一种肺顺应性预测模型训练方法、应用方法及系统
By training a lung compliance prediction model based on respiratory parameter curves, the problems caused by invasive procedures were solved, achieving non-invasive, rapid, and accurate lung compliance prediction, thus improving the reliability of the assessment and patient comfort.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHANGHAI JIAOTONG UNIV
- Filing Date
- 2026-05-14
- Publication Date
- 2026-07-17
AI Technical Summary
Current methods for assessing lung compliance rely on invasive procedures, which can cause patient discomfort and make the examination difficult to complete. They also involve demanding medical and nursing procedures and psychological fear.
By acquiring parameter curve data during the respiratory process, a lung compliance prediction model is trained using a feature extraction module, a global feature aggregation module, and a regression prediction module, avoiding direct pressure measurement and using a non-invasive method for prediction.
It achieves non-destructive, rapid, and accurate prediction of lung compliance, reducing physiological damage and psychological burden on patients, lowering data processing pressure, and improving the accuracy of prediction results.
Smart Images
Figure CN122242618B_ABST