To Create an Artificial Intelligence-enabled Device for Airway Assessment (AINFAS) to Identify Patients With Difficult Airway Pre-operatively.

Artificial INtelligence eNabled 3D Facial Scanner for Airway Assessment (AINFAS)

We're developing a new AI, which uses advanced computer technology to help doctors identify patients who might have a difficult airway before surgery or emergency procedures. Sometimes, when a person needs help breathing, doctors have to insert a tube into their airway. This can be challenging for some people due to the shape of their mouth, throat, or neck. We hope that AI will look at a patient's facial features to predict if there might be any difficulties.

Study Overview

• Status: Active, not recruiting
• Conditions: Anaesthesia
• Intervention / Treatment: Other: AI-Assisted Preoperative Airway Risk Assessment

Detailed Description

AINFAS (Artificial Intelligence-enabled system for airway assessment) is an innovative AI system we're developing to revolutionize airway management in healthcare. This advanced artificial intelligence is designed to analyze patient characteristics and predict potential difficulties in airway management before any medical procedure that might require breathing assistance. Using sophisticated machine learning algorithms, AINFAS processes data such as facial structure and neck anatomy to assess the likelihood of a difficult airway. This non-invasive, rapid assessment tool has potential applications across various healthcare settings, including pre-operative assessments, emergency departments, intensive care units, and even pre-hospital care. By providing early identification of potential airway challenges, AINFAS aims to enhance patient safety, improve resource allocation, and provide a standardized, objective method of airway assessment. Currently in development and testing, this AI system represents a significant step forward in using technology to enhance clinical decision-making and patient safety in critical aspects of medical care.

• Study Type: Observational
• Enrollment (Actual): 1000

Contacts and Locations

Study Locations

• Singapore
  • Singapore, Singapore, 119074
    • National University Hospital Singapore

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

Patients that undergoing surgery in National University Hospital Singapore Only.

Description

Inclusion Criteria:

• Undergoing surgery under general anaesthesia requiring endotracheal intubation or supraglottic airway
• 21-100 years old

Exclusion Criteria:

• Age less than 21 years
• Patients with prior surgery with altered facial appearance
• Patients with tracheostomy
• Patients with any oropharyngeal pathology
• Patients with nasopharyngeal carcinoma post radiotherapy or chemotherapy
• Pregnant females
• Patients whose physicians did not use a laryngoscope or supraglottic airway

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
General anaesthesia surgery	Other: AI-Assisted Preoperative Airway Risk Assessment; participants having their photograph taken using a tablet device following a standardized protocol to capture relevant facial and neck features. These photographs will then be analyzed using software, which assesses the images for potential indicators of a difficult airway.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Accuracy of AINFAS in Predicting Difficult Airways	To identify and characterize the key predictive parameters that contribute to the AI system's overall ability to detect difficult airways.	Assessment will occur from the time of preoperative AI analysis through to the completion of the intubation procedure, typically within 48 hours.

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Identification of Novel Predictors of Difficult Airways	To identify and characterize new predictive parameters that contribute to the AI system's overall ability to determine the likelihood of a difficult airway.	Data analysis will be conducted after completion of all participant procedures, typically within 2 years of the last participant's assessment.

Collaborators and Investigators

• Sponsor: National University Hospital, Singapore
• Collaborators: National University of Singapore
• Investigators: Principal Investigator: Will Ne-Hooi Loh, National University Hospital, Singapore

Study record dates

Study Major Dates

• Study Start (Actual): May 17, 2022
• Primary Completion (Actual): January 24, 2025
• Study Completion (Estimated): December 1, 2026

Study Registration Dates

• First Submitted: December 21, 2025
• First Submitted That Met QC Criteria: February 8, 2026
• First Posted (Actual): February 13, 2026

Study Record Updates

• Last Update Posted (Actual): February 13, 2026
• Last Update Submitted That Met QC Criteria: February 8, 2026
• Last Verified: December 1, 2025

More Information

Terms related to this study

• Keywords: General anaesthesia; difficult airway
• Other Study ID Numbers: 2021/00908

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No