文献速递结核与非结核分枝杆菌

计算机辅助检测数字胸部X线阅读技术在有既往结核病史者中分诊活动性结核的性能

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.
PubMed 文献 · Clin Infect Dis · 2023-01-01

该研究回顾性分析了一项横断面活动性结核病例发现研究的数据,纳入1884名有≥1项当前结核症状且数据完整的≥15岁参与者,使用CAD4TB(v.7.0)和qXR(v.3.0)评估数字胸部X线。在有既往结核病史者中,两种CAD系统的特异性均明显低于无既往结核病史者,作者结论认为CAD系统作为结核分诊工具在有既往结核治疗史者中性能下降。

要点

  • 在有既往结核病史者中,CAD4TB特异性为24.0%,无既往结核病史者为60.3%。
  • 在有既往结核病史者中,qXR特异性为22.2%,无既往结核病史者为61.8%。
  • 作者结论认为CAD系统作为结核分诊工具在有既往结核治疗史者中性能下降。

核心结论

  • 作者结论认为,CAD系统作为结核分诊工具在有既往结核治疗史者中性能下降。

研究设计与样本

  • 对一项横断面活动性结核病例发现研究的数据进行回顾性分析。
  • 纳入标准为年龄≥15岁、有≥1项当前结核症状、且有既往结核病史、数字胸部X线和结核微生物学参考标准(Xpert MTB/RIF)的完整数据。
  • 数字胸部X线使用CAD4TB(v.7.0)和qXR(v.3.0)评估,采用在总体人群中达到90%灵敏度且最大化特异性的单一阈值,总体及按既往结核病史分层分析诊断准确性。
  • 共纳入1884名参与者,其中452名(24.0%)有既往结核病史。

主要发现

  • 有既往结核病史者中微生物学确诊结核的患病率为12.4%,无既往结核病史者为16.9%。
  • 使用CAD4TB时,有既往结核病史者的灵敏度和特异性分别为89.3%(95% CI:78.1-96.0%)和24.0%(19.9-28.5%),无既往结核病史者分别为90.5%(86.1-93.3%)和60.3%(57.4-63.0%)。
  • 使用qXR时,有既往结核病史者的灵敏度和特异性分别为94.6%(95% CI:85.1-98.9%)和22.2%(18.2-26.6%),无既往结核病史者分别为89.7%(85.1-93.2%)和61.8%(58.9-64.5%)。

关键数值与推荐

  • CAD4TB和qXR的阈值设定为在总体人群中达到90%灵敏度并最大化特异性。
  • 有既往结核病史者中,CAD4TB灵敏度89.3%(95% CI:78.1-96.0%)、特异性24.0%(19.9-28.5%);qXR灵敏度94.6%(95% CI:85.1-98.9%)、特异性22.2%(18.2-26.6%)。
  • 无既往结核病史者中,CAD4TB灵敏度90.5%(86.1-93.3%)、特异性60.3%(57.4-63.0%);qXR灵敏度89.7%(85.1-93.2%)、特异性61.8%(58.9-64.5%)。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

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.

来源:Clin Infect Dis,查看原文。版权归原作者所有。

引用

  1. Kagujje M, Kerkhoff AD, Nteeni M, et al. 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. Clin Infect Dis. 2023. PMID: 36004409. doi:10.1093/cid/ciac679

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。