Development of an Artificial Intelligence-Based Model for Predicting Difficult Intubation Using Video Laryngoscopic Images and Cormack-Lehane Classification

NCT07152093 | Completed

• 1 other identifier: 2025/183
• Study Type: observational
• Target: 132
• Locations: 1 country
• Sites: 1

Brief Summary

This prospective observational study aims to develop an artificial intelligence model that can automatically determine the Cormack-Lehane classification from video laryngoscopy images in patients undergoing elective surgery. It also aims to predict the risk of difficult intubation based on this classification. The resulting data will evaluate the applicability of AI-supported decision support systems in clinical airway management.

Conditions

Difficult Airway Intubation

Keywords

Difficult Airway; Cormack-Lehane; Video Laryngoscopy; Artificial Intelligence; Machine Learning

Outcome Measures

Primary Outcomes (1)

• Accuracy of Machine Learning Model in Predicting Difficult Intubation Based on Video Laryngoscopy Images

  The primary outcome is the classification accuracy of the machine learning algorithm in identifying difficult intubation cases (Cormack-Lehane grade 3-4) from video laryngoscopy images, compared with expert anesthesiologists' consensus. Accuracy will be reported as a percentage.

  Immediately after data collection and model training

Study Arms (2)

Group 1: Normal Intubation Group

Intubations in patients assessed as Cormack-Lehane (CL) Class 1-2.

Difficult Intubation Group

Intubations in patients evaluated as Cormack-Lehane Class 3-4.

Eligibility Criteria

• Age: 18 Years - 65 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

The study population will consist of adult patients undergoing elective surgery under general anesthesia at the operating rooms of Düzce University Medical Faculty Hospital. All patients will have their airways assessed using video laryngoscopy as part of routine anesthesia induction. Only patients without known upper airway pathology will be included. Patients will be prospectively and consecutively recruited. Video laryngoscopy images will be captured during intubation and used for machine learning analysis. The Cormack-Lehane grade will be independently confirmed by two experienced anesthesiologists. Patients will be classified into normal and difficult intubation groups.

You may qualify if:

• years
• Elective surgery
• ASA I-II
• No upper airway pathology

You may not qualify if:

• Known history of difficult intubation
• Morbid obesity (BMI \> 40)
• Pregnancy
• History of upper airway surgery

Sponsors & Collaborators

• Duzce University: lead

Study Sites (1)

Duzce University Faculty of Medicine, Department of Anesthesiology and Reanimation

Düzce, Merkez, Turkey (Türkiye)

Location

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Target Duration: 1 Day
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Principal Investigator, Assistant Professor of Anesthesiology and Reanimation, Düzce University Faculty of Medicine

Study Record Dates

• First Submitted: August 21, 2025
• First Posted: September 3, 2025
• Study Start: May 1, 2025
• Primary Completion: September 30, 2025
• Study Completion: October 1, 2025
• Last Updated: November 18, 2025

Record last verified: 2025-11

Locations

TU (1)