McGill International TB Centre, Research Institute of the McGill University Health Centre, Montreal, Canada.
Clinical Addiction Research and Education Unit, Section of General Internal Medicine, Department of Medicine, Boston University School of Medicine and Boston Medical Center, Boston, Massachusetts, USA.
Clin Infect Dis. 2022 Apr 28;74(8):1390-1400. doi: 10.1093/cid/ciab639.
Automated radiologic analysis using computer-aided detection software (CAD) could facilitate chest X-ray (CXR) use in tuberculosis diagnosis. There is little to no evidence on the accuracy of commercially available deep learning-based CAD in different populations, including patients with smear-negative tuberculosis and people living with human immunodeficiency virus (HIV, PLWH).
We collected CXRs and individual patient data (IPD) from studies evaluating CAD in patients self-referring for tuberculosis symptoms with culture or nucleic acid amplification testing as the reference. We reanalyzed CXRs with three CAD programs (CAD4TB version (v) 6, Lunit v3.1.0.0, and qXR v2). We estimated sensitivity and specificity within each study and pooled using IPD meta-analysis. We used multivariable meta-regression to identify characteristics modifying accuracy.
We included CXRs and IPD of 3727/3967 participants from 4/7 eligible studies. 17% (621/3727) were PLWH. 17% (645/3727) had microbiologically confirmed tuberculosis. Despite using the same threshold score for classifying CXR in every study, sensitivity and specificity varied from study to study. The software had similar unadjusted accuracy (at 90% pooled sensitivity, pooled specificities were: CAD4TBv6, 56.9% [95% confidence interval {CI}: 51.7-61.9]; Lunit, 54.1% [95% CI: 44.6-63.3]; qXRv2, 60.5% [95% CI: 51.7-68.6]). Adjusted absolute differences in pooled sensitivity between PLWH and HIV-uninfected participants were: CAD4TBv6, -13.4% [-21.1, -6.9]; Lunit, +2.2% [-3.6, +6.3]; qXRv2: -13.4% [-21.5, -6.6]; between smear-negative and smear-positive tuberculosis was: were CAD4TBv6, -12.3% [-19.5, -6.1]; Lunit, -17.2% [-24.6, -10.5]; qXRv2, -16.6% [-24.4, -9.9]. Accuracy was similar to human readers.
For CAD CXR analysis to be implemented as a high-sensitivity tuberculosis rule-out test, users will need threshold scores identified from their own patient populations and stratified by HIV and smear status.
使用计算机辅助检测软件（CAD）进行自动化放射学分析，可以促进在结核病诊断中使用胸部 X 光（CXR）。目前，在不同人群中，包括涂片阴性结核病患者和人类免疫缺陷病毒（HIV，PLWH）感染者，商业化的基于深度学习的 CAD 的准确性证据很少或没有。
我们从评估 CAD 在自我报告结核病症状的患者中的研究中收集了 CXR 和个体患者数据（IPD），这些研究以培养或核酸扩增检测作为参考。我们使用三种 CAD 程序（CAD4TB 版本（v）6、Lunit v3.1.0.0 和 qXR v2）重新分析了 CXR。我们在每个研究中估计了敏感性和特异性，并使用 IPD 荟萃分析进行了汇总。我们使用多变量荟萃回归来确定特征对准确性的影响。
我们纳入了来自 4/7 项合格研究的 3727/3967 名参与者的 CXR 和 IPD。17%（621/3727）为 PLWH。17%（645/3727）有微生物学证实的结核病。尽管在每项研究中都使用相同的阈值评分来对 CXR 进行分类，但敏感性和特异性在研究之间有所不同。该软件的未调整准确性相似（在 90%的汇总敏感性时，汇总特异性分别为：CAD4TBv6，56.9%[95%置信区间（CI）：51.7-61.9%]；Lunit，54.1%[95%CI：44.6-63.3%]；qXRv2，60.5%[95%CI：51.7-68.6%]）。在 PLWH 和 HIV 未感染者之间，调整后的汇总敏感性的绝对差异分别为：CAD4TBv6，-13.4%[-21.1，-6.9%]；Lunit，+2.2%[-3.6，+6.3%]；qXRv2：-13.4%[-21.5，-6.6%]；在涂片阴性和涂片阳性结核病之间，CAD4TBv6：-12.3%[-19.5，-6.1%]；Lunit，-17.2%[-24.6，-10.5%]；qXRv2，-16.6%[-24.4，-9.9%]。准确性与人类读者相似。
为了将 CAD CXR 分析作为一种高灵敏度的结核病排除试验实施，用户将需要根据自身患者人群和 HIV 及涂片状态确定阈值评分。
Zotero 插件