基于人工智能的髋部及骨盆X线骨折检测工具在多中心回顾性队列中的外部验证
该多中心回顾性诊断准确性研究纳入642例连续创伤患者,评估商用AI工具检测髋部及骨盆骨折的效能;总体敏感度87%、特异度86%,陈旧骨折特异度降至29%,股骨颈和转子间骨折敏感度高,骨盆和髋臼骨折敏感度中等。
要点
- 总体敏感度87%、特异度86%,但陈旧骨折病例特异度仅29%,假阳性风险高。
- 股骨颈骨折敏感度95%、转子间骨折92%,骨盆骨折82%、髋臼骨折58%。
- 漏诊集中于AO/OTA分型中单侧前骨盆弓(61A2.2)、股骨颈头下型(31B1)和简单转子间骨折(31A1)。
核心结论
- AI工具对髋部区域创伤X线片诊断准确性高,但陈旧骨折特异度明显降低,骨盆和髋臼骨折敏感度中等,漏诊多发生于细微AO/OTA骨折组。
研究设计与样本
- 多中心回顾性诊断准确性研究,纳入642例连续创伤患者,以会议后临床放射学报告为参考标准,按MRI、CT、X线的层级顺序综合判定,骨折按AO/OTA系统分类。
诊断标准与关键数值
- 总体敏感度87%[95%CI 83-91%],特异度86%[95%CI 82-89%];陈旧骨折特异度29%[95%CI 13-51%];股骨颈骨折敏感度95%[95%CI 88-98%];转子间骨折敏感度92%[95%CI 82-97%];骨盆骨折敏感度82%[95%CI 70-91%];髋臼骨折敏感度58%[95%CI 28-85%]。
临床应用与阅片要点
- 阅片时需注意AI工具在陈旧骨折病例中特异度明显降低,以及对骨盆和髋臼骨折敏感度中等,漏诊集中于AO/OTA分型中单侧前骨盆弓(61A2.2)、股骨颈头下型(31B1)和简单转子间骨折(31A1)。
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
OBJECTIVE: Artificial intelligence tools show promise in fracture detection but may be impaired by hidden stratification. We aim to evaluate the diagnostic accuracy of a commercially available AI tool for detecting hip and pelvic fractures, with emphasis on clinically relevant subgroups and AO/OTA fracture classifications.
MATERIALS AND METHODS: This retrospective multicenter diagnostic test accuracy study included consecutive trauma patients who underwent hip or pelvic radiography. The reference standard was based on post-conference clinical radiology reports, incorporating MRI, CT, and radiography in hierarchical order. Fractures were classified according to the AO/OTA system. Studied subgroups included surgical metal, degenerative disease, old fractures, radiographically occult fractures and fracture classification. Sensitivity and specificity were calculated with 95% confidence intervals.
RESULTS: Among 642 patients (median age 82 years), 262 (42%) had fractures. Overall sensitivity was 87% [83-91%] and specificity 86% [82-89%]. Specificity was reduced in cases with old fractures (29% [13-51%]). Sensitivity was high for femoral neck (95% [88-98%]) and trochanteric fractures (92% [82-97%]) and moderate for pelvic (82% [70-91%]) and acetabular fractures (58% [28-85%]). Within each segment the classifications with most missed fractures were unilateral anterior pelvic arch (61A2.2), subcapital femur neck (31B1), and simple trochanteric fractures (31A1).
CONCLUSION: In summary, while specificity was notably reduced in cases with old fractures and sensitivity was moderate for pelvic and acetabular fractures, the AI tool demonstrated high diagnostic accuracy for hip-region trauma radiographs, with most missed cases occurring among the subtle AO/OTA fracture groups.
引用
- Bruun FJ, Omaraee Y, Nybing JU, et al. External validation of an AI-Based fracture detection tool for hip and pelvic radiographs in a multicenter retrospective cohort. Eur J Radiol. 2026. PMID: 41830703. doi:10.1016/j.ejrad.2026.112778
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。