iScience. 2026 Jun 19. 29(6):
115833
Yongyi Chen,
Haiqi Liao,
Yuzhi Liu,
Liulin Luo,
Jiangang Jin,
Dingding Hou,
Wenjia Liu,
Hanqing Zhang,
Beilong He,
Miao Luo,
Wei Liu,
Ziao Lin,
Songxiao Xu.
Cell-free DNA (cfDNA) in plasma provides attractive opportunities for early cancer diagnosis. This study aimed to establish gastric cancer (GC) artificial intelligence algorithms (GC-AIAs) based on cfDNA fragmentome for GC's early detection and subtyping. Whole-genome sequencing data were obtained from the training cohort of 404 participants, the internal testing cohort of 173 participants, and the independent validation cohort of 299 participants. Seven classes of cfDNA fragmentomic features were analyzed and employed to build the GC-AIA employing a stack ensemble model. The model's AUC in the internal testing cohort was 0.958 (95% confidence interval [CI]: 0.931-0.985) and that in the independent validation cohort was 0.951 (95% CI: 0.926-0.975). The GC-AIA showed high performance for various staged/differentiated GC detection and molecular subtyping. The stage shift analysis showed a notable increase in diagnosed stage Ⅰ patients. Our methodology built on the cfDNA fragmentomics exhibited encouraging preliminary performance in early detection and subtyping of GC patients.
Keywords: cancer; diagnostic procedure; machine learning