Stop TB Partnership, Geneva, Switzerland; Department of Infectious Disease and Tropical Medicine, Heidelberg University Hospital, German Center for Infection Research (partner site), Heidelberg, Germany.
South Africa Medical Research Council, Pretoria, South Africa.
Lancet Digit Health. 2024 Sep;6(9):e605-e613. doi: 10.1016/S2589-7500(24)00118-3. Epub 2024 Jul 19.
Computer-aided detection (CAD) can help identify people with active tuberculosis left undetected. However, few studies have compared the performance of commercially available CAD products for screening in high tuberculosis and high HIV settings, and there is poor understanding of threshold selection across products in different populations. We aimed to compare CAD products' performance, with further analyses on subgroup performance and threshold selection.
We evaluated 12 CAD products on a case-control sample of participants from a South African tuberculosis prevalence survey. Only those with microbiological test results were eligible. The primary outcome was comparing products' accuracy using the area under the receiver operating characteristic curve (AUC) against microbiological evidence. Threshold analyses were performed based on pre-defined criteria and across all thresholds. We conducted subgroup analyses including age, gender, HIV status, previous tuberculosis history, symptoms presence, and current smoking status.
Of the 774 people included, 516 were bacteriologically negative and 258 were bacteriologically positive. Diverse accuracy was noted: Lunit and Nexus had AUCs near 0·9, followed by qXR, JF CXR-2, InferRead, Xvision, and ChestEye (AUCs 0·8-0·9). XrayAME, RADIFY, and TiSepX-TB had AUC under 0·8. Thresholds varied notably across these products and different versions of the same products. Certain products (Lunit, Nexus, JF CXR-2, and qXR) maintained high sensitivity (>90%) across a wide threshold range while reducing the number of individuals requiring confirmatory diagnostic testing. All products generally performed worst in older individuals, people with previous tuberculosis, and people with HIV. Variations in thresholds, sensitivity, and specificity existed across groups and settings.
Several previously unevaluated products performed similarly to those evaluated by WHO. Thresholds differed across products and demographic subgroups. The rapid emergence of products and versions necessitates a global strategy to validate new versions and software to support CAD product and threshold selections.
Government of Canada.
计算机辅助检测（CAD）可帮助发现未被检出的活动性肺结核患者。然而，鲜有研究比较在高结核和高艾滋病毒环境下商业 CAD 产品的筛查性能，且不同人群中对产品阈值的选择理解欠佳。我们旨在比较 CAD 产品的性能，并进一步分析亚组性能和阈值选择。
我们在南非结核患病率调查的病例对照样本中评估了 12 种 CAD 产品。仅纳入具有微生物学检测结果的参与者。主要结局是使用受试者工作特征曲线（ROC）下面积（AUC）比较产品的准确性，与微生物学证据相对比。根据预定义标准和所有阈值进行了阈值分析。我们进行了亚组分析，包括年龄、性别、艾滋病毒状态、既往结核病史、症状存在和当前吸烟状况。
774 人中，516 人为微生物学阴性，258 人为微生物学阳性。准确性存在差异：Lunit 和 Nexus 的 AUC 接近 0.9，其次是 qXR、JF CXR-2、InferRead、Xvision 和 ChestEye（AUC 0.8-0.9）。XrayAME、RADIFY 和 TiSepX-TB 的 AUC 低于 0.8。这些产品和同一产品的不同版本之间的阈值差异显著。某些产品（Lunit、Nexus、JF CXR-2 和 qXR）在较宽的阈值范围内保持了较高的敏感性（>90%），同时减少了需要确诊性诊断检测的人数。所有产品在年龄较大、既往有结核病史和艾滋病毒感染者中的表现一般较差。在不同人群和不同环境中，阈值、敏感性和特异性存在差异。
一些之前未评估的产品与世卫组织评估的产品性能相当。不同产品之间以及不同人口统计学亚组之间阈值不同。产品和版本的快速出现需要制定全球策略来验证新版本，并为 CAD 产品和阈值选择提供软件支持。
加拿大政府。
