文献速递骨肌技术与安全DR

人工智能在平片骨折检测中的诊断准确性及其与临床医生的比较:系统综述与Meta分析

Artificial intelligence diagnostic accuracy in fracture detection from plain radiographs and comparing it with clinicians: a systematic review and meta-analysis.
PubMed 文献 · Clin Radiol · 2024-04-20

该系统综述与Meta分析纳入100项研究,评估AI算法在平片骨折检测中的性能。在83项提供混淆矩阵的研究中,AI敏感度为91.43%、特异度为92.12%,汇总ROC曲线下面积为0.968。AI与临床医生特异度相似,但AI敏感度倾向于更高(7.6%,p=0.07);放射科医生总体特异度高于AI。

要点

  • AI在平片骨折检测中汇总敏感度91.43%、特异度92.12%,汇总ROC曲线下面积0.968。
  • AI与临床医生特异度相似,AI敏感度倾向于更高(7.6%,p=0.07)。
  • 放射科医生总体及多个亚组特异度高于AI,FDR校正前对髋部骨折敏感度更高。

核心结论

  • 现有AI辅助工具可能在放射科医生不易获得的情况下显著改善诊疗;识别影响算法性能的因素可指导AI开发团队优化产品。

研究设计与样本

  • 系统综述与Meta分析,纳入100项评估AI算法在平片骨折检测中性能的研究,采用双变量回归方法合并性能,并用Meta回归分析影响算法性能的因素。

诊断标准与关键数值

  • 在83项提供混淆矩阵的研究中,AI算法检测骨折的敏感度为91.43%,特异度为92.12%,汇总ROC曲线下面积为0.968。
  • 经校正和错误发现率校正后,胫骨/腓骨(不含踝)骨折与AI敏感度较高相关(7.0%,p=0.004)。
  • 较新发表文献与AI特异度较高相关(5.5%,p=0.003),Xception架构与AI特异度较高相关(6.6%,p<0.001)。
  • AI与临床医生在骨折识别中特异度相似,AI敏感度倾向于更高(7.6%,p=0.07)。
  • 放射科医生总体及多个亚组中特异度高于AI,FDR校正前对髋部骨折敏感度更高。

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)。

英文原文(摘要)· 点击展开

PURPOSE: Fracture detection is one of the most commonly used and studied aspects of artificial intelligence (AI) in medicine. In this systematic review and meta-analysis, we aimed to summarize available literature and data regarding AI performance in fracture detection on plain radiographs and various factors affecting it.

METHODS: We systematically reviewed studies evaluating AI algorithms in detecting bone fractures in plain radiographs, combined their performance using meta-analysis (a bivariate regression approach), and compared it with that of clinicians. We also analyzed the factors potentially affecting algorithm performance using meta-regression.

RESULTS: Our analysis included 100 studies. In 83 studies with confusion matrices, AI algorithms showed a sensitivity of 91.43% and a specificity of 92.12% (Area under the summary receiver operator curve = 0.968). After adjustment and false discovery rate correction, tibia/fibula (excluding ankle) fractures were associated with higher (7.0%, p=0.004) AI sensitivity, while more recent publications (5.5%, p=0.003) and Xception architecture (6.6%, p<0.001) were associated with higher specificity. Clinicians and AI showed similar specificity in fracture identification, although AI leaned to higher sensitivity (7.6%, p=0.07). Radiologists, on the other hand, were more specific than AI overall and in several subgroups, and more sensitive to hip fractures before FDR correction.

CONCLUSIONS: Currently available AI aids could result in a significant improvement in care where radiologists are not readily available. Moreover, identifying factors affecting algorithm performance could guide AI development teams in their process of optimizing their products.

来源:Clin Radiol,查看原文。版权归原作者所有。

引用

  1. Nowroozi A, Salehi MA, Shobeiri P, et al. Artificial intelligence diagnostic accuracy in fracture detection from plain radiographs and comparing it with clinicians: a systematic review and meta-analysis. Clin Radiol. 2024. PMID: 38772766. doi:10.1016/j.crad.2024.04.009

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。