文献速递呼吸衰竭与机械通气重症综合管理与镇静镇痛

基于面部图像卷积神经网络深度学习创建气管插管困难分类人工智能模型:一项观察性研究

Creation of an artificial intelligence model for intubation difficulty classification by deep learning (convolutional neural network) using face images: an observational study.
PubMed 文献 · J Intensive Care · 2021-05-06
一句话结论仰卧闭口侧位面部图像训练的CNN模型分类插管困难准确率80.5%、AUC 0.864,作者认为可能有助于经验不足人员在紧急情况下插管。

该观察性研究纳入2020年4月至8月在Yamagata大学医院择期手术患者,排除面部外观改变、颈部活动度改变或由麻醉经验不足3年医生插管者,术后次日起采集16种面部图像,由麻醉科医师将图像判为「容易」或「困难」,用卷积神经网络(CNN)将面部图像与插管困难关联建立AI分类模型。表现最佳的模型来自仰卧闭口侧位,准确率80.5%、敏感度81.8%、特异度83.3%、AUC 0.864(95%CI 0.731-0.969),类激活热图集中在颈部。作者认为该模型可能对经验不足的医务人员在紧急情况或全麻下气管插管有用。

要点

  • 16种面部图像中,仰卧闭口侧位图像建立的AI模型分类插管困难表现最佳:准确率80.5%、敏感度81.8%、特异度83.3%、AUC 0.864(95%CI 0.731-0.969)。
  • 类激活热图显示模型判断不依赖背景,集中在颈部,提示模型识别面部轮廓来判断插管困难。
  • 研究纳入2020年4月至8月在Yamagata大学医院择期手术患者,术后次日起采集16种面部图像。
  • 排除面部外观改变、颈部活动度改变的手术患者,以及由麻醉经验不足3年医生插管的患者。
  • 作者认为该AI模型可能有助于经验不足的医务人员在紧急情况或全麻下实施气管插管。

适用人群与场景

  • 2020年4月至8月在Yamagata大学医院择期手术的患者。
  • 排除面部外观改变的手术患者、颈部活动度改变的手术患者、由麻醉经验不足3年医生插管的患者。

研究设计与关键结果

  • 研究类型为观察性研究,纳入2020年4月至8月在Yamagata大学医院择期手术的患者,术后次日起采集16种面部图像。
  • 所有图像由麻醉科医师判为「容易」或「困难」,用CNN将面部图像与插管困难关联建立AI分类模型。
  • 16种图像中最佳模型来自仰卧闭口侧位:准确率80.5%、敏感度81.8%、特异度83.3%、AUC 0.864(95%CI 0.731-0.969),以中位AUC作为结果。
  • 类激活热图显示模型判断不依赖背景,集中在颈部,模型识别面部轮廓来判断插管困难。

证据类型、等级与局限

  • 证据类型:观察性研究。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 作者认为该AI模型可能对经验不足的医务人员在紧急情况或全麻下实施气管插管有用。

提炼说明

  • 本条依据论文摘要整理;摘要未涉及「诊断标准与关键阈值」「处置流程与药物剂量」「红旗征与不能漏的情况」「指南或共识出处」,故未列出这些栏目;全文请点「阅读原文」。
英文原文(摘要)· 点击展开

BACKGROUND: Tracheal intubation is the gold standard for securing the airway, and it is not uncommon to encounter intubation difficulties in intensive care units and emergency rooms. Currently, there is a need for an objective measure to assess intubation difficulties in emergency situations by physicians, residents, and paramedics who are unfamiliar with tracheal intubation. Artificial intelligence (AI) is currently used in medical imaging owing to advanced performance. We aimed to create an AI model to classify intubation difficulties from the patient's facial image using a convolutional neural network (CNN), which links the facial image with the actual difficulty of intubation.

METHODS: Patients scheduled for surgery at Yamagata University Hospital between April and August 2020 were enrolled. Patients who underwent surgery with altered facial appearance, surgery with altered range of motion in the neck, or intubation performed by a physician with less than 3 years of anesthesia experience were excluded. Sixteen different facial images were obtained from the patients since the day after surgery. All images were judged as "Easy"/"Difficult" by an anesthesiologist, and an AI classification model was created using deep learning by linking the patient's facial image and the intubation difficulty. Receiver operating characteristic curves of actual intubation difficulty and AI model were developed, and sensitivity, specificity, and area under the curve (AUC) were calculated; median AUC was used as the result. Class activation heat maps were used to visualize how the AI model classifies intubation difficulties.

RESULTS: The best AI model for classifying intubation difficulties from 16 different images was generated in the supine-side-closed mouth-base position. The accuracy was 80.5%; sensitivity, 81.8%; specificity, 83.3%; AUC, 0.864; and 95% confidence interval, [0.731-0.969], indicating that the class activation heat map was concentrated around the neck regardless of the background; the AI model recognized facial contours and identified intubation difficulties.

CONCLUSION: This is the first study to apply deep learning (CNN) to classify intubation difficulties using an AI model. We could create an AI model with an AUC of 0.864. Our AI model may be useful for tracheal intubation performed by inexperienced medical staff in emergency situations or under general anesthesia.

来源:J Intensive Care,查看原文。版权归原作者所有。

参考来源

  1. Hayasaka T, Kawano K, Kurihara K, et al. Creation of an artificial intelligence model for intubation difficulty classification by deep learning (convolutional neural network) using face images: an observational study. J Intensive Care. 2021. PMID: 33952341. doi:10.1186/s40560-021-00551-x

供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。