人工智能辅助BoneView在X线片上检测骨折的系统综述
该系统综述纳入8项原始研究,评估BoneView辅助阅片对骨折X线检测的诊断性能与阅片速度的影响。多数研究中BoneView使敏感度显著提高,但特异度和诊断比值比结果不一;4项研究评估报告时间,其中3项阅片速度更快,1项无变化。现有文献存在方法学质量担忧,需进一步研究异质性原因。
要点
- BoneView辅助阅片在多数研究中使骨折检测敏感度显著提高(p<0.05)。
- 特异度和诊断比值比结果不一,可无显著变化或显著升高或降低。
- BoneView似不损害阅片速度,3项研究显示阅片更快(平均快5.3-15.7秒,p≤0.046)。
核心结论
- BoneView似乎能提高敏感度,但特异度和总体诊断准确性的结果不一;现有文献存在方法学质量担忧,需进一步研究异质性原因;BoneView的使用似乎不损害阅片速度,甚至可能提高。
研究设计与样本
- 系统综述,检索Medline和Embase,纳入报告人工阅片在有/无BoneView时检测X线骨折诊断性能的原始研究,共纳入8项研究,评估研究质量并提取诊断准确性数据和阅片速度。
诊断标准与关键数值
- 敏感度和特异度存在异质性(p≤0.0001)。
- 在纳入研究的绝大多数阅片者中,使用BoneView评估X线片时敏感度显著更高(p<0.05)。
- 特异度和诊断比值比结果不一,可无显著变化或显著升高或降低。
- 4项研究评估报告时间;3项研究中BoneView阅片速度更快(平均快5.3-15.7秒,p≤0.046),1项研究无变化(p=0.12)。
临床应用与阅片要点
- BoneView辅助阅片可能提高骨折检测敏感度,但特异度变化不一,阅片时需结合临床综合判断。
- 使用BoneView似乎不损害阅片速度,甚至可能提高阅片速度。
- 现有文献存在方法学质量担忧,应用时需注意研究间异质性。
局限性
- 患者选择方面存在高偏倚风险(5项研究)。
- 参考标准方面存在高偏倚风险(1项研究)。
- 流程和时间方面存在高偏倚风险(3项研究)。
- 1项研究中对指数试验执行的适用性存在高度担忧。
- 敏感度和特异度存在异质性(p≤0.0001)。
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)。
英文原文(摘要)· 点击展开
PURPOSE: To systematically review the added value of the artificial intelligence tool BoneView in detecting fractures on radiographs.
METHOD: Medline and Embase were searched for original studies that reported the diagnostic performance of human reading in detecting fractures on radiographs with and without BoneView. Study quality was assessed. Diagnostic accuracy data and reading speed were extracted.
RESULTS: Eight studies were included. There was high risk of bias with respect to patient selection (5 studies), reference standard (1 study), and flow and timing (3 studies). There was high concern regarding the applicability of the execution of the index test in one study. Sensitivities and specificities were heterogeneous (p ≤ 0.0001). Sensitivity was significantly higher (p < 0.05) among the far majority of the readers in the included studies when radiographs were evaluated with BoneView. Specificities and diagnostic odds ratio results were mixed, with either no significant change or significant increase or decrease. Four studies assessed reporting time. In 3 studies, reading speed was faster with BoneView (mean of 5.3-15.7 s, p ≤ 0.046), whereas in one study there was no change (p = 0.12).
CONCLUSION: BoneView appears to improve sensitivity, whereas the results regarding specificity and overall diagnostic accuracy are mixed. There are methodological quality concerns in the existing literature and further research is needed to explore causes of heterogeneity. The use of BoneView appears not to compromise reading speed and may even improve it.
引用
- Kwee RM, Kwee TC. Artificial intelligence-assisted detection of fractures on radiographs with BoneView: a systematic review. Eur J Radiol. 2025. PMID: 40554942. doi:10.1016/j.ejrad.2025.112230
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。