多模态数据融合的糖尿病心血管病风险评估特征获取方法
By combining multimodal data fusion and LSTM models with physiological and functional indicators to predict the changing trends of biochemical indicators, this technology solves the problem that existing technologies cannot analyze biochemical indicators of diabetic cardiovascular disease in real time, and achieves accurate assessment of patient risk.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- YANAN UNIV
- Filing Date
- 2025-08-05
- Publication Date
- 2026-07-17
AI Technical Summary
Current technologies cannot achieve real-time dynamic analysis of biochemical indicators in diabetic cardiovascular disease patients, nor can they capture the changing trends of biochemical indicators in high-risk patients in a timely manner.
By using a multimodal data fusion method, combining historical detection data with real-time acquired physiological and functional indicators, an LSTM model is used to predict the changing trends of biochemical indicators, constructing trend change curves of biochemical indicators, and performing weighted fusion to assess risk.
It enables real-time dynamic analysis of the changing trends of biochemical indicators, accurately captures the physiological changes of patients, and provides a basis for dynamic risk assessment of diabetic cardiovascular disease.
Smart Images
Figure CN120977567B_ABST