Researchers from the Johns Hopkins Kimmel Cancer Center and other institutions have used artificial intelligence technology to identify patterns of DNA fragments associated with lung cancer. They have created and verified a liquid biopsy that could potentially assist in the early detection of lung cancer. The team’s findings were published on June 3 in Cancer Discovery.potentially improve lung cancer screening by identifying individuals at higher risk based on DNA fragment patterns in the blood,” said one researcher. The study included 1,000 participants with and without cancer who were eligible for traditional CT screening. The participants were recruited from 47 centers in 23 U.S. states. Computer modeling suggests that this blood test could help identify high-risk patients and improve screening outcomes.The study’s lead author, Victor E. Velculescu, M.D., Ph.D., who is a professor of oncology and co-director of the Cancer Genetics and Epigenetics program at the Johns Hopkins Kimmel Cancer Center, stated that there is potential for a test to be done in a doctor’s office to indicate if patients have early signs of lung cancer and need a follow-up CT scan. Lung cancer is the deadliest cancer in the United States and worldwide. Annual CT scans for high-risk patients can aid in the early detection of lung cancer, making it more treatable and potentially preventing lung cancer deaths.The U.S. Preventive Services Task Force recommends screening for 15 million individuals aged 50 to 80 with a history of smoking. However, only 6%-10% of those eligible undergo the screening each year. According to Velculescu, people may be hesitant to get screened due to the time required to schedule and attend appointments, as well as concerns about the low radiation exposure from the scan.
To address these challenges, Velculescu and his team have spent the last five years developing a test that utilizes artificial intelligence to identify DNA fragment patterns in patients. This test aims to make screening more accessible and efficient for individuals.The research focused on lung cancer and the differences in DNA packaging between normal and cancer cells. In healthy cells, DNA is neatly folded, while in cancer cells, it is more disorganized. When these cells die, DNA fragments end up in the blood. The DNA fragments in cancer patients are more chaotic and irregular compared to those without cancer.
A team of researchers developed artificial intelligence software to recognize the patterns of DNA fragments in the blood of 576 individuals with or without lung cancer. They then confirmed the accuracy of the software’s findings.The study was conducted on a group of 382 individuals, some with cancer and some without. The results of the analysis showed that the test has a 99.8% negative predictive value, indicating that only 2 out of 1,000 people tested may be missed and actually have lung cancer.
The computer simulations conducted by the group revealed that if the test increased the rate of lung cancer screening to 50% within five years, it could quadruple the number of detected lung cancers and increase the detection of early-stage cancers by approximately 10%. This increase in early detection could potentially prevent around 14,000 cancer deaths over the span of five years.
Furthermore, the test is cost-effective and can be easily administered.Velculescu stated that the new blood test has the potential to significantly impact lung cancer screening on a large scale. He believes that the test will improve accessibility to screening and lead to an increase in early detection and treatment of lung cancers. Currently, the test is offered through DELFI Diagnostics for use in laboratories under CLIA. The team intends to pursue FDA approval for lung cancer screening and explore the possibility of using a similar approach for detecting other types of cancer. Robert B. Scharpf of Johns Hopkins University also contributed to the study.Hopkins collaborated on the research, with additional co-authors coming from a variety of institutions including the Cleveland Clinic, DELFI Diagnostics, Medicus Economics LLC, Miami Cancer Institute, the Pan American Center for Oncology, Washington University, Centura Health, Vanderbilt Health, Stratevi, Massachusetts General Hospital, the Medical University of South Carolina, the Department of Veterans Affairs, the Perelman School of Medicine at the University of Pennsylvania, New York University Langone Health, Allegheny Health Network, and Memorial Sloan Kettering Cancer Center.
The study received partial support from DELFI Diagnostics and the Dr. Miriam and Sheldon G. Adelson Medical Research Foundation.The Lung Foundation, Stand Up To Cancer, LUNGevity, American Lung Association, and various other organizations have provided grants for research projects. Velculescu and Scharpf are involved in patent applications related to cell-free DNA for cancer detection, licensed to multiple companies.In February 2022, Velculescu sold his shares in Personal Genome Diagnostics (PGDx) to LabCorp. Velculescu is a co-founder of DELFI Diagnostics, where he serves on the board of directors and owns stock in the company. Scharpf is also a co-founder and consultant at DELFI Diagnostics, with ownership of company stock. Velculescu, Scharpf, and Johns Hopkins University receive royalties and fees from DELFI Diagnostics, and the university also holds equity in the company. Velculescu advises Viron Therapeutics and Epitope, with these relationships being managed by Johns Hopkins in accordance with their conflict-of-interest policies.
