Videolaryngoscopy is widely used for tracheal intubation in anaesthesia and critical care; however, variability in patient anatomy, operator experience, and institutional practice may influence videolaryngoscopy performance and strategy selection. Conventional bedside airway assessments provide limited guidance for videolaryngoscopy-specific decision-making, particularly in diverse clinical environments.
This multicentre observational study will collect clinical parameters, demographic data, and point-of-care airway ultrasound measurements from adult patients undergoing videolaryngoscopy across participating centres. The collected data will be analysed using artificial intelligence-based analytical approaches, including statistical and machine-learning techniques, to examine their association with predefined videolaryngoscopy-related outcomes.
The primary objective is to evaluate the performance and generalisability of multimodal predictive models developed using multicentre data. The study is designed to support the development and validation of data-driven decision-support tools for videolaryngoscopy planning. These tools are intended for research purposes and do not replace clinical judgement.