Researchers have validated an AI-powered blood test that accurately detected liver cancer in people from geographically and biologically distinct populations. 

The findings build on the development of the DELFI (DNA Evaluation of Fragments for Early Interception) liquid biopsy platform, which analyzes fragments of DNA in the bloodstream. 

Liver cancer is one of the leading causes of cancer deaths worldwide, and its incidence is rising due to increasing rates of metabolic liver disease and other risk factors. Detecting the cancer early dramatically improves treatment options, but current screening methods can miss many early cancers. 

Researchers analyzed blood samples from 377 people from Guatemala and Romania to ensure that the approach could reliably detect liver cancer in people with different biological and geographical backgrounds, accounting for different causes of the disease. The blood test was able to consistently detect liver cancers across both populations. 

The researchers were also able to identify molecular signatures that differed between the populations. This suggests that genome-wide fragmentome analysis captures universal biological features of liver cancer and region-specific molecular changes, which hypothetically makes it adapatable to diverse patient populations worldwide.