Genetic information collected from healthy tissue near lung tumors may be predictive of posttreatment cancer recurrence compared with analysis of the tumors themselves, according to a novel study published by Dolgalev et al in Nature Communications.
Background
Lung adenocarcinomas are tumors that form in the alveolar epithelial cells and account for about 33% of all lung cancer cases in the United States. Most of the patients with lung adenocarcinomas can be cured if the tumors are surgically removed early in the disease’s progression; however, residual cancer cells can regrow in about 30% of cases, leading to mortality. Consequently, researchers have long searched for biomarkers that may prompt more aggressive initial treatments.
Study Methods and Results
In the new study, researchers compared genetic material from the tumors of 147 patients who were treated for early-stage lung cancer with their tumors’ adjacent tissue—with the goal of predicting cancer recurrence.
The researchers collected almost 300 tumor and healthy tissue samples from the patients. They then sequenced the RNA from each sample and fed these data, along with whether or not recurrence occurred within 5 years of surgery, into an artificial intelligence algorithm that used machine learning to build mathematic models designed to estimate the cancer recurrence risk.
The researchers found that analyzing the RNA collected from apparently healthy tissue adjacent to tumor cells was accurate at predicting cancer recurrence in 83% of the cases, whereas RNA from the tumors themselves was only informative in 63% of the cases. Additionally, the researchers noted that the expression of genes associated with inflammation, or heightened immune-system activity, in adjacent, apparently normal lung tissue, was especially useful for making predictions. They explained that this defensive reaction should not be present in tissue that is truly healthy and may be an early warning sign of disease.
“Our results suggest that seemingly normal tissue that sits close to a tumor may not be healthy after all,” revealed co–lead study author Hua Zhou, PhD, a bioinformatician at the New York University (NYU) Grossman School of Medicine and a member of the Perlmutter Cancer Center. “Instead, escaped tumor cells might be triggering this unexpected immune response in their neighbors,” he added.
Conclusions
“Immunotherapy, which bolsters the body’s immune defenses, might … help combat tumor growth before it becomes visible to traditional methods of detection,” proposed co–senior study author Aristotelis Tsirigos, PhD, Professor in the Department of Pathology at the NYU Grossman School of Medicine, Director of the Applied Bioinformatics Laboratories at NYU Langone Health, and a member of the Perlmutter Cancer Center.
The researchers cautioned that despite their findings, their investigation worked backward, training the computer model using cases already known to have had cancer recurrence.
As a result, the researchers plan to use the program to prospectively assess the risk of cancer recurrence in patients newly-treated for early-stage lung cancer.
“Our findings suggest that the pattern of gene expression in apparently healthy tissue might serve as an effective and, until now, elusive biomarker to help predict lung cancer recurrence in the earliest stages of the disease,” concluded co–lead study author Igor Dolgalev, PhD, Assistant Professor in the Department of Medicine at the NYU Grossman School of Medicine and a member of the Perlmutter Cancer Center.
Disclosure: The research in this study was funded by the National Institutes of Health, the American Association for Cancer Research, and the Roche Access to Distinguished Scientists Programme. For full disclosures of the study authors, visit nature.com.
