EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Deep learning‐based facial analysis for predicting difficult videolaryngoscopy: a feasibility study

M Xia, C Jin, Y Zheng, J Wang, M Zhao, S Cao, T Xu, B Pei, M G Irwin, Z Lin, H Jiang

Anaesthesia · 2024-04 · 79 (4) · 399-409

DOI: 10.1111/anae.16194 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Anaesthesia, online erschienen am 13.12.2023. Verfasst von M Xia und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Anaesthesiology, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China. Hauptthemen laut MEDLINE: Deep Learning, Laryngoscopes. Die Arbeit wurde bisher 40-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai Municipal Health Commission.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

While videolaryngoscopy has resulted in better overall success rates of tracheal intubation, airway assessment is still an important prerequisite for safe airway management. This study aimed to create an artificial intelligence model to identify difficult videolaryngoscopy using a neural network. Baseline characteristics, medical history, bedside examination and seven facial images were included as predictor variables. ResNet‐18 was introduced to recognise images and extract features. Different machine learning algorithms were utilised to develop predictive models. A videolaryngoscopy view of Cormack‐Lehane grade of 1 or 2 was classified as ‘non‐difficult’, while grade 3 or 4 was classified as ‘difficult’. A total of 5849 patients were included, of whom 5335 had non‐difficult and 514 had difficult videolaryngoscopy. The facial model (only including facial images) using the Light Gradient Boosting Machine algorithm showed the highest area under the curve (95%CI) of 0.779 (0.733–0.825) with a sensitivity (95%CI) of 0.757 (0.650–0.845) and specificity (95%CI) of 0.721 (0.626–0.794) in the test set. Compared with bedside examination and multivariate scores (El‐Ganzouri and Wilson), the facial model had significantly higher predictive performance (p < 0.001). Artificial intelligence‐based facial analysis is a feasible technique for predicting difficulty during videolaryngoscopy, and the model developed using neural networks has higher predictive performance than traditional methods.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningLaryngoscopesHumansLaryngoscopyArtificial IntelligenceFeasibility StudiesIntubation, Intratracheal

Stichwörter der Autor:innen

deep learningdifficult airwaydifficult laryngoscopyfacial analysisvideolaryngoscopy

Autor:innen und Institutionen

  • Department of Anaesthesiology, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
  • State Key Laboratory of Ocean Engineering, School of Naval Architecture, Ocean and Civil Engineering, Shanghai Jiao Tong University, Shanghai, China.
  • Department of Anaesthesiology, University of Hong Kong, Hong Kong.

Förderung

  • Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine
  • Shanghai Municipal Health Commission

Zitieren

APA

Xia, M., Jin, C., Zheng, Y., Wang, J., Zhao, M., Cao, S., Xu, T., Pei, B., Irwin, M. G., Lin, Z., & Jiang, H. (2024). Deep learning‐based facial analysis for predicting difficult videolaryngoscopy: a feasibility study. Anaesthesia, 79(4), 399-409. https://doi.org/10.1111/anae.16194

Vancouver

Xia M, Jin C, Zheng Y, Wang J, Zhao M, Cao S, et al. Deep learning‐based facial analysis for predicting difficult videolaryngoscopy: a feasibility study. Anaesthesia. 2024;79(4):399-409. doi:10.1111/anae.16194

BibTeX
@article{Xia2024,
  author = {Xia, M and Jin, C and Zheng, Y and Wang, J and Zhao, M and Cao, S and Xu, T and Pei, B and Irwin, M G and Lin, Z and Jiang, H},
  title = {Deep learning‐based facial analysis for predicting difficult videolaryngoscopy: a feasibility study},
  journal = {Anaesthesia},
  year = {2024},
  volume = {79},
  number = {4},
  pages = {399--409},
  doi = {10.1111/anae.16194}
}
Kostenlos starten →