医学新知2025，Vol.35Issue(7)：800-809,10.DOI:10.12173/j.issn.1004-5511.202409090
基于SEER数据库构建与验证儿童骨肉瘤的预后预测模型
Construction and validation of a prognostic prediction model for osteosarcoma in children based on the SEER database
摘要
Abstract
Objective To construct and validate a nomogram model for predicting the survival prognosis of pediatric osteosarcoma patients.Methods Data were collected from pediatric patients diagnosed with osteosarcoma based on the U.S.SEER database between 2000 and 2021,aged less than 14 years.Patients were randomly divided into a training set and a validation set in a 7∶3 ratio.Univariate and multivariate Cox proportional hazards models were used to identify factors affecting survival,then the prediction model was constructed and nomogram was plotted.The nomogram was validated using the concordance index(C-index),the receiver operating characteristic curve and the area under the curve(AUC),calibration curves,and decision curve analysis.Patients were divided into high-risk and low-risk groups according to the risk scores which were calculated based on the nomogram model.Subgroup survival analyses were performed using Kaplan-Meier survival curves.Results A total of 726 pediatric osteosarcoma patients were included,with 508 in the training set and 218 in the validation set.Multivariate Cox regression analysis identified tumor size[HR=1.002,95％CI(1.001,1.004)],lymph node metastasis[HR=3.341,95％CI(2.368,4.712)],and surgical approach(radical resection)[HR=0.382,95％CI(0.219,0.665)];amputation[HR=0.471,95％CI(0.255,0.870)])as independent prognostic factors.The C-index of the nomogram models constructed based on the above factors in the training and validation sets were 0.715 and 0.690,respectively.The AUC values for predicting 1-year,3-year,and 5-year tumor specific survival rates were 0.833 and 0.810(1-year),0.751 and 0.718(3-year),and 0.708 and 0.657(5-year)in the training and validation sets,respectively.The calibration curve showed that the predicted values were highly consistent with the observed values.The clinical decision curve showed that the model had demonstrated a certain clinical net benefit in predicting 1-year,3-year,and 5-year tumor specific survival rates within a certain prediction probability threshold range.Kaplan-Meier analysis showed that the survival rate of the high-risk group was significantly lower than that of the low-risk group(P＜0.05).Conclusion This study successfully developed a nomogram model for predicting tumor-specific survival rates in pediatric osteosarcoma patients based on key prognostic factors including tumor size,lymph node metastasis status,and type of surgery,demonstrating good predictive performance and potential clinical utility.关键词
儿童/骨肉瘤/预后/预测模型/列线图/SEER数据库Key words
Children/Osteosarcoma/Prognosis/Predictive model/Nomogram/SEER database分类
医药卫生引用本文复制引用
张磊,李豫皖,吴吟丹,徐志,邵金富..基于SEER数据库构建与验证儿童骨肉瘤的预后预测模型[J].医学新知,2025,35(7):800-809,10.基金项目
国家自然科学基金青年科学基金项目(82302853) （82302853）
