急诊医师与放射科医师应用人工智能辅助检测成人附肢骨骼骨折的评估:一项多中心横断面诊断研究
该多中心横断面诊断研究纳入了17家法国医学中心的600例成年创伤患者,评估AI系统辅助6名放射科医师和6名急诊医师检测附肢骨骼骨折的表现。AI辅助使医师敏感度提高8.7%、特异度提高4.1%,无骨折患者每人假阳性骨折数减少41.9%,平均阅片时间减少15.0%(差异未达统计学显著);AI新版本独立表现优于所有未辅助阅片者,AUC为0.94。
要点
- AI辅助使医师骨折检测敏感度提高8.7%、特异度提高4.1%,阅片速度未下降。
- 无骨折患者中AI辅助使每人假阳性骨折数减少41.9%。
- AI新版本独立AUC为0.94,优于所有未辅助阅片者(含骨骼专家放射科医师)。
核心结论
- AI辅助在不损失阅片速度的情况下提高了医师检测附肢骨骼骨折的敏感度和特异度。
研究设计与样本
- 多中心横断面诊断研究,回顾性纳入2016至2018年17家法国医学中心的600例成年创伤患者,AI系统此前基于60 170张创伤X线片训练并按70%训练、10%验证、20%测试随机划分。
关键影像表现/征象
- AI软件以高亮框形式标出AI检出的骨折位置,供医师判读时参考。
- X线片质量无法供人判读或仅含明显骨折者被排除。
诊断标准与关键数值
- AI辅助后医师敏感度提高8.7%(95%CI:3.1,14.2;P=.003,优效性检验)。
- AI辅助后医师特异度提高4.1%(95%CI:0.5,7.7;P<.001,非劣效性检验)。
- 无骨折患者中AI辅助使每人假阳性骨折数减少41.9%(95%CI:12.8,61.3;P=.02)。
- AI辅助使平均阅片时间减少15.0%(95%CI:-30.4,3.8;P=.12)。
- AI新版本独立AUC为0.94(95%CI:0.92,0.96),高于所有未辅助阅片者。
临床应用与阅片要点
- 原文未据此给出推荐。
- 作者结论为AI辅助可提高敏感度和特异度且不损失阅片速度。
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
Background The interpretation of radiographs suffers from an ever-increasing workload in emergency and radiology departments, while missed fractures represent up to 80% of diagnostic errors in the emergency department. Purpose To assess the performance of an artificial intelligence (AI) system designed to aid radiologists and emergency physicians in the detection and localization of appendicular skeletal fractures. Materials and Methods The AI system was previously trained on 60 170 radiographs obtained in patients with trauma. The radiographs were randomly split into 70% training, 10% validation, and 20% test sets. Between 2016 and 2018, 600 adult patients in whom multiview radiographs had been obtained after a recent trauma, with or without one or more fractures of shoulder, arm, hand, pelvis, leg, and foot, were retrospectively included from 17 French medical centers. Radiographs with quality precluding human interpretation or containing only obvious fractures were excluded. Six radiologists and six emergency physicians were asked to detect and localize fractures with (n = 300) and fractures without (n = 300) the aid of software highlighting boxes around AI-detected fractures. Aided and unaided sensitivity, specificity, and reading times were compared by means of paired Student t tests after averaging of performances of each reader. Results A total of 600 patients (mean age ± standard deviation, 57 years ± 22; 358 women) were included. The AI aid improved the sensitivity of physicians by 8.7% (95% CI: 3.1, 14.2; P = .003 for superiority) and the specificity by 4.1% (95% CI: 0.5, 7.7; P < .001 for noninferiority) and reduced the average number of false-positive fractures per patient by 41.9% (95% CI: 12.8, 61.3; P = .02) in patients without fractures and the mean reading time by 15.0% (95% CI: -30.4, 3.8; P = .12). Finally, stand-alone performance of a newer release of the AI system was greater than that of all unaided readers, including skeletal expert radiologists, with an area under the receiver operating characteristic curve of 0.94 (95% CI: 0.92, 0.96). Conclusion The artificial intelligence aid provided a gain of sensitivity (8.7% increase) and specificity (4.1% increase) without loss of reading speed. © RSNA, 2021 Online supplemental material is available for this article.
引用
- Duron L, Ducarouge A, Gillibert A, et al. Assessment of an AI Aid in Detection of Adult Appendicular Skeletal Fractures by Emergency Physicians and Radiologists: A Multicenter Cross-sectional Diagnostic Study. Radiology. 2021. PMID: 33944629. doi:10.1148/radiol.2021203886
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。