一种基于多模态数据构建的适用于可视喉镜困难气管插管辅助评估系统及方法
The auxiliary assessment system for difficult endotracheal intubation, constructed using multimodal data and combining structured clinical data with multi-position images, enables automated prediction of the risk of difficult endotracheal intubation under video laryngoscopy. This solves the problem of the inapplicability of existing assessment systems and improves the accuracy and safety of prediction.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- XUANWU HOSPITAL OF CAPITAL UNIV OF MEDICAL SCI
- Filing Date
- 2026-05-08
- Publication Date
- 2026-07-17
AI Technical Summary
Existing difficult airway assessment systems are not suitable for assessing difficult endotracheal intubation under video laryngoscopy, leading to increased clinical difficulties and risks.
A multimodal data-based auxiliary assessment system for difficult endotracheal intubation using video laryngoscopes was developed. Through a computational unit and a result output unit, combined with structured clinical data and multi-position head and neck images, a computer program was used to calculate the probability value of difficult endotracheal intubation, and prediction was made using a multi-layer attention mechanism and modal fusion weights.
It improves the accuracy and stability of predicting difficult intubation, reduces the intubation failure rate and the risk of complications, enhances the medical interpretability and transparency of the model, and provides a more objective and comprehensive risk assessment.
Smart Images
Figure CN122177499B_ABST