top of page

The Role of Artificial Intelligence in Lung Cancer Detection

Lung cancer is the second most common form of cancer in both men and women and the leading cause of cancer deaths worldwide.

A recent article published by Genetic Engineering & Biotechnology News highlights tremendous hope from new Artificial Intelligence (AI) technology developed by researchers at the Johns Hopkins Kimmel Cancer Center that can detect multiple stages and sub types of lung cancer across more than 90% of patients included in the study.

A novel artificial intelligence (AI) blood testing technology developed by researchers at the Johns Hopkins Kimmel Cancer Center has been shown to detect over 90% of lung cancers in samples from nearly 800 individuals with and without cancer.

The test approach, called DELFI (DNA evaluation of fragments for early interception), spots unique patterns in the fragmentation of DNA that is shed from cancer cells circulating in the bloodstream, or cell free DNA (cfDNA). A study reported in Nature Communications has now demonstrated how testing for fragmentation features, in combination with evaluating clinical risk factors, analyzing a protein biomarker, and CT imaging, enabled detection of 94% of patients with cancer across stages and subtypes.

Reporting on the study, senior author Victor E. Velculescu, MD, PhD, first author Dimitrios Mathios, PhD, and colleagues, concluded, “The observations that scalable and cost-effective noninvasive cfDNA fragmentation analyses can discriminate lung cancer patients from noncancer individuals may ultimately provide an opportunity to evaluate not only high-risk individuals but the general population for lung cancer.” Their paper is titled, “Detection and characterization of lung cancer using cell-free DNA fragmentomes.”

Lung cancer is the most common cause of cancer death, claiming almost two million lives worldwide each year, and incidence of the disease is on the rise, the authors noted. “The 5-year survival rate is <20%,” the authors said, “largely due to the late stage at diagnosis where treatments are less effective than at earlier stages…”

However, fewer than 6% of people in the United States at risk for lung cancers undergo recommended low-dose computed tomography (LDCT) screening, despite projections that tens of thousands of deaths could be avoided, and even fewer are screened worldwide, explained Velculescu, who is professor of oncology and co-director of the cancer genetics and epigenetics program at the Johns Hopkins Kimmel Cancer Center. This is due to reasons that include concerns about the potential harm from investigatio