Liver disease is a growing health problem around the world, yet many people who develop it do not know they are sick until the disease has already become serious. Conditions such as liver fibrosis and cirrhosis often develop slowly and quietly.
In the early stages, people may feel normal and show few symptoms. By the time clear signs appear, the liver may already be badly damaged. Because of this, scientists have been searching for better ways to detect liver disease earlier.
A new study from researchers at the Johns Hopkins Kimmel Cancer Center suggests that artificial intelligence could help doctors identify early liver disease through a simple blood test. The findings were published in the scientific journal Science Translational Medicine.
The researchers believe this new approach could eventually help doctors detect liver damage long before it becomes life‑threatening.
The new test is based on a type of technology known as a liquid biopsy. Unlike traditional biopsies, which require doctors to remove a small piece of tissue from the body, a liquid biopsy uses a blood sample. Blood contains small fragments of DNA that are released when cells die. These pieces of DNA float in the bloodstream and are known as cell‑free DNA.
Scientists have already used liquid biopsy techniques to detect cancer. Tumor cells release DNA into the blood, and researchers can sometimes identify cancer by studying these fragments. However, until now, most liquid biopsy research has focused mainly on cancer. Very little work has explored whether the same idea could help detect other diseases.
The new study looked at something scientists call the “fragmentome.” Instead of searching for specific gene mutations, the fragmentome examines how pieces of DNA are broken and distributed across the genome. These patterns may reveal information about what is happening inside the body.
When cells release DNA into the bloodstream, the DNA fragments vary in size and location. The way these fragments are cut and arranged can change depending on the type of disease affecting the body. By studying these patterns, researchers may be able to detect health problems even when no obvious genetic mutations are present.
To explore this idea, the research team collected blood samples from 1,576 people who had liver disease or other health conditions. They used whole‑genome sequencing, a powerful technology that reads DNA across the entire genome. This allowed them to analyze DNA fragments from thousands of different regions.
In each sample, the researchers examined roughly 40 million DNA fragments. This amount of data is far larger than what most liquid biopsy tests analyze. The scientists looked at the size of each fragment and how fragments were spread across the genome. They also examined repetitive DNA regions that are often ignored in other types of genetic testing.
Because the data were extremely complex, the researchers used machine learning to help analyze it. Machine learning is a form of artificial intelligence that allows computers to recognize patterns in large datasets. The AI system studied the fragment patterns and learned to identify signatures linked to different stages of liver disease.
The results showed that the AI‑based system could detect early liver fibrosis as well as more advanced disease such as cirrhosis. Liver fibrosis occurs when repeated injury to the liver causes scar tissue to form.
In the early stages, this damage can sometimes be reversed if the underlying cause is treated. However, if fibrosis continues to worsen, it can develop into cirrhosis, a severe form of liver scarring that can eventually lead to liver failure or liver cancer.
Detecting fibrosis early is therefore extremely important. Unfortunately, current blood tests often fail to identify early fibrosis. Imaging tests such as specialized ultrasound or MRI scans can sometimes detect the condition, but these tools require expensive equipment and trained specialists, which may not be available in all healthcare settings.
The researchers believe the fragmentome test could offer a simpler and more accessible option. Because it uses only a blood sample, it could potentially be used in routine medical care to screen people who may be at risk for liver disease.
The study also found that the DNA fragmentation patterns contained information about other health problems. In some participants, the AI system detected signals linked to cardiovascular disease, inflammation, and neurodegenerative conditions.
Although the study did not include enough patients to create specific diagnostic tests for all these diseases, the results suggest that the fragmentome may provide a broader picture of a person’s overall health.
The research team also developed a measure called a fragmentation comorbidity index. This index was able to distinguish people with higher levels of illness from those with fewer health problems. In some cases, it predicted survival outcomes even better than traditional markers of inflammation.
Despite the promising results, the researchers emphasize that the test is still in an early stage of development. The current version is considered a prototype and is not yet ready for routine clinical use. Larger studies will be needed to confirm that the method works reliably across different populations and healthcare settings.
Study analysis and interpretation: This study is significant because it shows that liquid biopsy technology may be useful for detecting diseases beyond cancer. By analyzing genome‑wide DNA fragmentation patterns, researchers were able to identify signals of liver fibrosis and cirrhosis using only a blood sample.
The large amount of data analyzed and the use of machine learning strengthen the findings. However, because the test is still experimental, more research will be necessary to confirm its accuracy and determine how it could be used in real‑world medical practice.
If validated, this approach could transform early disease detection by providing doctors with a simple tool to identify hidden health problems long before symptoms appear.
If you care about liver health, please read studies that refined fiber is link to liver cancer, and the best and worst foods for liver health.
For more health information, please see recent studies about how to boost your liver naturally, and simple ways to detox your liver.
The research findings were published in Science Translational Medicine.
Copyright © 2026 Knowridge Science Report. All rights reserved.
