计算机辅助检测数字胸部 X 射线阅读技术在有既往结核病史人群中筛查活动性结核病的性能。
The Performance of Computer-Aided Detection Digital Chest X-ray Reading Technologies for Triage of Active Tuberculosis Among Persons With a History of Previous Tuberculosis.
机构信息
Tuberculosis Department, Centre for Infectious Disease Research in Zambia, Lusaka, Zambia.
Division of HIV, Infectious Diseases and Global Medicine Zuckerberg, San Francisco General Hospital and Trauma Center, University of California, San Francisco, San Francisco, California, USA.
出版信息
Clin Infect Dis. 2023 Feb 8;76(3):e894-e901. doi: 10.1093/cid/ciac679.
BACKGROUND
Digital chest X-ray (dCXR) computer-aided detection (CAD) technology uses lung shape and texture analysis to determine the probability of tuberculosis (TB). However, many patients with previously treated TB have sequelae, which also distort lung shape and texture. We evaluated the diagnostic performance of 2 CAD systems for triage of active TB in patients with previously treated TB.
METHODS
We conducted a retrospective analysis of data from a cross-sectional active TB case finding study. Participants ≥15 years, with ≥1 current TB symptom and complete data on history of previous TB, dCXR, and TB microbiological reference (Xpert MTB/RIF) were included. dCXRs were evaluated using CAD4TB (v.7.0) and qXR (v.3.0). We determined the diagnostic accuracy of both systems, overall and stratified by history of TB, using a single threshold for each system that achieved 90% sensitivity and maximized specificity in the overall population.
RESULTS
Of 1884 participants, 452 (24.0%) had a history of previous TB. Prevalence of microbiologically confirmed TB among those with and without history of previous TB was 12.4% and 16.9%, respectively. Using CAD4TB, sensitivity and specificity were 89.3% (95% CI: 78.1-96.0%) and 24.0% (19.9-28.5%) and 90.5% (86.1-93.3%) and 60.3% (57.4-63.0%) among those with and without previous TB, respectively. Using qXR, sensitivity and specificity were 94.6% (95% CI: 85.1-98.9%) and 22.2% (18.2-26.6%) and 89.7% (85.1-93.2%) and 61.8% (58.9-64.5%) among those with and without previous TB, respectively.
CONCLUSIONS
The performance of CAD systems as a TB triage tool is decreased among persons previously treated for TB.
背景
数字胸部 X 射线（dCXR）计算机辅助检测（CAD）技术使用肺形状和纹理分析来确定结核病（TB）的概率。然而，许多患有既往治疗性 TB 的患者有后遗症，这也会使肺形状和纹理变形。我们评估了两种 CAD 系统在既往治疗性 TB 患者中筛查活动性 TB 的诊断性能。
方法
我们对一项横断面活动性 TB 病例发现研究的数据进行了回顾性分析。参与者年龄≥15 岁，有≥1 种当前 TB 症状，并且有既往 TB 病史、dCXR 和 TB 微生物学参考（Xpert MTB/RIF）的完整数据。使用 CAD4TB（v.7.0）和 qXR（v.3.0）评估 dCXR。我们使用每个系统达到 90%的敏感性并在总体人群中最大化特异性的单一阈值，确定了两种系统的总体诊断准确性和按 TB 病史分层的诊断准确性。
结果
在 1884 名参与者中，452 名（24.0%）有既往 TB 病史。有既往 TB 病史和无既往 TB 病史的参与者中，微生物学确诊 TB 的患病率分别为 12.4%和 16.9%。使用 CAD4TB，敏感性和特异性分别为 89.3%（95%CI：78.1-96.0%）和 24.0%（19.9-28.5%）和 90.5%（86.1-93.3%）和 60.3%（57.4-63.0%）。使用 qXR，敏感性和特异性分别为 94.6%（95%CI：85.1-98.9%）和 22.2%（18.2-26.6%）和 89.7%（85.1-93.2%）和 61.8%（58.9-64.5%）。
结论
在既往接受过 TB 治疗的人群中，CAD 系统作为 TB 分诊工具的性能降低。
Zotero 插件