Yongli Hou, Lili Zhang, Hui Wang, Wenhao Wang, Min Hao
{"title":"Development and validation of a risk prediction model for lymph node metastasis in stage IA2-IIA1 cervical cancer based on laboratory parameters.","authors":"Yongli Hou, Lili Zhang, Hui Wang, Wenhao Wang, Min Hao","doi":"10.62347/EOXM6715","DOIUrl":null,"url":null,"abstract":"<p><strong>Objective: </strong>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.</p><p><strong>Methods: </strong>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.</p><p><strong>Results: </strong>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.</p><p><strong>Conclusions: </strong>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.</p>","PeriodicalId":7437,"journal":{"name":"American journal of cancer research","volume":"15 3","pages":"1081-1095"},"PeriodicalIF":3.6000,"publicationDate":"2025-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11982735/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"American journal of cancer research","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.62347/EOXM6715","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"ONCOLOGY","Score":null,"Total":0}
引用次数: 0
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.
期刊介绍：
The American Journal of Cancer Research (AJCR) (ISSN 2156-6976), is an independent open access, online only journal to facilitate rapid dissemination of novel discoveries in basic science and treatment of cancer. It was founded by a group of scientists for cancer research and clinical academic oncologists from around the world, who are devoted to the promotion and advancement of our understanding of the cancer and its treatment. The scope of AJCR is intended to encompass that of multi-disciplinary researchers from any scientific discipline where the primary focus of the research is to increase and integrate knowledge about etiology and molecular mechanisms of carcinogenesis with the ultimate aim of advancing the cure and prevention of this increasingly devastating disease. To achieve these aims AJCR will publish review articles, original articles and new techniques in cancer research and therapy. It will also publish hypothesis, case reports and letter to the editor. Unlike most other open access online journals, AJCR will keep most of the traditional features of paper print that we are all familiar with, such as continuous volume, issue numbers, as well as continuous page numbers to retain our comfortable familiarity towards an academic journal.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
