Deep learning for video-based assessment of endotracheal intubation skills
Background Endotracheal intubation (ETI) is an emergency procedure performed in civilians and combat casualty care settings to establish an airway. It’s crucial that healthcare personnel are proficient in these skills, which traditionally have been evaluated through direct feedback from experts. Unf...
Uloženo v:
| Vydáno v: | Communications medicine Ročník 5; číslo 1; s. 116 - 10 |
|---|---|
| Hlavní autoři: | , , , , , , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
London
Nature Publishing Group UK
14.04.2025
Springer Nature B.V Nature Portfolio |
| Témata: | |
| ISSN: | 2730-664X, 2730-664X |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Shrnutí: | Background
Endotracheal intubation (ETI) is an emergency procedure performed in civilians and combat casualty care settings to establish an airway. It’s crucial that healthcare personnel are proficient in these skills, which traditionally have been evaluated through direct feedback from experts. Unfortunately, this method can be inconsistent and subjective, requiring considerable time and resources.
Methods
This study introduces a system for assessing ETI skills using video analysis. The system employs advanced video processing techniques, including a 2D convolutional autoencoder (AE) based on a self-supervision model, capable of recognizing complex patterns in videos. A 1D convolutional model enhanced with a cross-view attention module then uses AE features to make assessments. Data for the study was gathered in two phases, focusing first on comparisons between experts and novices, and then examining how novices perform under time constraints with outcomes labeled as either successful or unsuccessful. A separate set of data using videos from head-mounted cameras was also analyzed.
Results
The system successfully distinguishes between experts and novices in initial trials and demonstrates high accuracy in further classifications, including under time pressure and using head-mounted camera footage.
Conclusions
This system’s ability to accurately differentiate between experts and novices instills confidence in its effectiveness and potential to improve training and certification processes for healthcare providers.
Plain language summary
Endotracheal intubation (ETI) is a medical procedure where a tube is placed into a person’s windpipe (trachea) to keep their airway open. This procedure is critical in emergency and clinical settings but requires skill and experience to perform correctly. In this study, we used video analysis to assess how well ETI was performed by medical staff. Our approach involved a computer-based method that analyzed videos from multiple camera angles to evaluate ETI skills. The system could automatically distinguish between beginners and experienced professionals with high accuracy. This technology has the potential to improve medical training and certification by providing objective and automated feedback. By helping healthcare providers refine their skills, this method could lead to better patient outcomes for those undergoing ETI.
Ainam et al. introduce a video-based system to assess endotracheal intubation (ETI) skills, leveraging 2D and 1D convolutional models with a cross-view attention module to analyze complex patterns. The system effectively differentiates between experts and novices, improving the objectivity and efficiency of ETI training and certification. |
|---|---|
| Bibliografie: | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| ISSN: | 2730-664X 2730-664X |
| DOI: | 10.1038/s43856-025-00776-z |