PrediSuisse: Automatized Assessment of Difficult Airway

The Swiss multi-institutional research project "PrediSuisse" aims to automatically predict and classify the difficulty of intubation and airway management using three commercially available videolaryngoscopes (VL) by acquiring face/profiles photos and sequences on a training set of 900 patients during the pre-anaesthesia consultation. For each patient, with the help of recently developed Machine Learning (ML), Artificial Intelligence (AI) and Convolutional Neural Network (CNN) techniques, a specially developed software will be trained to provide a predicted airway management difficulty index. This will be performed by correlating those photos/sequences and the real difficulty level of intubation, determined by three experts by reviewing the recordings of the intubations of the training set patients. The software will then be used in routine on a set of 900 other patients to validate the prediction performance.

Inclusion criteria

• Adult patients (≥ 18 years old) presenting at the pre-anesthesia consult for an elective general anesthesia necessitating a tracheal intubation
• Signed informed consent.

Exclusion criteria

• Patients not speaking French (in Geneva and Lausanne) or Italian (in Lugano).
• Patients previously operated on the airway with anatomical modifications (ENT Flaps, tracheotomies).
• Patients unable to follow procedures or to give consent will also be excluded.