背景:乳腺癌患者病理完全缓解(pCR)和总生存期(OS)的预测模型的通用性需要不同的数据集。这项研究采用了四种机器学习模型,使用来自不同且服务不足的市中心人口的数据来预测长达7.5年的pCR和OS。
方法:人口统计,分期,肿瘤亚型,收入,保险状况,放射学报告的数据来自于在市中心卫生系统接受新辅助化疗的475例乳腺癌患者(2012年01月至2021年12月31日).Logistic回归,神经网络,随机森林,和梯度增强回归模型用于预测结果(pCR和OS),并进行五次交叉验证。
结果:pCR与年龄无关,种族,种族,肿瘤分期,诺丁汉等级,收入,和保险状况(p>0.05)。ER-/HER2+显示最高的pCR率,其次是三阴性,ER+/HER2+,和ER+/HER2-(所有p<0.05),肿瘤大小(p<0.003)和背景实质增强(BPE)(p<0.01)。机器学习模型排名为ER+/HER2-,ER-/HER2+,肿瘤大小,和BPE是pCR的最高预测因子(AUC=0.74-0.76)。操作系统与种族有关,pCR状态,肿瘤亚型,和保险状况(p<0.05),但不是种族和收入(p>0.05)。机器学习模型对肿瘤分期进行排名,pCR,节点阶段,和三阴性亚型作为OS的最高预测因子(AUC=0.83-0.85)。当按肿瘤亚型对种族和民族进行分组时,每种肿瘤亚型的OS和pCR均不因种族和民族而异(p>0.05)。
结论:肿瘤亚型和影像学特征是我们内城人群pCR的主要预测因子。保险状况,种族,肿瘤亚型和pCR与OS相关。机器学习模型准确预测pCR和OS。
Generalizability of predictive models for pathological complete response (pCR) and overall survival (OS) in breast cancer patients requires diverse datasets. This study employed four machine learning models to predict pCR and OS up to 7.5 years using data from a diverse and underserved inner-city population.
Demographics, staging, tumor subtypes, income, insurance status, and data from radiology reports were obtained from 475 breast cancer patients on neoadjuvant chemotherapy in an inner-city health system (01/01/2012 to 12/31/2021). Logistic regression, Neural Network, Random Forest, and Gradient Boosted Regression models were used to predict outcomes (pCR and OS) with fivefold cross validation.
pCR was not associated with age, race, ethnicity, tumor staging, Nottingham grade, income, and insurance status (p > 0.05). ER-/HER2+ showed the highest pCR rate, followed by triple negative, ER+/HER2+, and ER+/HER2- (all p < 0.05), tumor size (p < 0.003) and background parenchymal enhancement (BPE) (p < 0.01). Machine learning models ranked ER+/HER2-, ER-/HER2+, tumor size, and BPE as top predictors of pCR (AUC = 0.74-0.76). OS was associated with race, pCR status, tumor subtype, and insurance status (p < 0.05), but not ethnicity and incomes (p > 0.05). Machine learning models ranked tumor stage, pCR, nodal stage, and triple-negative subtype as top predictors of OS (AUC = 0.83-0.85). When grouping race and ethnicity by tumor subtypes, neither OS nor pCR were different due to race and ethnicity for each tumor subtype (p > 0.05).
Tumor subtypes and imaging characteristics were top predictors of pCR in our inner-city population. Insurance status, race, tumor subtypes and pCR were associated with OS. Machine learning models accurately predicted pCR and OS.