Pediatric anesthesia & critical care
Development of an artificial intelligence-assisted system for tracheal intubation using a video laryngoscope in infants and neonates
Authors' conclusion
The AI-assisted model effectively identified the larynx, including the opening vocal cord and the arytenoid portion, during video laryngoscopy and potentially can enhance the safety of tracheal intubation of infants and neonates. However, esophageal misidentification remains critical.
Study context
- Population
- Infants and neonates undergoing tracheal intubation with a video laryngoscope (video laryngoscope images)399 test images from 63 videos
- Outcome
- Identification of the larynx (sensitivity, specificity, AUC)
Methodological detailsArtificial intelligence (AI) model development (YOLOv8n), Train and validation data: 1197 images from 653 videos
- AI model development (YOLOv8n)
- Train and validation data: 1197 images from 653 videos
Performance
As reported in the abstract
Identification of the larynx
| Test or model | Sensitivity | Specificity | AUC |
|---|---|---|---|
| AI-assisted model | 0.74 | 0.99 | 0.91 |
AI-assisted model
Sensitivity0.74
Specificity0.99
AUC0.91
Further findings
Opening vocal cord and arytenoid portion
- Correctly identified in cases without obstacles
Safety
Misidentification and non-detection
- Esophageal misidentification of the larynx and undetected larynx caused by obstacles observed
Original publication
Development of an artificial intelligence-assisted system for tracheal intubation using a video laryngoscope in infants and neonates. J Clin Anesth. Published 25 June 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →