Clinical Decision Support Rule Database Automation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing clinical decision support systems face inefficiencies due to the need for expert intervention and time-consuming updates of rule databases, as they require strict data formats and cannot easily accommodate multiple inference engines or natural language inputs, leading to labor overheads and reduced application in various healthcare fields.
Innovation Solution
A data processing method utilizing the Self Evolutionary Rule-base algorithm and Ontology technique to infer and compare input and storage rules in natural language format, allowing for automatic updates and compatibility with various storage formats and inference engines, thereby reducing time and labor costs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If expert intervention is used to update rule database, then reliability of rule updates is improved, but productivity is worsened due to time consumption and labor overheads
Solution Approach 1:
The system automatically updates the rule database by comparing new rules with existing rules using the Self Evolutionary Rule-base algorithm, eliminating the need for expert intervention in the update process while maintaining reliability through systematic comparison and validation
Solution Approach 2:
The system changes the format parameter of rules from strict structured formats to natural language formats, enabling automatic processing and comparison while maintaining the essential rule logic and reliability
2Manufacturing precision
If strict data formats are required for inference engine, then manufacturing precision of rule storage is improved, but adaptability is worsened as multiple inference engines cannot be supported
Solution Approach 1:
The system uses a universal natural language format for storing rules that can be processed by multiple different inference engines, allowing a single rule database to serve multiple engines with different requirements without sacrificing format precision
Solution Approach 2:
The system introduces an intermediary layer (the natural language rule format and parser) between the rule database and inference engines, allowing rules to be stored in a flexible format while maintaining precise interpretation through the parsing mechanism
3Ease of operation
If natural language format is used for input data, then ease of operation is improved, but device complexity is worsened as computers cannot directly understand natural language
Solution Approach 1:
The system introduces a parser as an intermediary component that translates natural language rules into a structured format that computers can process, maintaining ease of operation while managing complexity through a dedicated translation layer
Solution Approach 2:
The system extracts the essential logical structure from natural language rules while retaining the natural language format for storage, separating the human-readable representation from the machine-processed interpretation
4Reliability
If periodic updates by experts are performed, then reliability of rule database is improved, but loss of time is worsened due to significant time consumption
Solution Approach 1:
The system performs automatic self-updating by comparing new rules with existing rules in the database using the Self Evolutionary Rule-base algorithm, eliminating the time-consuming manual update process while maintaining database reliability through systematic validation
Solution Approach 2:
The system performs preliminary comparison and validation of rules before updating the database, automatically identifying and integrating valid new rules while rejecting duplicates or conflicting rules, thus maintaining reliability without manual intervention
Data Source
AI summary
Provided is a data processing method for clinical decision support system. The data processing method provides an algorithm capable of performing parsing based on an Ontology technique and automatically updating rule database in order to reduce time and labor overloads accompanied by update of the rule database. According to an aspect, the data processing method includes inferring input data having a natural language format based on an Ontology technique to recognize at least one input rule included in the input data; inferring storage data having a natural language format and stored in rule database based on the Ontology technique to recognize at least one storage rule associated with the input rule from the storage data; comparing the input rule to the storage rule using a Self Evolutionary Rule-base algorithm; and updating the storage data stored in the rule database to the input data according to the result of the comparison.