Skip to content

Development and Performance Comparison of Machine Learning Models for Predicting Difficult Airway Based on Clinical Physical Measurements and Airway Ultrasound Parameters

Development and Performance Comparison of Machine Learning Models for Predicting Difficult Airway Based on Clinical Physical Measurements and Airway Ultrasound Parameters

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2600127067
Enrollment
Unknown
Registered
2026-06-24
Start date
2026-06-30
Completion date
Unknown
Last updated
2026-06-29

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Difficult airway

Interventions

Elective surgery patients undergoing general anesthesia:None

Sponsors

The Second Affiliated Hospital Of Zhengzhou University
Lead Sponsor

Eligibility

Sex/Gender
All
Age
18 Years to No maximum

Inclusion criteria

Inclusion criteria: 1.Patients aged over 18 years; 2.Patients scheduled for elective surgery under general anesthesia; 3.Patients classified as American Society of Anesthesiologists physical status (ASA PS) I–III; 4.Patients who voluntarily signed the informed consent form;

Exclusion criteria

Exclusion criteria: 1.Patients with central nervous system diseases or psychiatric disorders; 2.Patients with otolaryngological diseases or a history of surgery that may affect airway structures, as well as patients with a known difficult airway requiring fiberoptic bronchoscopy-guided intubation; 3.Patients with severe maxillofacial deformities or neck diseases that may affect airway assessment;

Design outcomes

Primary

MeasureTime frame
Occurrence of difficult airway;

Secondary

MeasureTime frame
F1 score;Positive predictive value;Area under the receiver operating characteristic curve;Sensitivity;Negative predictive value;Balanced accuracy;Specificity;Accuracy;Area under the precision-recall curve;

Countries

China

Contacts

Public ContactLi Xia

The Second Affiliated Hospital Of Zhengzhou University

13838293831@163.com+86 371 6393 4986

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Jul 3, 2026