McGill International TB Centre, Research Institute of the McGill University Health Centre, Montreal, Canada; Department of Medicine, McGill University, Montreal, Canada; Respiratory Epidemiology and Clinical Research Unit, Centre for Outcomes Research and Evaluation, Research Institute of the McGill University Health Centre, Montreal, Canada.
McGill International TB Centre, Research Institute of the McGill University Health Centre, Montreal, Canada; Respiratory Epidemiology and Clinical Research Unit, Centre for Outcomes Research and Evaluation, Research Institute of the McGill University Health Centre, Montreal, Canada.
Int J Infect Dis. 2024 Oct;147:107221. doi: 10.1016/j.ijid.2024.107221. Epub 2024 Sep 2.
Computer-aided detection (CAD) software packages quantify tuberculosis (TB)-compatible chest X-ray (CXR) abnormality as continuous scores. In practice, a threshold value is selected for binary CXR classification. We assessed the diagnostic accuracy of an alternative approach to applying CAD for TB triage: incorporating CAD scores in multivariable modeling.
We pooled individual patient data from four studies. Separately, for two commercial CAD, we used logistic regression to model microbiologically confirmed TB. Models included CAD score, study site, age, sex, human immunodeficiency virus status, and prior TB. We compared specificity at target sensitivities ≥90% between the multivariable model and the current threshold-based approach for CAD use.
We included 4,733/5,640 (84%) participants with complete covariate data (median age 36 years; 45% female; 22% with prior TB; 22% people living with human immunodeficiency virus). A total of 805 (17%) had TB. Multivariable models demonstrated excellent performance (areas under the receiver operating characteristic curve [95% confidence interval]: software A, 0.91 [0.90-0.93]; software B, 0.92 [0.91-0.93]). Compared with threshold scores, multivariable models increased specificity (e.g., at 90% sensitivity, threshold vs model specificity [95% confidence interval]: software A, 71% [68-74%] vs 75% [74-77%]; software B, 69% [63-75%] vs 75% [74-77%]).
Using CAD scores in multivariable models outperformed the current practice of CAD-threshold-based CXR classification for TB diagnosis.
计算机辅助检测（CAD）软件包将肺结核（TB）兼容的胸部 X 射线（CXR）异常量化为连续分数。在实践中，会为二进制 CXR 分类选择一个阈值。我们评估了将 CAD 应用于 TB 分诊的替代方法的诊断准确性：将 CAD 分数纳入多变量模型。
我们汇总了来自四项研究的个体患者数据。对于两种商业 CAD，我们分别使用逻辑回归来对微生物学确诊的 TB 进行建模。模型包括 CAD 评分、研究地点、年龄、性别、人类免疫缺陷病毒状态和既往 TB。我们比较了多变量模型与当前基于 CAD 使用阈值的方法在目标敏感性≥90%时的特异性。
我们纳入了 4733/5640（84%）具有完整协变量数据的参与者（中位数年龄 36 岁；45%为女性；22%有既往 TB；22%人携带人类免疫缺陷病毒）。共有 805 人（17%）患有 TB。多变量模型表现出优异的性能（受试者工作特征曲线下面积[95%置信区间]：软件 A，0.91[0.90-0.93]；软件 B，0.92[0.91-0.93]）。与阈值评分相比，多变量模型提高了特异性（例如，在敏感性为 90%时，阈值与模型特异性[95%置信区间]：软件 A，71%[68-74%]与 75%[74-77%]；软件 B，69%[63-75%]与 75%[74-77%]）。
在多变量模型中使用 CAD 评分优于当前基于 CAD 阈值的 CXR 分类方法用于 TB 诊断。
