文献速递结核与非结核分枝杆菌艾滋病与性传播感染

深度学习胸片分析软件作为肺结核分诊试验:个体患者数据诊断准确性Meta分析

Chest X-ray Analysis With Deep Learning-Based Software as a Triage Test for Pulmonary Tuberculosis: An Individual Patient Data Meta-Analysis of Diagnostic Accuracy.
PubMed 文献 · Clin Infect Dis · 2022-01-01

该个体患者数据Meta分析纳入4项研究3727例因结核症状就诊的患者,用三种深度学习CAD软件(CAD4TBv6、Lunit、qXRv2)重新分析胸片。在90%汇总敏感度下,三种软件汇总特异度分别为56.9%、54.1%、60.5%。HIV感染者和涂片阴性结核患者的敏感度低于对照人群,且不同研究间准确性变异大。

要点

  • CAD软件在90%敏感度下特异度约54%-61%,准确性与人阅片者相似。
  • HIV感染者中CAD4TBv6和qXRv2敏感度分别降低13.4%,Lunit无显著差异。
  • 涂片阴性结核患者中三种软件敏感度降低12.3%-17.2%。

核心结论

  • CAD胸片分析作为高敏感度结核排除试验时,需从本患者人群确定阈值并按HIV和涂片状态分层。

研究设计与样本

  • 个体患者数据Meta分析,纳入4项研究的3727例因结核症状就诊患者。
  • 以培养或核酸扩增试验为参考标准,用三种CAD软件重新分析胸片。
  • 采用多变量Meta回归识别影响准确性的特征。

主要发现

  • 90%汇总敏感度下,汇总特异度:CAD4TBv6为56.9%(95%CI 51.7-61.9),Lunit为54.1%(95%CI 44.6-63.3),qXRv2为60.5%(95%CI 51.7-68.6)。
  • HIV感染者与未感染者相比,汇总敏感度绝对差异:CAD4TBv6为-13.4%(-21.1,-6.9),Lunit为+2.2%(-3.6,+6.3),qXRv2为-13.4%(-21.5,-6.6)。
  • 涂片阴性 vs 涂片阳性结核,汇总敏感度绝对差异:CAD4TBv6为-12.3%(-19.5,-6.1),Lunit为-17.2%(-24.6,-10.5),qXRv2为-16.6%(-24.4,-9.9)。
  • 准确性与人阅片者相似。

临床怎么用

  • CAD胸片可用于结核高敏感度排除,但需本地验证阈值并按HIV和涂片状态分层解读。
  • HIV感染者和涂片阴性患者中CAD敏感度下降,阴性结果需谨慎解读。

局限性

  • 仅纳入4项研究,患者均为因症状自我转诊者,外推性有限。

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: 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). METHODS: 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. RESULTS: 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. CONCLUSIONS: 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.

来源:Clin Infect Dis,查看原文。版权归原作者所有。

引用

  1. Tavaziva G, Harris M, Abidi SK, et al. Chest X-ray Analysis With Deep Learning-Based Software as a Triage Test for Pulmonary Tuberculosis: An Individual Patient Data Meta-Analysis of Diagnostic Accuracy. Clin Infect Dis. 2022. PMID: 34286831. doi:10.1093/cid/ciab639

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。