In a new study involving 724 participants, a breakthrough artificial intelligence blood testing technique created and used by researchers at the Johns Hopkins Kimmel Cancer Center to successfully detect lung cancer in a 2021 study has now detected more than 80% of liver malignancies.

The blood test, known as DELFI (DNA evaluation of fragments for early interception), finds differences in DNA fragmentation among cell-free DNA, or DNA from cancer cells shed into the bloodstream (cfDNA). In the most recent study, researchers employed the DELFI technology to identify hepatocellular carcinoma (HCC), a kind of liver cancer, in blood plasma samples taken from 724 people in the U.S., the European Union (E.U.), and Hong Kong.

This analysis of genome-wide fragmentation, according to the researchers, is the first one that has been independently validated in two high-risk populations and across several racial and ethnic groups with various causes of liver cancer.

Representative Image

Their research was presented on November 18 at the American Association for Cancer Research Special Conference: Precision Prevention, Early Detection, and Interception of Cancer as well as in the journal Cancer Discovery.

According to a global review of the burden of liver disease, 400 million persons globally are thought to be at an increased risk of developing HCC due to cirrhosis from chronic liver illnesses such as chronic viral hepatitis or non-alcoholic fatty liver disease (J. Hepatology, 2019).

According to Victor Velculescu, M.D., Ph.D., professor of oncology and co-director of the Cancer Genetics and Epigenetics Program at the Johns Hopkins Kimmel Cancer Center, who co-led the study with Zachariah Foda, M.D., Ph.D., gastroenterology fellow, Akshaya Annapragada, M.D./Ph.D. student, and Amy Kim, M.D., assistant professor of medicine

To train and validate the machine learning model, a sort of artificial intelligence that uses data and algorithms to increase accuracy, Foda adds that out of the 724 plasma samples examined, 501 were obtained in the U.S. and E.U. and included samples from 75 persons with HCC. Additional 223 plasma samples from persons in Hong Kong were examined for validation; these samples came from 90 people with HCC, 66 with hepatitis B virus (HBV), 35 with HBV-related liver cirrhosis, and 32 without any known risk factors.

The DELFI technology analyzes the size and quantity of cell-free DNA present in the circulation from various areas of the genome to measure the way DNA is packaged inside the nucleus of a cell using a blood test. DNA is packaged by healthy cells like a well-organized suitcase, with distinct parts of the genome packed with care in discrete compartments. In contrast, the nuclei of cancer cells are like more jumbled luggage, with pieces of the DNA thrown in randomly. Cancer cells expel bits of DNA into the circulation as they decompose.

Credit: wildpixel/Getty Images

Millions of cfDNA fragments are examined by DELFI for aberrant patterns, including the size and quantity of DNA in various genomic areas, in order to detect the existence of cancer. According to the researchers, the DELFI technique only needs low-coverage sequencing, making this technology economical in a screening environment.

The technique, which has previously been demonstrated to accurately diagnose lung cancer, was used in the most recent investigation on cfDNA fragments isolated from plasma samples. To create a DELFI score, they examined the fragmentation patterns present in each sample.

The median DELFI score for cancer-free individuals with viral hepatitis or cirrhosis was 0.078, and for those with cirrhosis, it was 0.080. However, the 75 HCC patients in the U.S./E.U. samples had scores that were on average 5 to 10 times higher, with high scores seen in all cancer stages, including early-stage disease (DELFI scores for Stage 0 = 0.46, Stage A = 0.61, Stage B = 0. The test also identified significant alterations in the content and packing of genomes from liver cancer, particularly those from areas linked to liver-specific activity.

With an overall sensitivity of 88% and a specificity of 98%, which means it virtually never wrongly delivered a false positive result, the DELFI technique discovered liver tumors at their early stages in individuals at average risk. The test had an 85% sensitivity and an 80% specificity in samples taken from individuals with a high risk of developing HCC.

Currently, less than 20% of the high-risk population get screened for liver cancer due to accessibility and suboptimal test performance. This new blood test can double the number of liver cancer cases detected, compared to the standard blood test available, and increase early cancer detection.” Amy Kim, M.D., assistant professor of medicine at the Johns Hopkins University School of Medicine, co-senior author on the study

The next step, according to the researchers, is to validate this strategy in larger studies for clinical application.

According to the American Cancer Society, liver cancer is a primary cause of cancer deaths globally, with more than 800,000 people being diagnosed with it each year.