基于多模态信号的睡眠低通气类型自动判别方法及系统
By using multimodal signal fusion and machine learning algorithms, the problem of accurately distinguishing between obstructive hypoventilation and central hypoventilation has been solved, achieving high-precision automated discrimination and improving the diagnosis and treatment of sleep-disordered breathing.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING INST OF TECH
- Filing Date
- 2025-11-05
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies struggle to accurately distinguish between obstructive hypoventilation (OH) and central hypoventilation (CH), leading to clinical diagnostic biases. Traditional visual scoring methods are highly subjective, have low accuracy, and limited ability to discriminate based on a single feature.
By employing multimodal signal fusion technology, the system collects nasal airflow, chest and abdominal respiratory movements, blood oxygen saturation, and electroencephalogram (EEG) signals. It then combines these with machine learning algorithms to construct a classification model and extract multidimensional features such as limited inspiratory flow, chest-abdomen paradox, and event termination patterns to achieve automated discrimination.
It significantly improves the accuracy and objectivity of hypoventilation types, enhances the diagnostic precision of sleep-disordered breathing, provides reliable clinical decision support, avoids missed diagnosis of central events, and supports personalized treatment.
Smart Images
Figure CN121465519B_ABST