一种基于智慧医疗复诊随访数据处理方法及系统
By constructing a disease atlas based on graph neural networks and dynamic threshold recognition technology, the problem of insufficient predictability and adaptability of existing follow-up visit systems has been solved. This has enabled accurate identification of follow-up visit needs and automated task scheduling, thereby improving the system's adaptability and interpretability.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- GUANGZHOU SIYUN DATA TECH CO LTD
- Filing Date
- 2026-01-15
- Publication Date
- 2026-07-17
AI Technical Summary
Existing follow-up systems are insufficient in terms of predictability, adaptability, and proactivity. They cannot accurately depict key leaps in the disease progression process, leading to delayed or misjudged follow-up decisions and failing to achieve accurate positioning and personalized intervention for high-risk patients.
By constructing a unified event-level structured representation model, a structured event sequence is generated. A disease atlas is constructed using a graph neural network. The follow-up visit trigger node is identified by combining behavioral confidence regularization terms and dynamic thresholds, and a structured follow-up visit task is generated.
It achieves accurate identification of follow-up visit needs and automated task scheduling, improves the system's adaptability and interpretability, overcomes the problems of data heterogeneity, rigid rules and trigger lag, and has linkage and dynamism.
Smart Images
Figure CN121545722B_ABST
Abstract
Citation Information
Patent Citations
Intelligent urinary surgery diagnosis and treatment data processing system based on artificial intelligence
CN120452830A
Systemic lupus erythematosus assessment method and device based on multi-modal medical map and medical knowledge fusion, terminal equipment and medium
CN121306547A