Artificial intelligence‐assisted tracheal intubation in humans: a prospective observational study of diagnostic accuracy
Authors' conclusion
This first in-human study has established the feasibility of AI-guided real-time tracheal intubation using larynGuide.
Study context
- Population
- Adults undergoing elective surgery under GA with tracheal intubation by C-MAC® videolaryngoscope (Macintosh blade)110 analysed
- Participants
- 132 adults
- Comparison
- larynGuide vs Airway operator
- Outcome
- Real-time accuracy of larynGuide in identifying correct tracheal tube placement
Methodological detailsprospective, single-centre, investigator-initiated, observational, first in-human
- Prospective
- Single-centre
- Investigator-initiated
- Observational
- First in-human
Performance
As reported in the abstract
Identification of correctly placed tracheal tubes
| Test or model | Value | Sensitivity | Sensitivity 95% CI |
|---|---|---|---|
| larynGuide | 102 events | 0.94 | 0.88-0.98 |
larynGuide
Value102 events
Sensitivity0.94
Sensitivity 95% CI0.88-0.98
- Correctly placed tubes
- 108
- Misclassified tube position
- 6
- False negatives (failed intubation advised despite correct placement)
- 2
- No feedback
- 4
Further findings
Detection of oesophageal tube placement at first attempt
- Oesophageal placements detected by larynGuide (of 2)
- 1
Original publication
Artificial intelligence‐assisted tracheal intubation in humans: a prospective observational study of diagnostic accuracy. Anaesthesia. Published 17 November 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →