高春洁,刘 静,吴梦娟,等.基于Lasso-Cox回归和层次聚类分析乳腺癌患者1 313例预后[J].肿瘤学杂志,2024,30(5):400-406.
基于Lasso-Cox回归和层次聚类分析乳腺癌患者1 313例预后
Prediction for Survival of 1 313 Patients with Breast Cancer Based on Lasso-Cox Regression and Hierarchical Clustering Analysis of Clinicopathological Factors
投稿时间:2024-01-16  
DOI:10.11735/j.issn.1671-170X.2024.05.B008
中文关键词:  乳腺癌  Lasso-Cox 回归  层次聚类分析  预后
英文关键词:breast cancer  Lasso-Cox regression  hierarchical clustering analysis  prognosis
基金项目:国家自然科学基金(12061079);“天山英才”青年科技创新人才培养(2022TSYCCX0108);新疆自然科学基金(2022D01C287)
作者单位
高春洁 新疆医科大学公共卫生学院 
刘 静 新疆医科大学公共卫生学院 
吴梦娟 新疆医科大学公共卫生学院 
依帕拉·伊力哈木 新疆医科大学公共卫生学院 
摘要点击次数: 184
全文下载次数: 115
中文摘要:
      摘 要:[目的] 探讨乳腺癌患者的临床特征及个体差异,比较不同类别乳腺癌患者预后差异,为患者的个性化诊疗提供数据支撑。[方法] 共纳入2016年1月1日至12月31日期间于新疆医科大学附属肿瘤医院确诊的1 313例乳腺癌患者,包括1 139例生存,174例死亡。采用Lasso-Cox回归对数据进行变量筛选,筛选出对乳腺癌患者预后影响较大的变量;基于分类数据的层次聚类方法挖掘乳腺癌患者之间临床病理特点的相似性并进行聚类,根据聚类结果绘制Kaplan-Meier生存曲线,比较不同类别乳腺癌患者的预后差异。[结果] 通过Lasso-Cox回归筛选出了与乳腺癌患者预后相关的14个临床特征,包括T分期、N分期、M分期、临床分期、新辅助治疗、手术类型、淋巴结清扫术、辅助治疗、ER阳性表达、分子分型、脑转移、肺转移、肝转移以及骨转移。基于层次聚类方法将研究对象聚为两类,Kaplan-Meier生存分析发现两类乳腺癌患者生存预后存在显著性差异(χ2=397.00,P<0.001)。[结论] 乳腺癌患者之间存在高度异质性,不同临床特征的患者生存预后情况不同。因此有必要根据患者的临床病理特点进行分类,从而为患者制定个性化的治疗方案。
英文摘要:
      Abstract:[Objective] To explore the prediction for survival of breast cancer patients based on Lasso-Cox regression and Hierarchical clustering analysis of clinicopathological features. [Methods] A total of 1 313 breast cancer patients admitted in the Affiliated Cancer Hospital of Xinjiang Medical University from January to December 2016 were included in this study, including 1 139 survival cases and 174 fatal cases. Lasso-Cox regression was used to analyze variables associated with the prognosis of breast cancer patients. Hierarchical clustering based on categorical data was performed to reveal the similarity of clinical and pathological characteristics, and Kaplan-Meier survival analysis curves were plotted to compare the prognosis between different categories of breast cancer patients. [Results] Fourteen clinicopathological features related to the prognosis of breast cancer patients were screened out by Lasso-Cox regression, including T stage, N stage, M stage, clinical stage, neoadjuvant therapy, type of surgery, lymph node dissection, adjuvant therapy, ER positive expression, molecular typing, brain metastasis, lung metastasis, liver metastasis and bone metastasis. Patients were clustered into 2 categories based on hierarchical clustering. Kaplan-Meier survival analysis showed that there were significant differences in the prognosis between two categories of patients (χ2=397.00, P<0.001). [Conclusion] Breast cancer patients exhibit high heterogeneity, and patients with varying clinicopathological features have different survival prognosis. Therefore, it is necessary to classify patients based on their clinical and pathological characteristics in order to develop personalized treatment plans.
在线阅读   查看全文  查看/发表评论  下载PDF阅读器