Washington: A New Artificial Intelligence Blood Testing Technology A 2021 study developed and used by Johns Hopkins Kimmel Cancer Center researchers to successfully detect lung cancer found more than 80 percent of liver cancers in a new study of 724 people.
The findings were reported at the Cancer Discovery and American Association for Cancer Research Special Conference: Precision Prevention, Early Detection, and Interception of Cancer.
A blood test, called DELFI (DNA Evaluation of Fragments for Early Disruption) detects fragmentation changes in DNA from cancer cells circulating in the bloodstream, known as cell-free DNA (cfDNA). In the most recent study, investigators used DELFI technology to detect hepatocellular cancer (HCC), a type of liver cancer, on blood plasma samples obtained from 724 individuals in the US, European Union (EU) and Hong Kong.
The researchers believe this is the first genome-wide fragmentation analysis that has been independently validated in two high-risk populations and in different racial and ethnic groups with different causes associated with their liver cancer.
It is estimated that 400 million people worldwide are at increased risk of developing HCC due to cirrhosis from chronic liver diseases, including chronic viral hepatitis or nonalcoholic fatty liver disease, according to a worldwide analysis of the burden of liver disease (J. Hepatology, 2019).
“Increased early detection of liver cancer could save lives, but currently available screening tests are underutilized and many cancers are missed,” says Victor Valculescu, MD, Ph.D., professor of oncology and co-director of the Cancer Genetics and Epigenetics Program. is Johns Hopkins Kimmel Cancer Center, who has Zakaria Foda, MD, Ph.D., gastroenterology fellow, Akshay Annapragada, MD/Ph.D. Co-led the study with student, and Amy Kim, MD, assistant professor of medicine at Johns Hopkins University School of Medicine.
Of the 724 plasma samples studied, 501 were collected in the US and EU and included samples from 75 people with HCC to train and validate a machine learning model, a type of artificial intelligence that uses data and algorithms to improve accuracy. It does, explains Foda. For validation, an additional 223 plasma samples from individuals in Hong Kong were analyzed and included samples from 90 people with HCC, 66 with hepatitis B virus (HBV), 35 with HBV-related liver cirrhosis, and 32 people with no underlying risk factors.
DELFI technology uses a blood test to measure how DNA is packaged inside a cell’s nucleus by studying the size and quantity of circulating cell-free DNA from different regions of the genome. Healthy cells package DNA like a well-organized suitcase, with different regions of the genome carefully placed in different compartments. In contrast, the nuclei of cancer cells are more like a messy suitcase, with items haphazardly tossed around the genome. When cancer cells die, they randomly release DNA fragments into the bloodstream.
DELFI identifies the presence of cancer by examining millions of cfDNA fragments for abnormal patterns, including the size and proportion of DNA in different genomic regions. The DELFI approach requires only low-coverage sequencing, enabling the technology to be cost-effective in a screening setting, the researchers say.
In the latest study, the researchers performed the test — which had previously been shown to accurately classify lung cancer — on cfDNA fragments isolated from plasma samples. They analyzed the pattern of fragmentation in each sample to develop a DELFI score.
Scores were lower for cancer-free individuals with viral hepatitis or cirrhosis (median DELFI scores were 0.078 and 0.080, respectively), but were, on average, 5- to 10-fold higher for 75 HCC patients in the US/EU sample, with higher scores for early-stage disease (stage 0 = 0.46, DELFI score for stage A = 0.61, stage B = 0.83, and stage C = 0.92). In addition, the test found fragmentation changes in the content and packaging of liver cancer genomes, including genome regions associated with liver-specific activity.
DELFI technology detects liver cancers in their earliest stages, with an overall sensitivity — or ability to accurately detect cancer — of 88 percent and specificity of 98 percent, meaning it almost never provides a false-positive result, with an average risk. among the people. In samples collected from people at high risk of HCC, the test had 85 percent sensitivity and 80 percent specificity.
“Currently, less than 20 percent of the high-risk population is screened for liver cancer due to accessibility and suboptimal test performance. This new blood test could double the number of liver cancer cases compared to the standard blood test available, and increase early cancer detection, ” says Kim, co-senior author of the study.
Next steps include validating the approach in larger studies for clinical use, the researchers said.
More than 800,000 people worldwide are diagnosed with liver cancer each year, and it is the leading cause of cancer death worldwide, according to the American Cancer Society.
In addition to Valculescu, Foda, Annapragada, and Kim, other researchers included Kavya Boyapati, Daniel Brahm, Nicolas Vulpescu, Jamie Medina, Dimitrios Mathios, Stephen Cristiano, Naushin Niknafs, Harry Lu, Michael Goggins, Robert Anders, Jing Sun, Shruti Mehta, and others. David Thomas, Gregory Kirk, Wilmos Adeleff, Jillian Phalen, and Robert Scarp.
