Development and validation of a risk prediction model for lymph node metastasis in stage IA2-IIA1 cervical cancer based on laboratory parameters

基于实验室参数的IA2-IIA1期宫颈癌淋巴结转移风险预测模型的建立与验证

阅读:1

Abstract

OBJECTIVE: To develop and validate a risk prediction model for lymph node metastasis (LNM) in stage IA2-IIA1 cervical cancer (CC) using laboratory parameters to aid in preoperative risk assessment and personalized treatment planning. METHODS: A retrospective analysis was conducted on 624 patients treated between 2017 and 2023, divided into a training group (418 patients) and a validation group (206 patients). Clinical and laboratory data, including squamous cell carcinoma antigen (SCC-Ag), carcinoembryonic antigen (CEA), cancer antigen 125 (CA125), platelet count (PLT), fibrinogen (FIB), and C-reactive protein (CRP), were collected. Independent risk factors for LNM were identified using Least Absolute Shrinkage and Selection Operator (LASSO) regression. A predictive model was constructed and evaluated using receiver operating characteristic (ROC) curve analysis, decision curve analysis (DCA), and calibration curve. RESULTS: SCC-Ag, CEA, CA125, PLT, FIB, and CRP were identified as significant predictors of LNM, with SCC-Ag demonstrating an AUC of 0.811 (sensitivity: 65.00%, specificity: 93.08%). The model achieved an AUC of 0.969 in the training group and 0.942 in the validation group, indicating robust generalizability and high predictive accuracy. DCA confirmed the model's clinical utility across a wide range of risk thresholds, and the calibration curve showed a good agreement between predicted and observed outcomes. CONCLUSIONS: This laboratory parameter-based risk prediction model is a reliable and practical tool for assessing LNM risk in stage IA2-IIA1 CC patients, supporting better clinical decision-making and reducing unnecessary interventions.

特别声明

1、本页面内容包含部分的内容是基于公开信息的合理引用;引用内容仅为补充信息,不代表本站立场。

2、若认为本页面引用内容涉及侵权,请及时与本站联系,我们将第一时间处理。

3、其他媒体/个人如需使用本页面原创内容,需注明“来源:[生知库]”并获得授权;使用引用内容的,需自行联系原作者获得许可。

4、投稿及合作请联系:info@biocloudy.com。