Study of Difficult Airway and Intubation Rates in Adults Having Heart Surgery and Creating a Prediction Model Using Artificial Intelligence

What this Trial Is About

This research aims to investigate the incidence and factors associated with difficult airway and difficult intubation in patients undergoing cardiovascular surgery. The study addresses the challenge of predicting difficult airways, which can arise due to complex interactions between anesthesia, underlying cardiac conditions, and airway management difficulties. Since these situations can lead to severe complications, understanding and predicting difficult airway in this patient group is crucial for enhancing patient safety. Participants undergoing cardiovascular surgery will be observed to assess components such as difficult mask ventilation, difficult laryngoscopy, difficult endotracheal intubation, and difficult supraglottic airway device placement. The study will collect data using established scoring systems like the LEMON Score, El-Ganzouri Risk Index, Arne Score, Cormack-Lehane Classification, Han Score, Intubation Difficulty Scale, and others. Using this data, researchers aim to develop a machine learning prediction model based on artificial intelligence algorithms. During the study, participants will be evaluated before and after anesthesia induction with measurements including intubation difficulty, mask ventilation difficulty, laryngeal view score, and preoperative LEMON score. These assessments will help determine the incidence and risk factors of difficult airway situations in cardiovascular surgery patients. The study involves routine clinical observations and scoring during the perioperative period, with ongoing monitoring to ensure comprehensive data collection for analysis.

Difficult Airway Incidence in Cardiovascular Surgery and a Prediction Model Development