AI-Powered Blood Test Detects Liver Cancer Across Diverse International Populations

AI-Powered Blood Test Validates Liver Cancer Detection Across Populations

Researchers at Johns Hopkins Kimmel Cancer Center validated an AI-powered blood test that accurately detects liver cancer in people from two geographically and biologically distinct populations while uncovering the underlying biological signals that make the test effective1

1

2

2

. Published July 31 in Cell Press Blue, the findings build on the team's earlier development of the DELFI (DNA Evaluation of Fragments for Early Interception) liquid biopsy platform, which analyzes millions of fragments of cell-free DNA circulating in the bloodstream1

1

. This study validates a previously developed liver cancer classifier in independent high-risk populations and provides new insights into the biology behind its performance.

Study Design Encompasses Diverse International Populations

Investigators analyzed blood samples from 377 people from Guatemala and Romania, with and without hepatocellular carcinoma, the most common form of liver cancer2

2

. The two populations represent markedly different causes of liver cancer. Most participants in Romania developed liver disease related to viral hepatitis or alcohol use, while participants in Guatemala primarily had metabolic liver disease, obesity and diabetes, with many also exposed to aflatoxin, a naturally occurring toxin linked to liver cancer1

1

. Study co-author John Groopman, Ph.D., Anna M. Baetjer Professor at Johns Hopkins Bloomberg School of Public Health, is a leading expert on the role of aflatoxins in initiating liver cancer.

AI-Driven Blood Tests Outperform Traditional Methods

Despite differences between populations, the blood test consistently detects liver cancer across both groups2

2

. When combined with AFP protein tests and simple clinical risk factors such as age and sex, the approach identified early- and late-stage cancers with greater sensitivity than existing blood testing alone1

1

. This represents a significant advance for noninvasive cancer screening, as current methods relying primarily on ultrasound imaging and the blood protein alpha-fetoprotein can miss many early cancers.

MethID Method Reveals Biological Signals Beyond Tumor Cells

Using a newly developed method for tracing where DNA fragments originate, called MethID, the team showed that the DELFI test works because it captures more than signals from tumor cells2

2

. It also captures signals from liver cells, blood vessels and immune cells responding to the cancer. "As a result, these DNA fragments contain much more information than whether cancer is present," says Zachariah Foda, M.D., Ph.D., assistant professor of medicine at Johns Hopkins University School of Medicine and co-senior author of the study1

1

. "It tells us where these fragments originate and how they change during cancer development, allowing us to better understand the biology of the disease and improve our ability to detect it."

Molecular Signatures Differ Yet Classifier Remains Effective

The researchers identified molecular signatures that differed between populations2

2

. For example, they detected a distinctive mutation pattern across the genome associated with aflatoxin exposure in participants from Guatemala, but they also showed that the overall fragmentome classifier remained effective regardless of the underlying cause of liver cancer1

1

. The study suggests that genome-wide fragmentome analysis captures both universal biological features of liver cancer and region-specific molecular changes, making it adaptable to diverse patient populations around the world.

Early Cancer Detection Advances Broader Vision for Global Health

"Our earlier studies showed that fragmentome analyses could detect liver cancer and, more recently, chronic liver diseases that increase cancer risk," says Victor Velculescu, M.D., Ph.D., the Cancer Genetics and Epigenetics Professor, co-director of the cancer genetics and epigenetics program, and co-senior author of the study2

2

. "This study demonstrates that the approach works with high performance across different patient populations while revealing the biological signals in the bloodstream that make this type of detection possible." This study also advances research from March 2026, in which the researchers demonstrated that a similar genome-wide fragmentome technology could detect liver fibrosis and cirrhosis, conditions that often precede liver cancer1

1

.

Platform Technology Extends to Lung Cancer Detection

The findings extend the researchers' broader vision for fragmentome technology, suggesting that genome-wide analysis of cell-free DNA could ultimately provide a foundation for noninvasive blood tests capable of detecting multiple diseases using a common technology platform2

2

. As an example, Velculescu and colleagues working with DELFI Diagnostics recently reported the clinical validation of a blood test for lung cancer detection, called FirstLook Lung1

1

. Liver cancer is one of the leading causes of cancer deaths worldwide, and its incidence continues to rise because of increasing rates of metabolic liver disease and other risk factors, making early detection critical for improving treatment options.