AI-Powered Blood Test Detects Liver Cancer Across Diverse Populations: Cell | July 2026

Researchers at Johns Hopkins have validated an AI-powered DELFI liquid biopsy that accurately detected hepatocellular carcinoma (HCC) in geographically and biologically distinct high-risk populations.

Key findings:

✅ Successfully detected HCC in patients from Romania (viral hepatitis/alcohol-related liver disease) and Guatemala (MASLD, obesity, diabetes, aflatoxin exposure).

✅ Combining DELFI + AFP + simple clinical factors (age and sex) improved detection of both early- and late-stage HCC.

✅ The AI analyzes cell-free DNA fragment patterns (fragmentomics), capturing signals not only from tumor cells but also from surrounding liver tissue, blood vessels, and immune cells.

✅ The approach may provide a universal, noninvasive platform for early cancer detection across diverse populations.

💡 Take-home message: AI-driven fragmentomics is moving liquid biopsy beyond mutation detection. By integrating genome-wide DNA fragmentation patterns with clinical data, it has the potential to transform early HCC screening, particularly in high-risk populations where timely diagnosis can save lives.