Difficult airway management is one of the most challenging core competencies in anesthesiology, with traditional teaching heavily reliant on experiential instruction and limited case exposure. Artificial intelligence (AI), particularly deep learning, is profoundly transforming the clinical assessment and management of difficult airways through multimodal data fusion, high-precision prediction, and intelligent assistance. This paper systematically reviews recent advancements in deep learning models for difficult airway prediction and proposes a novel framework for their deep integration into the entire workflow of anesthesiology teaching rounds. This framework facilitates a paradigm shift from 'experience-based instruction' to 'data-driven, intelligent interaction' by enabling the real-time integration of AI assessment tools during rounds, creating virtual case repositories using generative technology, constructing intelligent decision-support systems, and implementing quantitative procedural skill evaluation. This approach provides anesthesiologists with transformative tools to cultivate precise assessment capabilities, structured clinical reasoning, and proficiency in emergency decision-making.

Keywords: Deep Learning; Difficult Airway; Anesthesia Education; Teaching Rounds; Multimodal Fusion; Artificial Intelligence.

1. Nørskov AK, Rosenstock CV, Wetterslev J, et al. Diagnostic accuracy of anaesthesiologists' prediction of difficult airway management in daily clinical practice: a cohort study of 188 064 patients registered in the Danish Anaesthesia Database[J]. Anaesthesia, 2015, 70(3): 272-81.
2. De Rosa S, Bignami E, Bellini V, et al. The Future of Artificial Intelligence Using Images and Clinical Assessment for Difficult Airway Management[J]. Anesth Analg, 2025, 140(2): 317-325.
3. Weixiong C, Yu T, Yingjie W, et al. Advances in the application of artificial intelligence for difficult airway prediction[J]. International Journal of Anesthesiology and Resuscitation, 2025, 46(3): 312-315.
4. Wilk M, Pikiewicz W, Florczak K, et al. Use of Artificial Intelligence in Difficult Airway Assessment: The Current State of Knowledge[J]. J Clin Med, 2025, 14(5)
5. Li X, Zhang G, Ye W, et al. Voice-assisted multimodal fusion network for difficult airway assessment[J]. Signal, Image and Video Processing, 2025, 19(5): 381.
6. Li X, Peng B, Yao Y, et al. Reliable multi-modal prototypical contrastive learning for difficult airway assessment[J]. Expert Systems with Applications, 2025, 273: 126870.
7. Commission HPH. AI System "ShuWen" Helps Enhance Quality and Efficiency in Anesthesia Preoperative Visits. 2025-05-23 2025-05-23 ]; Available from: https://wjw.hubei.gov.cn/bmdt/mtjj/mtgz/202505/t20250523_5660862.shtml.
8. Bureau WSaTI. AI Anesthesia Preoperative Visit System "ShuWen" Released with Accuracy Rate as High as 97.5%. 2025-05-06 2025-05-06]; Available from: https://kjj.wuhan.gov.cn/xwzx_8/kjspxw/202505/t20250506_2576999.html.
9. Wu J, Yao Y, Zhang G, et al. Difficult Airway Assessment Based on Multi-View Metric Learning[J]. Bioengineering (Basel), 2024, 11(7)
10. Estrada Alamo CE, Diatta F, Monsell SE, et al. Artificial Intelligence in Anesthetic Care: A Survey of Physician Anesthesiologists[J]. Anesth Analg, 2024, 138(5): 938-950.
11. Hendrix JM, Patel R, and Friede R, 3-3-2 Rule, in StatPearls. 2025, StatPearls Publishing Copyright © 2025, StatPearls Publishing LLC.: Treasure Island (FL) with ineligible companies. Disclosure: Roshan Patel declares no relevant financial relationships with ineligible companies. Disclosure: Rotem Friede declares no relevant financial relationships with ineligible companies.
12. Hayasaka T, Kawano K, Kurihara K, et al. Creation of an artificial intelligence model for intubation difficulty classification by deep learning (convolutional neural network) using face images: an observational study[J]. J Intensive Care, 2021, 9(1): 38.
13. Battegazzorre E, Gino B, Strada F, et al. Enhancing difficult airway management training: the role of virtual reality and adaptive learning[J]. Virtual Reality, 2025, 29(1): 22.

Yan Cheng

Department of Anesthesiology, Shaanxi Provincial People's Hospital, Xi'an, Shaanxi, 710068, China