医疗知识图谱驱动的诊疗决策支持系统

By using a medical knowledge graph-driven diagnostic decision support system, which utilizes a vector space model for real-time data updates and composite vector calculations, the system addresses the issues of data lag and insufficient evaluation in existing systems. This enables dynamic quantitative assessment of complex clinical situations and early risk warnings, thereby improving the objectivity and transparency of decision-making.

CN121617595BActive Publication Date: 2026-07-17GANSU UNIV OF CHINESE MEDICINE

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
GANSU UNIV OF CHINESE MEDICINE
Filing Date
2025-11-28
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Existing clinical decision support systems cannot effectively integrate real-time multi-source heterogeneous data, lack dynamic quantitative assessment of complex clinical situations and early risk warning, resulting in delayed treatment plan adjustments and an inability to accurately assess the unified evaluation of drug efficacy and side effect risks.

Method used

The medical knowledge graph-driven diagnosis and treatment decision support system employs a data acquisition module, a data update module, a data processing module, and a data output module to update the knowledge graph in real time. It uses a vector space model for vectorized representation and composite vector calculation to generate clinical status assessment results.

Benefits of technology

It enables dynamic quantitative assessment of complex clinical situations, provides early risk warnings, improves the objectivity and transparency of decision-making, avoids the limitations of single-indicator judgment, and supports earlier and more predictive risk identification.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121617595B_ABST
    Figure CN121617595B_ABST
Patent Text Reader

Abstract

本发明公开了医疗知识图谱驱动的诊疗决策支持系统,涉及医疗知识图谱数据处理技术领域,通过获取患者临床数据流并映射为对预构建医疗知识图谱的更新指令,动态更新实体节点和关系边的属性数据;进而以目标实体节点为原点,根据其与关联节点之间关系边的属性数据,生成该节点的向量化表示;随后根据预设规则筛选待复合节点,并计算目标核心节点与待复合节点向量化表示之间的复合向量;最终根据复合向量的数学特征生成临床状态评估结果。本发明将复杂的医学关系量化为可计算的向量空间模型,实现了对患者临床状态的动态、客观、量化评估与风险预警,显著提升了诊疗决策的准确性和前瞻性。
Need to check novelty before this filing date? Find Prior Art