Blood + AI = diagnosis
The DELFI blood test (DNA evaluation of fragments for early interception, evaluation of DNA fragments for early interception) detects fragments of cancer DNA circulating in the bloodstream. The researchers tested the DELFI technology on blood plasma samples obtained from 724 volunteers from the United States, the European Union and Hong Kong belonging to different racial and ethnic groups to detect hepatocellular cancer (HCC) – a type of liver cancer.
According to the American Cancer Society, liver cancer is diagnosed in more than 800,000 people worldwide every year, and it is the leading cause of cancer deaths worldwide. 400 million people are at high risk of developing HCC due to cirrhosis as a result of chronic liver diseases, including chronic viral hepatitis and non-alcoholic fatty hepatosis.
Earlier detection of HCR significantly improves the prognosis of the disease, but currently available screening tests are not used enough and cancer is missed.
Of the 724 plasma samples studied, 501 were collected in the United States and the European Union and included samples from 75 people with GCR for training and testing a machine learning model – artificial intelligence that uses data and algorithms to improve accuracy. For verification, an additional 223 plasma samples taken from people in Hong Kong were analyzed and included samples from 90 people with HCC, 66 with hepatitis B virus (HBV), 35 with liver cirrhosis associated with HBV, and 32 people without major risk factors.
DELFI technology determines the size and number of extracellular DNA fragments present in the bloodstream, and based on these data, evaluates the packaging of DNA inside cells. Healthy cells compactly pack DNA like a well-packed suitcase, in which different regions of the genome are neatly placed in different compartments. The nuclei of cancer cells, on the contrary, are more like suitcases, in which regions from all over the genome are randomly scattered. When cancer cells die, they randomly release DNA fragments into the bloodstream. According to them, DELFI determines the presence of cancer. The approach requires sequencing with low coverage, which makes this technology cost-effective in screening conditions.
In a previous study, the group successfully tested DELFI to detect lung cancer from fragments of extracellular cancer DNA.
With a total sensitivity of 88% and specificity of 98%, DELFI detects liver cancer at the earliest stages. In samples taken from individuals at high risk of HCR, the test had a sensitivity of 85% and a specificity of 80%.
The next step is to test this approach in larger studies for clinical use.
Currently, less than 20% of the high-risk population is screened for liver cancer due to the low availability and suboptimal effectiveness of tests. If successful, a new blood test can double the number of detected cases of liver cancer compared to a standard blood test, including at an early stage of the disease.
Article by Z.H.Foda et al. Detecting liver cancer using cell-free DNA fragments is published in the journal Cancer Discovery.
Aminat Adzhieva, portal "Eternal Youth" http://vechnayamolodost.ru based on Johns Hopkins University: Novel AI Blood Test Detects Liver Cancer.