Development of a new AI blood test technology for the identification of lung cancers

Maryland: In samples from nearly 800 people with and without cancer, more than 90% of lung cancers have been detected by new artificial intelligence blood testing technology developed by researchers at the Johns Hopkins Kimmel Cancer Center. The testing approach, called DELFI (Evaluation of DNA Fragments for Early Interception), detects unique patterns in the fragmentation of DNA released by cancer cells circulating in the blood. By applying this technology to blood samples taken from 796 people in Denmark, the Netherlands and the United States, the researchers found that the DELFI approach accurately distinguished patients with and without lung cancer. These results will be published in the August issue of the journal Nature Communications.

By combining the test with the analysis of clinical risk factors, a protein biomarker, and followed by CT imaging, DELFI detected 94% of cancer patients at all stages and subtypes. This included 91 percent of patients with earlier or less invasive stage I / II cancers and 96 percent of patients with more advanced stage III / IV cancers.

Lung cancer is the most common cause of cancer death, claiming nearly 2 million deaths worldwide each year. However, less than 6% of Americans at risk for lung cancer undergo recommended low-dose CT scans, despite projections that tens of thousands of deaths could be prevented, and even fewer are screened globally, explains the lead author of the study Victor E. Velculescu. , MD, PhD, Professor of Oncology and Co-Director of the Cancer Genetics and Epigenetics Program at Johns Hopkins Kimmel Cancer Center.

This is due to a variety of reasons, including concerns about potential harm from investigating false positive imaging results, radiation exposure, or concerns about complications from invasive procedures.

“It is clear that there is an urgent and unmet clinical need for the development of alternative, non-invasive approaches to improve cancer screening in high risk individuals and ultimately the general population,” says lead author Dimitrios Mathios, postdoctoral researcher at the Johns Hopkins Kimmel Cancer Center. “We believe that a blood test, or ‘liquid biopsy’, for lung cancer could be a good way to improve screening efforts because it would be easy to do, widely accessible and cost effective.”

DELFI technology uses a blood test to indirectly measure how DNA is packaged inside a cell’s nucleus by studying the size and amount of cell-free DNA present in circulation from different regions of the genome . Healthy cells pack DNA like a well-organized suitcase, in which different regions of the genome are neatly placed in various compartments.

The nuclei of cancer cells, on the other hand, are like more disorganized suitcases, with pieces of the entire genome thrown at random. When cancer cells die, they chaotically release DNA into the bloodstream. DELFI helps identify the presence of cancer using machine learning, a type of artificial intelligence, to examine millions of cell-free DNA fragments for abnormal patterns, including size and amount of DNA in different genomic regions.

This approach provides a view of the cell-free DNA called a “fragmentome”. The DELFI approach requires only low-coverage genome sequencing, which allows this technology to be cost-effective in a screening setting, the researchers say.

For the study, researchers at Johns Hopkins, working with researchers in Denmark and the Netherlands, first performed genome sequencing of cell-free DNA in blood samples from 365 people participating in a Danish study. age seven called LUCAS. The majority of participants were at high risk for lung cancer and had smoking-related symptoms such as cough or difficulty breathing.

The DELFI approach revealed that patients who were later determined to have cancer had a large variation in their fragmentome profiles, while patients who were found to have no cancer had a large variation in their fragmentome profiles. consistent fragmentome profiles. Subsequently, the researchers validated the DELFI technology using a different population of 385 people without cancer and 46 people with cancer. Overall, the approach has detected over 90 percent of lung cancer patients, including those in early and advanced stages, and with different subtypes.

“DNA fragmentation models provide a remarkable fingerprint for the early detection of cancer which we believe could be the basis of a widely available liquid biopsy test for lung cancer patients,” says the author Rob Scharpf, PhD, associate professor of oncology at the Johns Hopkins Kimmel Cancer Center.

A one-of-a-kind national clinical trial called DELFI-L101, sponsored by Johns Hopkins University spin-off company Delfi Diagnostics, evaluates a test based on DELFI technology in 1,700 participants in the United States, including participants in good health, people with lung cancers and people with other cancers. The group wishes to deepen the study of DELFI in other types of cancer.

Other scientists who contributed to the work include Stephen Cristiano, Jamie E. Medina, Jillian Phallen, Daniel Bruhm, Noushin Niknafs, Leonardo Ferreira, Vilmos Adleff, Jia Yuee Ciao, Alessandro Leal, Michael Noe, James White, Adith S. Arun , Carolyn Hruban, Akshaya V. Annapragada, Patrick M. Forde, Valsamo Anagnostou, and Julie R. Brahmer of Johns Hopkins.

Additional authors came from Herlev and Gentofte Hospital and Bispebjerg Hospital in Copenhagen; Aarhus University Hospital in Aarhus, Denmark; Herning Regional Hospital in Herning, Denmark; the Dutch Cancer Institute in Amsterdam; Delphi diagnostics; and Hvidovre Hospital in Hvidovre, Denmark.