free DNA (cfDNA) fragmentation circulating in the bloodstream. By evaluating how DNA fragments are distributed and structured across the genome, researchers were able to identify patterns associated with early liver fibrosis and advanced cirrhosis. Unlike traditional approaches that focus on identifying specific genetic mutations, this method evaluates large-scale fragmentomic signatures, enabling the detection of disease-related physiological changes across the entire genome.
To develop the model, researchers analyzed whole-genome sequencing data from cfDNA samples collected from 1,576 individuals with liver disease and related health conditions. Each sample generated tens of millions of DNA fragments spanning thousands of genomic regions. Machine-learning algorithms then processed this large dataset to identify disease-specific fragmentation patterns and classify individuals based on their likelihood of having early-stage liver disease, advanced fibrosis or cirrhosis.
“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 Johns Hopkins Kimmel 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.”
Also Read: Cortical Labs Introduces CL1, the World’s First Code-Deployable Biological Computer
The fragmentome-based approach examines how DNA fragments are cut, packaged and distributed across the genome. According to the research team, this broader analysis enables the identification of physiological changes that extend beyond cancer mutations and may indicate other underlying health conditions. The study was co-led by Robert Scharpf, Ph.D., professor of oncology, and Jill Phallen, Ph.D., assistant professor of oncology.
“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.”
Liver disease remains a major public health challenge, with an estimated 100 million people in the United States living with conditions that increase their risk of cirrhosis and liver cancer. Existing diagnostic tools often struggle to detect early fibrosis, while imaging technologies such as ultrasound or MRI may not always be readily accessible. The AI-powered liquid biopsy could offer a more scalable, non-invasive method for identifying patients at risk before the disease progresses to more severe stages.
Beyond liver disease, the researchers also observed fragmentomic signals associated with other chronic conditions, including cardiovascular, inflammatory and neurodegenerative diseases. While the current study did not include enough data to build separate classifiers for each condition, the results suggest the underlying platform could potentially support broader disease detection capabilities in future research.
The researchers noted that the liver fibrosis assay described in the study remains a prototype and is not yet available as a clinical diagnostic test. Future work will focus on further validating the technology and expanding its ability to detect additional chronic diseases through fragmentome-based biomarkers.
Source: Johns Hopkins
