Assertion Acceptance Matrix for Patient Record Linkage
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In a medical environment, patients often receive care from multiple geographically dispersed healthcare providers, resulting in fragmented patient data across multiple sites, necessitating a system to reconcile and link multiple patient identifiers and records effectively.
Innovation Solution
A method and apparatus that utilize likelihood ratios and assertion acceptance values to determine record matching, with records falling between accept and reject thresholds flagged for manual review, and an assertion acceptance matrix to quantify trust among institutions, facilitating efficient and accurate patient record linkage across disparate medical systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple healthcare providers maintain separate patient records with local identifiers, then each provider can independently manage their data, but patient data becomes fragmented and difficult to link across providers
Solution Approach 1:
The patent introduces an intermediary assertion acceptance matrix that mediates between multiple healthcare providers' record systems. This matrix stores and evaluates assertions about record matches, enabling providers to share and verify patient record linkages without directly integrating their separate systems, thus reducing system complexity while maintaining data accuracy.
Solution Approach 2:
The assertion acceptance matrix serves multiple functions: it stores assertions, evaluates match confidence, facilitates information sharing, and enables automated decision-making across different healthcare providers. This multi-functional component reduces the need for separate mechanisms for each function, simplifying the overall system architecture.
2Productivity
If automated record matching uses single threshold comparison, then the process is simple and fast, but accuracy decreases for records with ambiguous matches
Solution Approach 1:
The system performs preliminary automated matching using likelihood ratios and threshold comparisons to quickly identify clear matches and non-matches. Records that fall into the ambiguous range are then flagged for further evaluation using the assertion acceptance matrix, allowing the system to maintain high productivity for clear cases while ensuring accuracy for ambiguous cases.
Solution Approach 2:
The patent segments the record matching process into distinct stages: initial automated filtering using likelihood ratios, intermediate evaluation using assertion acceptance values from the matrix, and final manual review for ambiguous cases. This segmentation allows each stage to optimize for its specific function, improving both efficiency and accuracy.
3Measurement precision
If all record comparisons are manually reviewed, then accuracy is maximized, but time consumption and processing speed increase significantly
Solution Approach 1:
The system applies partial manual review only to records that fall into the ambiguous match range, rather than reviewing all records manually. The assertion acceptance matrix automatically evaluates records with high confidence, requiring minimal or no manual intervention, while directing only uncertain cases to human reviewers, thus reducing processing time while maintaining accuracy.
Solution Approach 2:
The assertion acceptance matrix accumulates feedback from multiple assertions about record matches, using this historical information to improve future matching decisions. This feedback mechanism allows the system to learn from past cases and automatically handle similar cases more efficiently, reducing the need for manual review over time.
4Reliability
If healthcare institutions do not share assertion information, then institutional autonomy is maintained, but record linkage accuracy across providers decreases
Solution Approach 1:
The assertion acceptance matrix allows each healthcare provider to contribute assertions with locally appropriate confidence levels based on their own judgment and expertise. Each provider's assertions are evaluated with weights that reflect their local quality and reliability, enabling the system to maintain institutional autonomy while improving overall linkage accuracy through information sharing.
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
An assertion acceptance value matrix (300) indicates the reliability of assertions, particularly assertions or decisions whether records match or do not match, made by other medical institutions in a federation of medical institutions with different patient record systems and some common patients. Records from different institutions with a high likelihood of matching or not matching are automatically matched or not matched. Those that are ambiguous are manually reviewed. The assertion acceptance value matrix is used to reduce or expedite the manual review.