Hypotension prediction method and apparatus, electronic device, and storage medium
By segmenting the mean arterial pressure and arterial blood pressure waveform information in hypotension prediction and combining time-domain and frequency-domain features, a self-attention mechanism neural network is used for prediction, which solves the problems of low prediction accuracy and low computational efficiency in existing technologies and achieves more efficient and accurate hypotension prediction.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- BEIJING UNIV OF POSTS & TELECOMM
- Filing Date
- 2026-03-03
- Publication Date
- 2026-07-17
AI Technical Summary
Existing methods for predicting hypotension lose fine-grained dynamic information of arterial blood pressure waveforms when using mean arterial pressure, while directly using high-frequency arterial blood pressure waveforms leads to excessive computational complexity, making it difficult to strike a balance between prediction accuracy and computational efficiency.
By acquiring mean arterial pressure and arterial blood pressure waveform information within the same time window, processing them in segments, extracting and fusing features, using a self-attention neural network for prediction, and combining time-domain and frequency-domain features for modeling.
It improves the accuracy and computational efficiency of hypotension prediction, and can capture the correlation between different time segments in a compact sequence structure, balancing the integrity of information expression and computational efficiency.
Smart Images
Figure CN122398239A_ABST