机器学习胸片软件在基层与急诊的前瞻性验证研究
本研究在英国一家医院连续纳入2015年基层转诊和急诊的1960例胸片,以两名胸部放射科专家共识读片为参考标准,评估AI算法Lunit INSIGHT CXR的诊断性能。AI在急诊和基层数据集中AUROC分别为0.881-0.999和0.881-0.998,除胸腔积液外各征象无差异。结论认为AI能准确一致区分正常与主要胸部异常,可作分诊工具。
要点
- AI对正常与10种常见胸片征象的AUROC均较高,可辅助分诊。
- 基层与急诊数据集性能基本一致,仅胸腔积液AUROC有差异。
- 研究为单中心回顾性验证,需多中心前瞻性确认。
核心结论
- AI算法能准确一致区分正常与主要胸部异常,在急诊和基层均适用。
- AI可作为胸片分诊工具,辅助放射科医生优先处理异常病例。
研究设计与样本
- 单中心回顾性验证研究,纳入2015年英国一家医院连续1960例胸片(基层992例,急诊968例)。
- 参考标准为两名经验>20年的胸部放射科专家独立共识读片。
- 评估AI算法Lunit INSIGHT CXR,计算正常及10种常见征象的AUROC。
诊断标准与关键数值
- AI对急诊数据集AUROC为0.881-0.999,对基层数据集AUROC为0.881-0.998。
- 基层与急诊数据集各征象AUROC无差异,仅胸腔积液有差异(0.954 vs 0.988,p<0.001)。
- 评估征象包括肺不张、纤维化、钙化、实变、肺结节、心脏增大、纵隔增宽、胸腔积液、气胸、气腹。
临床应用与阅片要点
- AI可用于胸片分诊,优先标记异常病例,提高放射科工作效率。
- 胸腔积液在基层与急诊性能有差异,解读时需注意不同场景下的阈值可能不同。
局限性
- 单中心回顾性研究,结果外推需谨慎。
- 参考标准为两名专家共识,未采用多读者独立评估。
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
AIM: To evaluate the performance of a machine learning based algorithm tool for chest radiographs (CXRs), applied to a consecutive cohort of historical clinical cases, in comparison to expert chest radiologists.
MATERIALS AND METHODS: The study comprised 1,960 consecutive CXR from primary care referrals and the emergency department (992 and 968 cases respectively), obtained in 2015 at a UK hospital. Two chest radiologists, each with >20 years of experience independently read all studies in consensus to serve as a reference standard. A chest artificial intelligence (AI) algorithm, Lunit INSIGHT CXR, was run on the CXRs, and results were correlated with those by the expert readers. The area under the receiver operating characteristic curve (AUROC) was calculated for the normal and 10 common findings: atelectasis, fibrosis, calcification, consolidation, lung nodules, cardiomegaly, mediastinal widening, pleural effusion, pneumothorax, and pneumoperitoneum.
RESULTS: The ground truth annotation identified 398 primary care and 578 emergency department datasets containing pathologies. The AI algorithm showed AUROC of 0.881-0.999 in the emergency department dataset and 0.881-0.998 in the primary care dataset. The AUROC for each of the findings between the primary care and emergency department datasets did not differ, except for pleural effusion (0.954 versus 0.988, p<0.001).
CONCLUSIONS: The AI algorithm can accurately and consistently differentiate normal from major thoracic abnormalities in both acute and non-acute settings, and can serve as a triage tool.
引用
- van Beek, Ahn, Kim, et al. Validation study of machine-learning chest radiograph software in primary and emergency medicine. Clin Radiol. 2022. PMID: 36171164. doi:10.1016/j.crad.2022.08.129
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。