A gene-based predictive model for lymph node metastasis in cervical cancer: superior performance over imaging techniques

• DOI: 10.1186/s12967-025-06327-3
• Publication Date: 2025-04-04T10:20:39Z
• Authors: Dongdong Xu; Xibo Zhao; Dongdong Ye; Chuying Huo; Xuanwei Peng; Yunyun Liu; Huaiwu Lu
• Keywords: Lasso

Abstract Objective Lymph node metastasis (LNM) critically impacts the prognosis and treatment decisions of cervical cancer patients. The accuracy sensitivity current imaging techniques, such as CT MRI, are limited in assessing lymph status. This study aims to develop a more accurate efficient method for predicting LNM. Methods Three independent cohorts were merged divided into training internal validation groups, with our cohort those from other centers serving external validation. A predictive model LNM was established using LASSO regression multivariate logistic regression. diagnostic performance compared that CT/MRI terms accuracy, sensitivity, specificity, AUC. Results Using RNA-seq data, four genes (MAPT, EPB41L1, ACSL5, PRPF4B) identified through regression, constructed calculate risk score. Compared CT/MRI, demonstrated higher efficiency, an 0.840 0.804, CT/MRI’s 0.713 0.587. corrected 81% misdiagnoses by demonstrating significant improvements sensitivity. Conclusion developed this study, based on gene expression significantly improves preoperative assessment cancer. traditional shows superior accuracy. provides robust foundation developing precise tools, paving way future clinical applications individualized planning.