Researchers at Johns Hopkins Kimmel Cancer Center [Source] have achieved remarkable success in detecting liver cancer using a groundbreaking artificial intelligence (AI) blood testing technology. Following their previous study in 2021, which showcased the test's ability to detect lung cancer, the researchers have now reported that the test, known as DELFI (DNA evaluation of fragments for early interception), successfully detected more than 80% of liver cancers in a new study involving 724 participants.
The DELFI blood test identifies fragmentation changes in cell-free DNA (cfDNA), which are DNA fragments shed into the bloodstream by cancer cells. In the new study, the researchers used the DELFI technology to identify hepatocellular carcinoma (HCC), a common kind of liver cancer, in blood plasma samples collected from people in the United States, Hong Kong, and the European Union (EU).
The researchers consider this study as the first-ever genome-wide fragmentation analysis independently validated in two high-risk populations, spanning different racial and ethnic groups with varying causes associated with their liver cancers. At the American Association for Cancer Research Special Conference: Precision Prevention, Early Detection, and Interception of Cancer on November 18, the findings were presented.
According to a global analysis of the burden of liver disease, an estimated 400 million people worldwide are at higher risk of developing HCC due to cirrhosis from chronic liver disorders, such as non-alcoholic fatty liver disease or chronic viral hepatitis (J. Hepatology, 2019).
Dr. Victor Velculescu, professor of oncology and co-director of the Johns Hopkins Kimmel Cancer Center's Cancer Genetics and Epigenetics Programme, who co-led the study with Dr. Zachariah Foda, gastroenterology fellow, Dr. Akshaya Annapragada, M.D./Ph.D. student, and Dr. Amy Kim, assistant professor of medicine at the Johns Hopkins University School of Medicine, highlighted the significance of increased early detection in liver cancer. They emphasized that currently, available screening tests are underutilized and often miss many cancers.
The study involved analyzing 724 plasma samples, including 501 collected from the U.S. and EU, and 223 from individuals in Hong Kong. The training and validation of the machine learning model, a type of AI that employs data and algorithms to enhance accuracy, included 75 plasma samples from individuals with HCC. The validation process encompassed an additional 223 plasma samples from individuals in Hong Kong, consisting of 90 people with HCC, 66 with hepatitis B virus (HBV), 35 with HBV-related liver cirrhosis, and 32 people with no risk factors.
The DELFI technology analyses the size and quantity of cell-free DNA from various genomic regions in the blood to determine how DNA is packaged inside the nucleus of a cell. Like well-organized luggage, healthy cells painstakingly compartmentalize different parts of the genome to package DNA in an orderly fashion. On the other hand, the nuclei of cancer cells resemble disorganized suitcases, with items from different parts of the genome thrown in haphazardly. When cancer cells die, they release DNA fragments into the bloodstream.
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 is economical for usage in a screening scenario because it just needs low-coverage sequencing.
During the latest study, the researchers conducted the DELFI test on cfDNA fragments isolated from the plasma samples. They analyzed the fragmentation patterns in each sample to establish a DELFI score. For individuals without cancer but having viral hepatitis or cirrhosis, the scores were low (median DELFI score of 0.078 and 0.080, respectively). However, the scores were on average 5 to 10 times higher for the 75 HCC patients in the U.S./EU samples, with high scores observed across all cancer stages, including (DELFI scores for Stage 0 = 0.46, Stage A = 0.61, Stage B = 0.83, and Stage C = 0.92) Early-stage disease. The test also identified genomic packing and content abnormalities in liver cancers, particularly those linked to liver-specific activity.
With an overall sensitivity of 88% and a specificity of 98% among people at average risk, the DELFI technology proved its capacity to identify liver tumors in their earliest stages. The test had an 85% sensitivity and an 80% specificity in high-risk patients. Currently, less than 20% of the high-risk population undergoes screening for liver cancer due to accessibility and suboptimal test performance. However, this new blood test can double the number of liver cancer cases detected compared to the standard blood test, enabling early cancer detection.
Dr. Amy Kim, co-senior author of the study and assistant professor of medicine at the Johns Hopkins University School of Medicine, expressed that the new blood test has the potential to significantly impact liver cancer detection and increase early diagnosis rates. The researchers are now focusing on validating this approach in larger studies for clinical use.
Liver cancer affects over 800,000 people worldwide each year and stands as one of the leading causes of cancer-related deaths globally, as reported by the American Cancer Society.