Scholarlink

Objective <p>Video laryngoscopy (VL) improves glottic visualization during neonatal intubation, but real-time guidance on blade insertion depth is lacking. We developed a deep learning model to classify insertion depth during VL as shallow, glottic zone, or deep.</p> Study design <p>A deep learning model was trained on 298,955 annotated frames from 132 neonatal VL videos from two NICUs on one platform with fivefold cross-validation. 31 clinicians were surveyed regarding preferred device feedback modalities.</p> Results <p>The model detected glottic zone and shallow insertion depths with F1 scores of 0.894 and 0.718, respectively. Deep insertion events were rare (2.7%) with low performance (F1 = 0.034). Most clinicians preferred visual, minimal prompts over voice or haptic feedback.</p> Conclusion <p>AI-enabled VL may support blade-insertion depth assessment and training. Given the rarity of deep events, conclusions about deep insertion and clinical impact are limited. Future multi-site studies should focus on clinical integration and assessing outcomes.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Deep learning to assess laryngoscope insertion depth during neonatal intubation with video laryngoscopy

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年10月27日

查看全文
  • Abrar Majeedi,
  • Patrick J. Peebles,
  • Yin Li,
  • Ryan M. McAdams

摘要

Objective

Video laryngoscopy (VL) improves glottic visualization during neonatal intubation, but real-time guidance on blade insertion depth is lacking. We developed a deep learning model to classify insertion depth during VL as shallow, glottic zone, or deep.

Study design

A deep learning model was trained on 298,955 annotated frames from 132 neonatal VL videos from two NICUs on one platform with fivefold cross-validation. 31 clinicians were surveyed regarding preferred device feedback modalities.

Results

The model detected glottic zone and shallow insertion depths with F1 scores of 0.894 and 0.718, respectively. Deep insertion events were rare (2.7%) with low performance (F1 = 0.034). Most clinicians preferred visual, minimal prompts over voice or haptic feedback.

Conclusion

AI-enabled VL may support blade-insertion depth assessment and training. Given the rarity of deep events, conclusions about deep insertion and clinical impact are limited. Future multi-site studies should focus on clinical integration and assessing outcomes.