Mohammadi Soheil, Jahanshahi Ali, Shahrabi Farahani Mohammad, Salehi Mohammad Amin, Frounchi Negin, Guermazi Ali
Mallinckrodt Institute of Radiology, Washington University in St. Louis, Saint Louis, Missouri, United States of America.
Social Determinants of Health Research Center, Trauma Institute, Guilan University of Medical Sciences, Rasht, Iran.
PLoS One. 2025 Jun 24;20(6):e0326339. doi: 10.1371/journal.pone.0326339. eCollection 2025.
The aim was to systematically review the literature and perform a meta-analysis to estimate the performance of artificial intelligence (AI) algorithms in detecting meniscal injuries.
A systematic search was performed in the Scopus, PubMed, EBSCO, Cinahl, Web of Science, IEEE Xplore, and Cochrane Central databases on July, 2024. The included studies' reporting quality and risk of bias were evaluated using the Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD) and the Prediction Model Study Risk of Bias Assessment Tool (PROBAST), respectively. Also, a meta-analysis was done using contingency tables to estimate diagnostic performance metrics (sensitivity and specificity), and a meta-regression analysis was performed to investigate the effect of the following variables on the main outcome: imaging view, data augmentation and transfer learning usage, and presence of meniscal tear in the injury, with a corresponding 95% confidence interval (CI) and a P-value of 0.05 as a threshold for significance.
Among 28 included studies, 92 contingency tables were extracted from 15 studies. The reference standard of the studies were mostly expert radiologists, orthopedics, or surgical reports. The pooled sensitivity and specificity for AI algorithms on internal validation were 81% (95% CI: 78, 85), and 78% (95% CI: 72, 83), and for clinicians on internal validation were 85% (95% CI: 76, 91), and 88% (95% CI: 83, 92), respectively. The pooled sensitivity and specificity for studies validating algorithms with an external test set were 82% (95% CI: 74, 88), and 88% (95% CI: 84, 91), respectively.
The results of this study imply the lower diagnostic performance of AI-based algorithms in knee meniscal injuries compared with clinicians.
本研究旨在系统回顾文献并进行荟萃分析，以评估人工智能（AI）算法在检测半月板损伤方面的性能。
2024年7月，在Scopus、PubMed、EBSCO、Cinahl、Web of Science、IEEE Xplore和Cochrane Central数据库中进行了系统检索。分别使用个体预后或诊断多变量预测模型的透明报告（TRIPOD）和预测模型研究偏倚风险评估工具（PROBAST）评估纳入研究的报告质量和偏倚风险。此外，使用列联表进行荟萃分析以估计诊断性能指标（敏感性和特异性），并进行荟萃回归分析以研究以下变量对主要结局的影响：成像视图、数据增强和迁移学习的使用，以及损伤中半月板撕裂的存在情况，相应的95%置信区间（CI）和P值为0.05作为显著性阈值。
在纳入的28项研究中，从15项研究中提取了92个列联表。这些研究的参考标准大多是专家放射科医生、骨科医生或手术报告。AI算法在内部验证中的合并敏感性和特异性分别为 81%（95%CI：78，85）和78%（95%CI：72，83），临床医生在内部验证中的合并敏感性和特异性分别为85%（95%CI：76，91）和88%（95%CI：83，92）。使用外部测试集验证算法的研究的合并敏感性和特异性分别为82%（95%CI：74，88）和88%（95%CI：84，91）。
本研究结果表明，与临床医生相比，基于AI的算法在膝关节半月板损伤中的诊断性能较低。
