Lung cancer is one of the most prevalent cancers worldwide, yet only approximately 16% of patients are diagnosed in early stage, highlighting the urgent need for novel, highly accurate detection models. In our study, patients with suspected lung cancer or lung disease, as identified through radiographic imaging, along with healthy individuals, were consecutively recruited from Beijing Chest Hospital. Circulating free DNA (cfDNA) was extracted from plasma samples, and low-depth whole-genome sequencing was performed to identify fragmentomic features for model construction. A total of 265 participants were prospectively enrolled, comprising 124 lung cancer patients and 141 noncancer individuals. The model we developed was based on four cfDNA fragmentation characteristics, including 20-bp breakpoint nucleotides motif, fragmentation size coverage, fragmentation size distribution, and copy number variation. In an independent test cohort, the model achieved an area under the curve (AUC) of 0.861 (95% CI: 0.781-0.942) and demonstrated a sensitivity of 70% (95% CI: 53.5%-83.4%) at a specificity of 89.4% (95% CI: 76.9%-96.5%). Notably, the model was also effective in detecting early-stage cancer, with an AUC of 0.808 (95% CI: 0.69-0.925). In summary, our lung cancer detection model shows strong screening capabilities by leveraging four cfDNA fragmentation characteristics, exhibiting robust performance in early cancer diagnosis.
Read full abstract