医学新知2024，Vol.34Issue(6)：611-621,11.DOI:10.12173/j.issn.1004-5511.202401099
基于SEER数据库构建和验证男性乳腺癌预后模型
Construction and validation of a prognostic model for male breast cancer based on the SEER database
摘要
Abstract
Objective To explore the prognostic factors of male breast cancer(MBC)patients,and construct a survival prognostic nomogram for MBC patients,and predict the 3-year and 5-year overall survival rates.Methods Patients from the Surveillance,Epidemiology,and End Results(SEER)cancer registry database were included,along with MBC patients from the Affiliated Hospital of North Sichuan Medical College,Suining Central Hospital,and Deyang People's Hospital.Clinical baseline data and survival information of the patients were obtained.The data of patients from the SEER database served as the training coherent,and the data of patients from 3 hospitals as the validation coherent.Independent prognostic factors for the overall survival(OS)of MCB patients were determined by univariate and multivariate Cox regression analysis.A nomogram predicting 3-year and 5-year survival rates for MBC patients was constructed based on the independent prognostic factors,and its accuracy and practical application value were assessed using calibration curves,the concordance index(C-index),receiver operating characteristic curves(ROC),and decision curve analysis(DCA).Results A total of 3,387 MBC patients were included,3,307 patients were in training coherent and 80 patients were in validation coherent.After univariate and multivariate Cox regression analysis of the training set,it was found that diagnostic age,histological grade,TNM stage,prgesterone receptor status,surgery,chemotherapy,and radiotherapy were the independent prognostic factors for MBC.These factors were incorporated into the nomogram model and validated,with a C-index of 0.711 for the training set and 0.787 for the external validation set.In the training set,the nomogram showed an AUC of 0.744 for 3-year OS and an AUC of 0.720 for 5-year OS;in the validation set,the nomogram showed an AUC of 0.835 for 3-year OS and an AUC of 0.858 for 5-year OS.The ROC curve indicated good discriminative ability of the model,the calibration curve showed good predictive performance,and the DCA curve indicated high clinical utility of the model.Conclusion The nomogram provides a reliable and practical method for predicting the prognosis of MBC patients,aiding in personalized treatment decisions and thereby improving patient outcomes.关键词
男性乳腺癌/列线图/SEER数据库/预后Key words
Male breast cancer/Nomogram/SEER database/Prognosis引用本文复制引用
苏小涵,谭巧,曾姣,程攀科,侯令密..基于SEER数据库构建和验证男性乳腺癌预后模型[J].医学新知,2024,34(6):611-621,11.基金项目
国家自然科学基金青年科学基金项目(32000967) （32000967）
四川省自然科学基金面上项目(2022NSFSC0775) （2022NSFSC0775）
