# A novel AI-guided and motorized videolaryngoscope aiming to democratize endotracheal intubation

**Authors:** Robert Harutyunyan, Joshua Morse, David Gauthier, Gilles Bronchti, Thomas Hemmerling, Pascal Laferrière-Langlois

PMC · DOI: 10.3389/fmed.2026.1744451 · Frontiers in Medicine · 2026-02-12

## TL;DR

A new AI-guided and motorized videolaryngoscope was tested and showed high success rates and low workload in preclinical trials.

## Contribution

A novel AI-guided and motorized videolaryngoscope designed to reduce manual dexterity demands and operator workload.

## Key findings

- First-attempt success rate was 100% with a median intubation time of 14.3 seconds.
- Operator workload was low, with a weighted NASA-TLX score of 29.1 ± 6.7.
- High usability scores were reported, especially for clinical adoption and training suitability.

## Abstract

Videolaryngoscopy has improved glottic visualization during intubation, but difficulties in tube advancement and hand-eye coordination continue to limit procedural efficiency. These ergonomic challenges contribute to failed intubations even when visualization is adequate. The present study evaluated a novel artificial intelligence guided and motorized videolaryngoscope (AI-VL) designed to reduce manual dexterity demands and operator workload.

A preclinical validation was conducted using 5 Thiel-embalmed cadavers. Three operators with varying airway experience performed 30 intubations using the AI-VL. Primary outcomes were first-attempt success rate, intubation time, and visible airway trauma. Secondary outcomes included operator workload using the weighted NASA task load index (NASA-TLX) and post-procedural usability Likert questionnaire.

First-attempt success was 100% across all procedures, with a median intubation time of 14.3 s (IQR 11.0–22.8) and no visible tissue injury. The weighted NASA-TLX global workload was 29.1 ± 6.7 (0–100 scale), below the 25th percentile of published medical task norms, indicating low to moderate perceived demand. Mean usability ratings were 4.3 ± 0.6 on 5, with the highest scores for likelihood of clinical adoption and training suitability, 4.7 ± 0.6 and 5.0 ± 0.0 respectively.

In this cadaveric study, the AI-VL preliminarily demonstrated consistent procedural success, short intubation times, relatively low operator workload, and high usability scores. These findings support its potential as a next generation videolaryngoscope and indicates the need for further clinical trials to explore its effectiveness across diverse clinical settings.

## Full-text entities

- **Diseases:** tissue trauma (MESH:D014947), hypoxic injury (MESH:D002534), bleeding (MESH:D006470), airway trauma (MESH:D000402), vocal cord damage (MESH:D014826), pharyngeal laceration (MESH:D010612), death (MESH:D003643), aspiration (MESH:D011015)
- **Species:** Homo sapiens (human, species) [taxon 9606]

## Full text

_Full body text omitted from this summary view._ Fetch the complete paper as Markdown: https://tomesphere.com/paper/PMC12937148/full.md

## Figures

2 figures with captions in the complete paper: https://tomesphere.com/paper/PMC12937148/full.md

## References

17 references — full list in the complete paper: https://tomesphere.com/paper/PMC12937148/full.md

---
Source: https://tomesphere.com/paper/PMC12937148