A prediction model based on cfDNA concentration and cfDNA methylation biomarkers for lung cancer detection

Abstract Early detection plays a critical role in reducing lung cancer mortality. DNA methylation biomarker assay based on cell-free DNA (cfDNA) is a promising method for early detection of lung cancer. In this study, we aimed to develop a prediction model based on cfDNA methylation biomarkers and c...

Full description

Saved in:
Bibliographic Details
Main Authors: Li Ke, Xiang Huang, Wenting Liu, Bo Hong, Hongzhi Wang, Jian Qi, Yannan Chu
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-15273-5
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Abstract Early detection plays a critical role in reducing lung cancer mortality. DNA methylation biomarker assay based on cell-free DNA (cfDNA) is a promising method for early detection of lung cancer. In this study, we aimed to develop a prediction model based on cfDNA methylation biomarkers and cfDNA concentration for early detection of lung cancer. We recruited 179 lung cancer patients and 82 healthy controls, and assessed the methylation level of four DNA methylation biomarkers (PTGER4, RASSF1A, SHOX2, and H4C6) and cfDNA concentration. The LASSO and Boruta algorithms were then used to select the best performing variables, and a lung cancer prediction model was constructed using the generalized linear models (GLMs) algorithm. The model was then validated in an independent set. Finally, the AUC for this model in the training and validation cohorts was 0.8012 and 0.8436, respectively. The accuracy of the model was significantly higher than the individual biomarkers. These results demonstrated that this panel based on four methylation markers and cfDNA concentration was effective in lung cancer detection, and may provide clinical utility in combination with current lung cancer detection techniques to improve the diagnosis of lung cancer.
ISSN:2045-2322