Artificial Intelligence in Airway Management: Current Evidence and Future Perspectives.

Airway management remains a critical component of anesthetic practice, and failure to anticipate a difficult airway may result in significant morbidity and mortality. Conventional airway assessment tools demonstrate limited predictive accuracy and are often influenced by operator subjectivity. Recent advances in artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL), have introduced novel approaches to airway assessment, prediction, procedural guidance, and education. This review aims to provide a comprehensive overview of the current applications of AI in airway management, evaluate the emerging evidence, discuss existing challenges, and explore future directions for clinical implementation. A narrative review of the literature was conducted using the PubMed, Scopus, and Google Scholar databases. Relevant studies, review articles, and guidelines published in English were screened to identify evidence related to AI-based airway assessment, difficult airway prediction, video laryngoscopy, airway imaging, simulation-based education, and emerging airway technologies. AI has demonstrated promising applications across multiple domains of airway management. ML and DL models have shown improved performance in predicting difficult airways compared with conventional bedside assessment methods by incorporating clinical variables, facial image analysis, voice characteristics, and imaging data. AI-assisted ultrasound interpretation and videolaryngoscopy have enabled real-time anatomical recognition, procedural guidance, and automated performance assessment. Furthermore, AI-enhanced simulation and educational platforms have facilitated personalized training and objective competency evaluation. Despite these advances, challenges related to dataset quality, external validation, algorithm transparency, ethical considerations, and clinical integration remain significant barriers to widespread adoption. AI has the potential to transform airway management through enhanced prediction, decision support, procedural guidance, and education. While current evidence is encouraging, further multicenter studies, regulatory oversight, and the development of explainable AI systems are required before routine clinical implementation. AI should be considered a complementary tool that augments clinical expertise rather than a replacement for clinician judgment.