基于机器学习的病理组学特征可预测乳腺癌患者对新辅助化疗的反应

张杰秋 , 伍棋 , 王舰梅 , 要小鹏

重庆医科大学学报 ›› 2023, Vol. 48 ›› Issue (12) : 1483 -1488.

PDF (2885KB)
重庆医科大学学报 ›› 2023, Vol. 48 ›› Issue (12) : 1483 -1488. DOI: 10.13406/j.cnki.cyxb.003380
人工智能技术应用于医学数据分析

基于机器学习的病理组学特征可预测乳腺癌患者对新辅助化疗的反应

作者信息 +

Pathomics signature based on machine learning can predict the response to neoadjuvant chemotherapy in breast cancer patients

Author information +
文章历史 +
PDF (2953K)

摘要

目的 利用病理组学的方法开发用于预测乳腺癌(breast cancer,BC)患者新辅助化疗(neoadjuvant chemotherapy,NAC)反应的新型标志物。 方法 回顾性纳入211例西南医科大学附属医院的非特殊浸润性BC患者(训练组:155例,验证组:56例),使用CellProfiler软件提取患者数字病理切片中的高维病理组学特征,利用Mann-Whitney U检验、Spearman相关系数和最小绝对值收敛和选择算子(least absolute shrinkage and selection operator,LASSO)算法进行特征逐层筛选。筛选后的最优特征通过支持向量机(support vector machine,SVM)方法在训练集中开发了病理组学特征(pathomics signature,PS)并在独立验证集中进行验证。PS与单因素有意义的临床病理因素(P<0.05)纳入多因素逻辑回归进行进一步验证。 结果 PS的曲线下面积(area under the curve,AUC)为0.749(95%CI=0.672~0.827),验证集中AUC为0.737(95%CI=0.604~0.870)。多因素逻辑回归的结果显示,PS(OR=2.317)与人表皮生长因子受体2(human epidermal growth factor receptor 2,HER2)(OR=4.018)是BC患者NAC反应的独立预测因素。 结论 PS可以帮助临床医生在治疗前准确预测NAC的反应,促进BC患者的个性化治疗。

Abstract

Objective To develop a novel marker for predicting the response to neoadjuvant chemotherapy(NAC) in patients with breast cancer(BC) using the pathomics approach. Methods A retrospective analysis was performed for 211 patients with non-specific invasive BC in The Affiliated Hospital of Southwest Medical University,among whom 155 were enrolled as training group and 56 were enrolled as validation group. CellProfiler software was used to extract high-dimensional pathomics signature from the digital pathological sections of patients,and then the Mann-Whitney U test,the Spearman correlation coefficient,and the least absolute shrinkage and selection operator(LASSO) algorithm were used for the stepwise screening of features. The optimal features after screening were used to develop pathomics signature(PS) by the support vector machine(SVM) method in the training set and validate in the independent validation set. PS and significant clinicopathological factors(P<0.05) identified in the univariate analysis were included in the multivariate logistic regression analysis for further validation. Results PS had an area under the ROC curve of 0.749(95%CI=0.672-0.827) in the training set and 0.737(95%CI=0.604-0.870) in the validation set. The multivariate logistic regression analysis showed that PS [odds ratio(OR)=2.317] and human epidermal growth factor receptor 2(OR=4.018) were independent predictive factors for response to NAC in BC patients. Conclusion PS can help clinicians accurately predict the response to NAC before treatment and improve the personalized treatment for BC patients.

Graphical abstract

关键词

病理组学 / 新辅助化疗 / 乳腺癌 / 预测模型

Key words

pathomics / neoadjuvant chemotherapy / breast cancer / predictive model

引用本文

引用格式 ▾
张杰秋,伍棋,王舰梅,要小鹏. 基于机器学习的病理组学特征可预测乳腺癌患者对新辅助化疗的反应[J]. 重庆医科大学学报, 2023, 48(12): 1483-1488 DOI:10.13406/j.cnki.cyxb.003380

登录浏览全文

4963

注册一个新账户 忘记密码

参考文献

基金资助

四川省科技计划资助项目(2022YFS0616)

泸州市科技计划资助(2023SYF112)

AI Summary AI Mindmap
PDF (2885KB)

45

访问

0

被引

详细

导航
相关文章

AI思维导图

/