Researchers at Johns Hopkins Medicine have developed a new blood test that could help detect liver disease years before symptoms appear. The test uses artificial intelligence to analyze fragments of DNA circulating in the blood.
These fragments, known as cell-free DNA, can break apart in patterns that can reveal information about a person’s health. By studying these patterns across the entire genome, the AI system can identify early signs of liver fibrosis and cirrhosis.
The findings were published in Science Translational Medicine. Liver fibrosis occurs when scar tissue builds up in the liver. In the early stages, the condition can sometimes be reversed.
However, if the condition goes unnoticed, it can develop into cirrhosis, a more serious disease that increases the risk of liver failure and liver cancer.
“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,” Dr. Victor Velculescu, co-senior author of the study and a researcher at the Johns Hopkins Kimmel Cancer Center, said.
While most liquid biopsy tests search for specific genetic mutations, this new approach is different. Instead of looking for a single mutation, the test studies the overall pattern of DNA fragments across the genome.
“The fact that we are not looking for individual mutations is what makes this study so powerful,” Akshaya Annapragada, the study’s first author, said.
“We are analyzing the entire fragmentome, which contains a tremendous amount of information about a person’s physiologic state,” she said.
The research team analyzed blood samples from 1,576 people with liver disease and other health conditions. Whole genome sequencing and machine learning were used to examine about 40 million DNA fragments in each sample.
The AI system learned to recognize patterns linked to early liver disease.
The results showed the test could detect early liver fibrosis as well as advanced diseases, including cirrhosis.
Early detection is important because many people with liver disease do not realize they have it until serious damage has already occurred.
“Many individuals 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.”
The researchers also noticed that DNA fragmentation patterns may provide evidence about other conditions, including cardiovascular and inflammatory diseases. However, more research is needed before the test can be used to detect liver diseases.
The liver disease test remains a prototype and is not yet available for clinical use. The research team plans to continue testing and improving the system.
