Development of an Artificial Intelligence Model for Mask Ventilation Difficulty/Intubation Difficulty Classification Using Deep Learning with Patient Facial Images
Not Applicable
- Conditions
- Scheduled surgical cases
- Registration Number
- JPRN-UMIN000052233
- Lead Sponsor
- Yamagata Universal Faculty of Medcine
- Brief Summary
Not available
- Detailed Description
Not available
Recruitment & Eligibility
- Status
- Pending
- Sex
- All
- Target Recruitment
- 800
Inclusion Criteria
Not provided
Exclusion Criteria
Patients who cannot give consent Patients considered inappropriate by the anesthesiologist in the case Cardiac surgery cases Patients who cannot follow instructions Patients with limited mobility of the neck Patients whose facial appearance, mask ventilation, or intubation is affected by artifacts
Study & Design
- Study Type
- Observational
- Study Design
- Not specified
- Primary Outcome Measures
Name Time Method Prediction accuracy of classifiers (systems) that can discriminate between mask ventilation difficulties and intubation difficulties
- Secondary Outcome Measures
Name Time Method