Patient Record Matching via Entity Profile Verification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current healthcare systems face challenges in accurately matching patient records across different providers and insurers due to the lack of a unique patient identifier, leading to risks of incorrect clinical decisions and inappropriate exposure of private health information.
Innovation Solution
A method and system for monitoring a stream of messages from multiple sources of medical records to identify new or updated records, and using a person entity profile to determine whether suspect records match, allowing for merging or splitting of records to ensure accurate patient identity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If patient records are matched using multiple data sources without a unique identifier, then more records can be associated with patients, but the risk of overmatching increases leading to incorrect clinical decisions and privacy exposure
Solution Approach 1:
The system changes the parameters used for matching by incorporating multiple data points (name, date of birth, gender, address, phone number, insurance information) and their variations over time, rather than relying on a single identifier. This allows comprehensive matching while maintaining accuracy through multi-parameter verification
Solution Approach 2:
The system introduces an intermediary matching process that acts as a mediator between multiple data sources and the final patient record association. This intermediary layer applies sophisticated algorithms to evaluate potential matches against multiple criteria before confirming associations, preventing both overmatching and undermatching
2Object-affected harmful factors
If patient records are matched conservatively to avoid overmatching, then privacy is protected, but undermatching occurs causing clinical decisions to miss relevant information
Solution Approach 1:
The system dynamically adjusts matching sensitivity based on the confidence level of matches and the specific clinical context. Rather than using a fixed conservative threshold, the system can adaptively increase or decrease matching stringency depending on the quality of available data and the potential clinical impact, ensuring both privacy protection and information completeness
3Ease of operation
If traditional matching methods are used without considering data variations over time, then the system is simpler to operate, but matching accuracy decreases due to typographical errors and demographic changes
Solution Approach 1:
The system performs preliminary actions by collecting and storing historical patient data including name changes, address changes, phone number changes, and insurance changes over time. This pre-established historical context allows the matching algorithm to account for legitimate variations and reduce false mismatches due to demographic changes or typographical errors
Data Source
AI summary
A system and method may monitor a stream of messages from plural different sources of medical records to identify a new or updated record of the medical records, identifying one or more suspect records from a system of record (SOR) database. The one or more suspect records are identified as being potential matches to the new or updated record that is identified. The system and method can determine that the one or more suspect records match the new or updated record, and can obtain a person entity profile related to the new or updated record from a person entity database. The system and method can merge the new or updated record with the one or more suspect records or splitting the new or updated record from the one or more suspect records based on the person entity profile that is obtained.