文献速递气道管理

人工智能在气道管理中的应用:叙述性综述

Artificial intelligence in airway management: a narrative review.
PubMed 文献 · Br J Anaesth · 2026-02-04

本叙述性综述通过截至2025年7月的结构化文献检索,考察人工智能在气道管理中的应用。AI在困难气道预测、视频喉镜辅助、危机情境认知支持、虚拟现实教学及机器人插管方面展现潜力,但仍面临阳性预测值偏低、算法可解释性不足和临床医生技能退化等挑战,应作为人类专业能力的补充而非替代。

要点

  • AI可通过面部识别、语音分析等多参数评估预测困难气道,阳性预测值优于传统床旁测试但仍不完美。
  • AI辅助视频喉镜可实时识别结构、引导操作并验证气管导管位置,可能减少并发症。
  • AI在危机情境中提供认知支持,但需警惕技能退化与黑箱算法问题,应坚持人机协作。

核心结论

  • AI在气道管理多个环节展现潜力,但应补充而非替代人类专业知识,理想模式为人机协作。

研究设计与样本

  • 叙述性综述,通过截至2025年7月的结构化文献检索完成。

主要发现

  • AI通过面部识别、语音分析和多参数评估预测困难气道,阳性预测值较传统床旁测试改善但仍不完美。
  • AI驱动的视频喉镜系统提供实时结构识别、操作引导和气管导管位置验证,可能减少并发症。
  • AI在关键场景中提供认知支持,包括减轻决策偏差、智能报警和确保指南依从。
  • AI增强的虚拟现实模拟为学习者提供个性化反馈的逼真练习环境。
  • AI算法引导的实验性机器人插管系统在受控环境中表现与专家相当,主要用于培训和远程应用。

临床怎么用

  • 可将AI作为困难气道预测和视频喉镜操作的辅助工具,但不应替代临床判断。
  • 在危机情境中利用AI认知支持减少决策偏差,同时保持对指南的遵循。
  • 使用AI教学工具时需注意防范临床医生技能退化,并优先选择可解释性较强的算法。

局限性

  • 低阳性预测值的基本挑战仍然存在,尽管水平有所降低。
  • 部分算法的黑箱性质限制透明度,广泛实施前需稳健验证。
  • 存在临床医生技能退化风险,需同步发展伦理框架和监管监督。

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)。

原文

This narrative review examines artificial intelligence (AI) applications in airway management through a structured literature search completed in July 2025. AI shows promise in predicting difficult airways through facial recognition, voice analysis, and multiparametric assessment. AI models demonstrate improved positive predictive values compared with conventional bedside tests, though prediction remains imperfect. The fundamental challenge of low positive predictive values persists, albeit at reduced levels. For videolaryngoscopy, AI-powered systems provide real-time structure identification, procedural guidance, tracheal tube placement verification, and potentially fewer complications. AI also offers cognitive support during critical scenarios by mitigating decision biases, providing intelligent alarms, and ensuring guideline adherence when human performance might be compromised by stress. In education, AI-enhanced virtual reality simulations create realistic practice environments with personalised feedback tailored to learners' needs. Experimental robotic intubation systems guided by AI algorithms demonstrate performance comparable with experts in controlled settings, though primarily for training and remote applications. Despite these advances, AI should complement rather than replace human expertise. Important challenges remain, including the risk of clinician deskilling, the 'black box' nature of some algorithms limiting transparency, and the need for robust validation before widespread implementation. The ideal approach involves human-machine collaboration where AI compensates for cognitive limitations while physicians contribute clinical judgement, context awareness, and empathy. As AI continues evolving, appropriate ethical frameworks and regulatory oversight must be developed in parallel to ensure these technologies enhance patient safety while preserving the essential human element of healthcare.

来源:Br J Anaesth,查看原文。版权归原作者所有。

引用

  1. Sorbello M, La Via L, Paternò DS, et al. Artificial intelligence in airway management: a narrative review. Br J Anaesth. 2026. PMID: 41644371. doi:10.1016/j.bja.2025.12.052

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。