文献速递胸部技术与安全DR

人工智能评估床旁胸片上的气管插管位置:两家机构患者的验证

Artificial Intelligence for Assessment of Endotracheal Tube Position on Chest Radiographs: Validation in Patients From Two Institutions.
PubMed 文献 · AJR Am J Roentgenol · 2023-09-13

本回顾性研究在两家机构的三个患者样本中评估基于深度学习的人工智能系统检测气管插管存在及位置的表现;该系统识别插管存在的敏感度和特异度分别为100.0%和98.7%(样本B)、99.2%和94.5%(样本C),识别位置不当的敏感度和特异度分别为72.5%和92.0%(样本A)、78.9%和100.0%(样本B)、83.7%和99.1%(样本C);结论认为人工智能可在两家机构插管后及ICU胸片上识别位置不当的气管插管。

要点

  • AI识别气管插管存在的敏感度100.0%、特异度98.7%(样本B),敏感度99.2%、特异度94.5%(样本C)。
  • AI识别位置不当的敏感度72.5%、特异度92.0%(样本A),敏感度78.9%、特异度100.0%(样本B),敏感度83.7%、特异度99.1%(样本C)。
  • 以y轴气管插管尖端至隆突距离≤2 cm为阈值,AI识别危重位置的敏感度100.0%、特异度96.7%(样本A)、100.0%和100.0%(样本B)、100.0%和99.2%(样本C)。

核心结论

  • AI在两家机构插管后及ICU患者胸片上可识别位置不当的气管插管;自动识别可能允许更早重新定位并因此减少并发症。

研究设计与样本

  • 回顾性研究,纳入机构A样本A(2020年1月1日至3月31日插管后立即拍摄的539张胸片,505例患者,男293例、女212例,平均年龄63岁)、机构A样本B(2020年1月1日至1月3日ICU拍摄的637张胸片,302例患者,男157例、女145例,平均年龄66岁,带或不带气管插管)及机构B样本C(2020年1月1日至1月20日ICU拍摄的546张胸片,83例患者,男54例、女29例,平均年龄70岁,带或不带气管插管);使用商业深度学习人工智能系统识别气管插管存在并测量尖端至隆突距离,参考标准由人工读者判定。

诊断标准与关键数值

  • 气管插管位置正确的参考标准为气管插管尖端至隆突距离大于3 cm且小于7 cm(由人工读者判定);危重气管插管位置另行定义为尖端位于隆突下方或尖端至隆突距离≤1 cm;AI识别气管插管存在的敏感度和特异度分别为100.0%和98.7%(样本B)、99.2%和94.5%(样本C);AI识别位置不当的敏感度和特异度分别为72.5%和92.0%(样本A)、78.9%和100.0%(样本B)、83.7%和99.1%(样本C);以y轴尖端至隆突距离≤2 cm为阈值,AI识别危重位置的敏感度和特异度分别为100.0%和96.7%(样本A)、100.0%和100.0%(样本B)、100.0%和99.2%(样本C)。

临床应用与阅片要点

  • 作者指出自动人工智能识别胸片上位置不当的气管插管可能允许更早重新定位并因此减少并发症。

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. Timely and accurate interpretation of chest radiographs obtained to evaluate endotracheal tube (ETT) position is important for facilitating prompt adjustment if needed. OBJECTIVE. The purpose of our study was to evaluate the performance of a deep learning (DL)-based artificial intelligence (AI) system for detecting ETT presence and position on chest radiographs in three patient samples from two different institutions. METHODS. This retrospective study included 539 chest radiographs obtained immediately after ETT insertion from January 1 to March 31, 2020, in 505 patients (293 men, 212 women; mean age, 63 years) from institution A (sample A); 637 chest radiographs obtained from January 1 to January 3, 2020, in 302 patients (157 men, 145 women; mean age, 66 years) in the ICU (with or without an ETT) from institution A (sample B); and 546 chest radiographs obtained from January 1 to January 20, 2020, in 83 patients (54 men, 29 women; mean age, 70 years) in the ICU (with or without an ETT) from institution B (sample C). A commercial DL-based AI system was used to identify ETT presence and measure ETT tip-to-carina distance (TCD). The reference standard for proper ETT position was TCD between greater than 3 cm and less than 7 cm, determined by human readers. Critical ETT position was separately defined as ETT tip below the carina or TCD of 1 cm or less. ROC analysis was performed. RESULTS. AI had sensitivity and specificity for identification of ETT presence of 100.0% and 98.7% (sample B) and 99.2% and 94.5% (sample C). AI had sensitivity and specificity for identification of improper ETT position of 72.5% and 92.0% (sample A), 78.9% and 100.0% (sample B), and 83.7% and 99.1% (sample C). At a threshold y-axis TCD of 2 cm or less, AI had sensitivity and specificity for critical ETT position of 100.0% and 96.7% (sample A), 100.0% and 100.0% (sample B), and 100.0% and 99.2% (sample C). CONCLUSION. AI identified improperly positioned ETTs on chest radiographs obtained after ETT insertion as well as on chest radiographs obtained of patients in the ICU at two institutions. CLINICAL IMPACT. Automated AI identification of improper ETT position on chest radiographs may allow earlier repositioning and thereby reduce complications.

来源:AJR Am J Roentgenol,查看原文。版权归原作者所有。

引用

  1. An JY, Hwang EJ, Nam G, et al. Artificial Intelligence for Assessment of Endotracheal Tube Position on Chest Radiographs: Validation in Patients From Two Institutions. AJR Am J Roentgenol. 2023. PMID: 37703195. doi:10.2214/AJR.23.29769

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。