当前位置: X-MOL 学术Eur. Respir. J. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Accuracy of CAD4TB (Computer-Aided Detection for Tuberculosis) on paediatric chest radiographs
European Respiratory Journal ( IF 16.6 ) Pub Date : 2024-11-07
Edem, V. F., Nkereuwem, E., Agbla, S. C., Owusu, S. A., Sillah, A. K., Saidy, B., Jallow, M. B., Forson, A. G., Egere, U., Kampmann, B., Togun, T.

Background

Computer-aided detection (CAD) systems hold promise for improving tuberculosis (TB) detection on digital chest radiographs. However, data on their performance in exclusively paediatric populations are scarce.

Methods

We conducted a retrospective diagnostic accuracy study evaluating the performance of CAD4TBv7 (Computer-Aided Detection for Tuberculosis version 7) using digital chest radiographs from well-characterised cohorts of Gambian children aged <15 years with presumed pulmonary TB. The children were consecutively recruited between 2012 and 2022. We measured CAD4TBv7 performance against a microbiological reference standard (MRS) of confirmed TB, and also performed Bayesian latent class analysis (LCA) to address the inherent limitations of the MRS in children. Diagnostic performance was assessed using the area under the receiver operating characteristic curve (AUROC) and point estimates of sensitivity and specificity.

Results

A total of 724 children were included in the analysis, with confirmed TB in 58 (8%), unconfirmed TB in 145 (20%) and unlikely TB in 521 (72%). Using the MRS, CAD4TBv7 showed an AUROC of 0.70 (95% CI 0.60–0.79), and demonstrated sensitivity and specificity of 19.0% (95% CI 11–31%) and 99.0% (95% CI 98.0–100.0%), respectively. Applying Bayesian LCA with the assumption of conditional independence between tests, sensitivity and specificity estimates for CAD4TBv7 were 42.7% (95% CrI 29.2–57.5%) and 97.9% (95% CrI 96.6–98.8%), respectively. When allowing for conditional dependence between culture and Xpert assay, CAD4TBv7 demonstrated a sensitivity of 50.3% (95% CrI 32.9–70.0%) and specificity of 98.0% (95% CrI 96.7–98.9%).

Conclusion

Although CAD4TBv7 demonstrated high specificity, its suboptimal sensitivity underscores the crucial need for optimisation of CAD4TBv7 for detecting TB in children.



中文翻译:


儿科胸片上 CAD4TB(结核病计算机辅助检测)的准确性


 背景


计算机辅助检测 (CAD) 系统有望改善数字胸片上的结核病 (TB) 检测。然而,关于它们在儿科人群中的表现的数据很少。

 方法


我们进行了一项回顾性诊断准确性研究,使用数字胸片评估了 CAD4TBv7 (结核病计算机辅助检测第 7 版) 的性能,这些数字胸片来自年龄 <15 岁、疑似肺结核的冈比亚儿童的特征明确队列。这些孩子是在 2012 年至 2022 年间连续招募的。我们根据确诊 TB 的微生物参考标准 (MRS) 测量了 CAD4TBv7 的性能,并进行了贝叶斯潜在类别分析 (LCA) 以解决儿童 MRS 的固有局限性。使用受试者工作特征曲线下面积 (AUROC) 和敏感性和特异性的点估计值评估诊断性能。

 结果


分析共纳入 724 名儿童,其中 58 名 (8%) 确诊结核病,145 名 (20%) 未确诊结核病,521 名 (72%) 疑似结核病。使用 MRS,CAD4TBv7 显示 AUROC 为 0.70 (95% CI 0.60-0.79),敏感性和特异性分别为 19.0% (95% CI 11-31%) 和 99.0% (95% CI 98.0-100.0%)。应用贝叶斯 LCA 并假设测试之间的条件独立性,CAD4TBv7 的敏感性和特异性估计分别为 42.7% (95% CrI 29.2-57.5%) 和 97.9% (95% CrI 96.6-98.8%)。当允许培养和 Xpert 检测之间的条件依赖性时,CAD4TBv7 的灵敏度为 50.3% (95% CrI 32.9–70.0%) 和 98.0% (95% CrI 96.7–98.9%)。

 结论


尽管 CAD4TBv7 表现出高特异性,但其次优的敏感性凸显了优化 CAD4TBv7 以检测儿童结核病的迫切需求。

更新日期:2024-11-07
down
wechat
bug