Researchers at Johns Hopkins Kimmel Cancer Center have developed an innovative liquid biopsy test that uses AI to detect early liver fibrosis and cirrhosis. Unlike traditional tests that focus on specific genetic mutations, this approach examines cell-free DNA (cfDNA) fragmentation patterns across the genome, revealing subtle signs of liver disease (and potentially other chronic conditions) much earlier than conventional methods.

Published in Scientific translational medicineThis study marks the first systematic use of fragmentome technology to identify chronic non-cancerous diseases. This work opens the door to a new era of liquid biopsies, where a simple blood sample could provide detailed information about a person’s overall health, risk of disease progression, and even early warning signs of conditions that currently go undetected.

From cancer to chronic disease

The origins of this study date back to 2023, when Victor Velculescuco-director of the Cancer Genetics and Epigenetics Program at the Johns Hopkins Kimmel Cancer Center, and his team were Analysis of liver cancer fragmentomes.. They noticed that individuals with fibrosis or cirrhosis had fragmentation profiles that appeared largely normal but showed subtle signs of early disease. This prompted research focused on fragmentation patterns specific to liver fibrosis and cirrhosis, laying the foundation for the current study.

Using this information, the researchers first tested a cohort of 570 patients with suspected severe disease to develop a fragmentation comorbidity index. This index distinguished individuals with high or low scores on the Charlson Comorbidity Index (a common measure of overall health burden) and independently predicted overall survival. In some cases, it was even more specific than traditional inflammatory markers.

“The fragmentome can serve as a basis for building different classifiers for different diseases, and more importantly, these classifiers are disease-specific and do not cross-react.” Akshaya Annapragadafirst author of the study and a doctoral student working in Velculescu’s laboratory, explained in the Press release. “A liver fibrosis classifier is different from a cancer classifier. It is a unique, disease-specific test built on the same underlying platform.”

Encouraged by these early results, the team expanded their focus to a larger study of 1,576 people with liver disease and other comorbidities. Using whole genome sequencing, they analyzed millions of cfDNA fragments across thousands of genomic regions. The researchers examined the size, distribution and patterns of fragments in repetitive regions of the genome that had been little explored previously. Each analysis evaluated approximately 40 million DNA fragments, generating a data set much larger than that of most liquid biopsy tests.

Using machine learning algorithms, the team identified disease-specific fragmentation signatures, enabling highly sensitive detection of early liver disease, advanced fibrosis and cirrhosis.

“This builds directly on our previous work on fragmentomes in cancer,” Velculescu said. “For many of these diseases, early detection could make a profound difference, and liver fibrosis and cirrhosis are important examples. Liver fibrosis is reversible in its early stages, but if left undetected, it can progress to cirrhosis and ultimately increase the risk of liver cancer.”

How fragmentomics works

Fragmentomics is an emerging field that studies the patterns of circulating cfDNA fragments found in the bloodstream. These fragments originate from dying cells throughout the body, which release DNA fragments into the circulation. Instead of remaining intact, this DNA is often highly fragmented, producing characteristic size distributions and genomic patterns that can provide clues about where the DNA comes from and what biological processes are occurring in the body.

The term fragmentomics refers to the analysis of the entire collection of these fragments, known as a fragmentome, to understand their structure, origin, and biological function. In the case of cfDNA, researchers examine not only the DNA sequence but also features such as fragment length, endpoints, and how the fragments are distributed throughout the genome. Together, these features create complex signatures that reflect cellular activity, tissue damage, or pathological processes.

“The fact that we are not looking for individual mutations is what makes this study so powerful,” Annapragada said. “We are analyzing the entire fragmentome, which contains an enormous amount of information about a person’s physiological state. The scale of this data, together with machine learning, allows the development of specific classifiers for many different health conditions.”

Address a major health gap

In the United States, an estimated 100 million people suffer from liver diseases, putting them at high risk of cirrhosis and cancer. Existing blood markers often fail to detect early fibrosis, and imaging tools such as ultrasound or MRI may not be accessible to all patients.

“Many people at risk don’t know they have liver disease,” Velculescu said. “If we can intervene earlier, before fibrosis progresses to cirrhosis or cancer, the impact could be substantial.” Early detection of precursor diseases could also allow doctors to treat underlying health problems, potentially preventing cancer development altogether.

While the study focused primarily on liver disease, the researchers also detected fragmentomic signals associated with cardiovascular, inflammatory, and neurodegenerative conditions. Although the current cohort size was insufficient to develop classifiers for each of these diseases, the findings suggest broader applicability of cfDNA fragmentomics in the detection of chronic diseases.

A promising future for liquid biopsies

The researchers emphasized that the liver fibrosis assay described in the study is still a prototype and not yet ready for clinical use. Future work will focus on refining and validating the liver disease classifier in larger patient populations, as well as exploring fragmentomic signatures associated with other chronic diseases.

Ultimately, this approach could support a new generation of liquid biopsies for multiple diseases, capable of detecting early physiological changes in a wide range of conditions. Because fragmentomic patterns reflect the biological state of tissues throughout the body, a single blood test could reveal signs of inflammation, organ damage, or disease progression long before symptoms appear.

If validated in larger studies, fragmentomics combined with machine learning could transform the way doctors detect and monitor diseases, shifting medicine toward earlier intervention and more proactive care. For conditions like liver fibrosis, where early-stage disease is often silent but still reversible, that change could make a critical difference for millions of patients.