Wu Yirong, Liu Jie, Del Rio Alejandro Munoz, Page David C, Alagoz Oguzhan, Peissig Peggy, Onitilo Adedayo A, Burnside Elizabeth S
Dept. of Radiology, UW Madison, WI, USA.
Dept. of Computer Science, UW Madison, WI, USA.
Proc SPIE Int Soc Opt Eng. 2015 Feb 21;9416. doi: 10.1117/12.2081954. Epub 2015 Mar 17.
Combining imaging and genetic information to predict disease presence and behavior is being codified into an emerging discipline called "radiogenomics." Optimal evaluation methodologies for radiogenomics techniques have not been established. We aim to develop a clinical decision framework based on utility analysis to assess prediction models for breast cancer. Our data comes from a retrospective case-control study, collecting Gail model risk factors, genetic variants (single nucleotide polymorphisms-SNPs), and mammographic features in Breast Imaging Reporting and Data System (BI-RADS) lexicon. We first constructed three logistic regression models built on different sets of predictive features: (1) Gail, (2) Gail+SNP, and (3) Gail+SNP+BI-RADS. Then, we generated ROC curves for three models. After we assigned utility values for each category of findings (true negative, false positive, false negative and true positive), we pursued optimal operating points on ROC curves to achieve maximum expected utility (MEU) of breast cancer diagnosis. We used McNemar's test to compare the predictive performance of the three models. We found that SNPs and BI-RADS features augmented the baseline Gail model in terms of the area under ROC curve (AUC) and MEU. SNPs improved sensitivity of the Gail model (0.276 . 0.147) and reduced specificity (0.855 . 0.912). When additional mammographic features were added, sensitivity increased to 0.457 and specificity to 0.872. SNPs and mammographic features played a significant role in breast cancer risk estimation (p-value < 0.001). Our decision framework comprising utility analysis and McNemar's test provides a novel framework to evaluate prediction models in the realm of radiogenomics.
将影像信息与基因信息相结合以预测疾病的存在及发展情况,正被编纂成一门名为“放射基因组学”的新兴学科。放射基因组学技术的最佳评估方法尚未确立。我们旨在基于效用分析开发一个临床决策框架,以评估乳腺癌预测模型。我们的数据来自一项回顾性病例对照研究,收集了盖尔模型风险因素、基因变异(单核苷酸多态性-SNP)以及乳腺影像报告和数据系统(BI-RADS)词典中的乳腺钼靶特征。我们首先基于不同的预测特征集构建了三个逻辑回归模型:(1)盖尔模型,(2)盖尔模型+SNP,以及(3)盖尔模型+SNP+BI-RADS。然后,我们为这三个模型生成了ROC曲线。在为每类结果(真阴性、假阳性、假阴性和真阳性)赋予效用值后,我们在ROC曲线上寻找最优操作点,以实现乳腺癌诊断的最大期望效用(MEU)。我们使用麦克尼马尔检验来比较这三个模型的预测性能。我们发现,SNP和BI-RADS特征在ROC曲线下面积(AUC)和MEU方面增强了基线盖尔模型。SNP提高了盖尔模型的敏感性(0.276对0.147),并降低了特异性(0.855对0.912)。当加入额外的乳腺钼靶特征时,敏感性增加到0.457,特异性增加到0.872。SNP和乳腺钼靶特征在乳腺癌风险评估中发挥了重要作用(p值<0.001)。我们包含效用分析和麦克尼马尔检验的决策框架为放射基因组学领域评估预测模型提供了一个新的框架。