Clinical Decision Support via Knowledge Graph Rule Merging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current clinical decision support systems rely on single rule sets, which can lead to inefficiencies in storing and managing a large amount of clinical data, and do not effectively merge similar clinical conditions or therapy schemes across different rule sets.
Innovation Solution
A computer-implemented method and system that uses a knowledge graph to represent a plurality of rule sets, allowing for the combination of clinical conditions and conclusions, enabling efficient searching and retrieval of clinical decisions based on patient information by indicating paths with nodes and edges, and determining clinical conclusions by matching patient data with graph paths.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple separate rule sets are used to represent clinical data, then comprehensive clinical coverage is achieved, but storage and management complexity increases
Solution Approach 1:
The patent merges multiple separate rule sets into a unified graph structure where clinical conditions, conclusions, and relationships are integrated into a single interconnected knowledge base. This consolidation maintains comprehensive clinical coverage while simplifying storage and management operations.
Solution Approach 2:
The graph structure serves multiple functions simultaneously: it stores clinical rules, represents relationships between conditions and conclusions, enables efficient querying, and supports clinical decision-making. This multi-functionality reduces the need for separate systems for each operation.
2Ease of manufacture
If traditional rule set structures are used, then implementation is straightforward, but merging similar clinical conditions across rule sets is ineffective
Solution Approach 1:
The graph structure inherently merges similar clinical conditions by representing them as interconnected nodes. When multiple rule sets are integrated into the graph, identical or similar conditions automatically converge to the same nodes, enabling effective merging while maintaining implementation feasibility.
Solution Approach 2:
The patent nests multiple rule sets within a hierarchical graph structure where general clinical conditions and conclusions form the outer layers, while specific conditions and conclusions are nested within. This nesting enables automatic merging of similar conditions at appropriate hierarchical levels.
3Loss of information
If clinical data is stored in distributed rule sets, then data completeness is maintained, but retrieval efficiency decreases
Solution Approach 1:
The graph structure performs preliminary organization of clinical data by pre-establishing all relationships between conditions and conclusions during graph construction. This preliminary structuring enables rapid retrieval operations without sacrificing data completeness, as the query engine can directly traverse pre-defined paths.
Solution Approach 2:
The patent transitions from flat, distributed rule set storage to a multi-dimensional graph structure where relationships are represented as edges and paths. This dimensional transformation enables efficient retrieval by allowing queries to traverse multiple relationships simultaneously rather than searching through distributed rule sets sequentially.
Data Source
AI summary
A computer-implemented method for clinical decision support is provided according to an embodiment of the present disclosure. In the method, patient information can be obtained that comprises at least one clinical condition. A graph can be searched for at least one rule matching the at least one clinical condition. The graph represents a plurality of rule sets. The rule set comprises one or more rule. The rule can be indicated with a path comprising at least one first node and a second node. The first node can indicate a clinical condition, and the second node can indicate a clinical conclusion. Then, a clinical conclusion can be determined based on the at least one path in response that the at least one path matching the at least one clinical condition is searched out.