Knowledge Model Refactoring For Clinical Record Reconciliation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing knowledge models and systems rely heavily on rules to evaluate electronic records, leading to increased complexity, resource consumption, and maintenance challenges as the amount of information grows.
Innovation Solution
The implementation of a contextually intelligent framework that refactors rules within a knowledge model, generating composite thresholds and reducing the number of rules while increasing the number of concepts, thereby improving the internal structure and consistency of the knowledge model.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the number of rules in the knowledge model is increased to handle more information, then the coverage and evaluation capability improve, but the complexity and resource consumption increase
Solution Approach 1:
The patent merges multiple rules with different thresholds into a single unified rule structure. The system combines several threshold-based rules into one rule that uses a unified threshold mechanism, reducing the total number of rules while maintaining the ability to handle diverse information types and evaluation scenarios.
Solution Approach 2:
The patent creates a universal rule structure that can handle multiple types of evaluations through a single unified threshold mechanism. The unified threshold can be dynamically adjusted to serve different evaluation purposes, making the rule system more versatile without requiring separate rules for each scenario.
2Adaptability or versatility
If more rules are added to the knowledge model, then the evaluation coverage improves, but the resource consumption and maintenance difficulty increase
Solution Approach 1:
The patent combines multiple maintenance-intensive rules into a single unified rule, significantly reducing the maintenance burden. Instead of maintaining numerous separate rules with different thresholds, the system maintains one unified rule with a single threshold mechanism that can be adjusted to serve multiple evaluation needs.
Solution Approach 2:
The patent uses parameter changes (specifically, dynamic threshold adjustment) to enable a single rule to adapt to different evaluation scenarios. By changing the threshold parameter rather than creating new rules, the system maintains flexibility while reducing maintenance complexity.
3Measurement precision
If the knowledge model uses multiple rules with different thresholds, then the precision of evaluation improves, but the consistency and structural simplicity deteriorate
Solution Approach 1:
The patent maintains evaluation precision by allowing the unified threshold parameter to be dynamically adjusted based on the specific evaluation context. The threshold can be modified to reflect different precision requirements while maintaining a consistent rule structure, thus preserving both precision and consistency.
Solution Approach 2:
The unified rule structure serves multiple evaluation functions while maintaining structural consistency. The same rule framework is used across different evaluation scenarios, ensuring consistency in the knowledge model structure while adapting to different precision requirements through parameter adjustment.
Data Source
AI summary
Methods, systems, and computer-readable media are disclosed herein that employ a contextually intelligent framework. In accordance with embodiments, a knowledge model having rules, axioms, and a domain ontology is evaluated to determine rules that are redundant to other rules and axioms, to determines those rules thresholds that may be refactored to generate composite rules and reduce the overall quantity of rules in the knowledge model, and to generate and add new concepts as axioms to the domain ontology as determined through refactoring. Methods, systems, and computer-readable media are disclosed herein that use the refactored and improved knowledge model to reconcile information currently stored in one system with information imported from a plurality of diverse systems, in order to generate recommendations that promote continuity of care in clinical settings.