Chronic atrophic gastritis (CAG) is a critical precursor lesion of gastric cancer (GC); however, precise tools for identifying high-risk individuals are currently lacking. This study aimed to develop a predictive model integrating clinicopathological characteristics and molecular biomarkers to enable individualized risk assessment for GC progression in CAG patients. Gene expression profiles from GEO were analyzed using differential expression genes(DEGs) analysis, weighted gene co-expression network analysis (WGCNA). Random Forest and Support Vector Machine models evaluated biomarkers. Least absolute shrinkage and selection operator (LASSO) regression analysis was utilized to identify risk factors for CAG, thus constructing a nomogram. The protein expression level of the key biomarker was evaluated through immunohistochemistry, which was subsequently integrated into the clinical model to create a novel model. Age, smoking history, and histological severity were identified as independent risk factors for GC progression. The clinical nomogram based on these factors demonstrated good predictive capability. Multi-omics analysis revealed that IGFBP7 was significantly upregulated in tissues from patients who progressed to GC. Integrating the IHC score of IGFBP7 into the clinical prediction model significantly enhanced its predictive performance. We successfully developed and validated a nomogram model combining clinical risk factors and the biomarker IGFBP7. This model effectively identifies CAG patients at high risk for GC, providing a practical tool for implementing precision surveillance and early intervention.
Guo et al. (Fri,) studied this question.