Logistic LASSO regression for the diagnosis of breast cancer using clinical demographic data and the BI-RADS lexicon for ultrasonography.
Logistic LASSO regression for the diagnosis of breast cancer using clinical demographic data and the BI-RADS lexicon for ultrasonography.
复制标题
DOI：
10.14366/usg.16045
复制
发表时间：
2018-01
期刊：
影响因子：
--
通讯作者：
Kim J
中科院分区：
文献类型：
--
作者：
Kim SM;Kim Y;Jeong K;Jeong H;Kim J
本研究的目的是比较使用两种不同的回归模型预测乳腺癌的图像分析的性能，并评估将临床和人口统计数据 (CDD) 纳入图像分析以改善乳腺癌诊断的有用性。这项研究包括来自 139 名患者的 139 个实体肿块，这些患者在 2009 年 6 月至 2010 年 4 月期间接受了超声引导的核心活检并进行了 CDD。三位乳腺放射科医生回顾性审查了 139 个乳腺肿块，并使用乳腺影像报告和数据系统 (BI-RADS) 词典描述了每个病变。我们应用并比较了两种回归方法——逐步 Logistic (SL) 回归和 Logistic 最小绝对收缩和选择算子 (LASSO) 回归，其中 BI-RADS 描述符和 CDD 用作协变量。我们研究了这些回归方法的性能以及放射科医生在测试错误分类误差和测试曲线下面积 (AUC) 方面的一致性。无论协变量中是否包含 CDD，Logistic LASSO 回归在测试误分类误差（无 CDD 时为 0.234 vs. 0.253；有 CDD 时为 0.196 vs. 0.258）和 AUC（无 CDD 时为 0.785 vs. 0.759；无 CDD 时为 0.873 vs. 0.735）方面均优于 SL 回归（P<0.05）。与CDD）。然而，在测试错误分类错误（无 CDD 时为 0.234 vs. 0.168；有 CDD 时为 0.196 vs. 0.088）和无 CDD 的 AUC（0.785 vs. 0.844，P<0.001）方面，其一致性较差（P<0.05），但与有 CDD 的 AUC（0.873 vs. 0.873 vs. 0.001）相当。 0.880, P=0.141）。基于 BI-RADS 描述符和 CDD 的 Logistic LASSO 回归在预测乳腺癌的存在方面表现出比 SL 更好的性能。使用 CDD 作为 BI-RADS 描述符的补充，使用逻辑 LASSO 回归显着改善了乳腺癌的预测。
The aim of this study was to compare the performance of image analysis for predicting breast cancer using two distinct regression models and to evaluate the usefulness of incorporating clinical and demographic data (CDD) into the image analysis in order to improve the diagnosis of breast cancer. This study included 139 solid masses from 139 patients who underwent a ultrasonography-guided core biopsy and had available CDD between June 2009 and April 2010. Three breast radiologists retrospectively reviewed 139 breast masses and described each lesion using the Breast Imaging Reporting and Data System (BI-RADS) lexicon. We applied and compared two regression methods-stepwise logistic (SL) regression and logistic least absolute shrinkage and selection operator (LASSO) regression-in which the BI-RADS descriptors and CDD were used as covariates. We investigated the performances of these regression methods and the agreement of radiologists in terms of test misclassification error and the area under the curve (AUC) of the tests. Logistic LASSO regression was superior (P<0.05) to SL regression, regardless of whether CDD was included in the covariates, in terms of test misclassification errors (0.234 vs. 0.253, without CDD; 0.196 vs. 0.258, with CDD) and AUC (0.785 vs. 0.759, without CDD; 0.873 vs. 0.735, with CDD). However, it was inferior (P<0.05) to the agreement of three radiologists in terms of test misclassification errors (0.234 vs. 0.168, without CDD; 0.196 vs. 0.088, with CDD) and the AUC without CDD (0.785 vs. 0.844, P<0.001), but was comparable to the AUC with CDD (0.873 vs. 0.880, P=0.141). Logistic LASSO regression based on BI-RADS descriptors and CDD showed better performance than SL in predicting the presence of breast cancer. The use of CDD as a supplement to the BI-RADS descriptors significantly improved the prediction of breast cancer using logistic LASSO regression.