Patient Record Matching via Demographic Digests
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Healthcare practitioners face difficulties in accessing comprehensive patient records across multiple healthcare facilities due to independent record systems and unique patient identifiers, leading to incomplete information and reduced treatment efficiency.
Innovation Solution
A method and system that use fuzzy representations and hashing of demographic attributes to identify and match patient records across different healthcare facilities, allowing for efficient retrieval of records associated with the same individual by comparing digests of demographic attributes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If patient records are maintained independently by different healthcare facilities with unique identifiers, then each facility can manage its own records efficiently, but healthcare practitioners cannot access comprehensive patient history across multiple facilities
Solution Approach 1:
The patent introduces a mediator system that receives patient records from multiple independent healthcare facilities, generates standardized digests from demographic attributes, and compares these digests to identify matching patients. This intermediary layer enables comprehensive patient information access without requiring direct integration between independent facility systems, thus maintaining their operational independence while achieving data interoperability.
2Loss of information
If a physician requests patient records from multiple healthcare facilities, then comprehensive patient history can be obtained, but the time and resources required to collect and review records increase significantly
Solution Approach 1:
The system performs preliminary actions by pre-processing patient records from multiple healthcare facilities to generate standardized digests of demographic attributes before any query is made. When a physician requests patient records, the system can immediately compare the query against these pre-generated digests and rapidly identify matching patients, eliminating the need for time-consuming real-time data collection and manual review across multiple facilities.
3Measurement precision
If unique patient identifiers are assigned by each healthcare facility, then patient records can be accurately tracked within each facility, but identifying the same patient across different facilities becomes difficult
Solution Approach 1:
The patent creates a universal identification mechanism that works across multiple independent healthcare facilities. By generating digests from demographic attributes (name, date of birth, address) and comparing these standardized representations, the system enables patient identification across facilities without requiring a centralized patient identifier. This universal approach maintains the accuracy of local identification while adding cross-facility adaptability.
4Loss of information
If all patient records from multiple healthcare facilities are collected and reviewed, then comprehensive patient understanding is achieved, but the volume of records to be processed becomes overwhelming
Solution Approach 1:
The system extracts only the essential demographic attributes (name, date of birth, address) from complete patient records to generate compact digests. When a physician needs comprehensive patient understanding, the system uses these extracted digests to rapidly identify matching patients across facilities, then retrieves only the relevant complete records for review. This extraction approach maintains complete patient understanding while dramatically reducing the volume of data that requires processing and review.
Data Source
AI summary
A method, computing device and computer program product are provided to identify records that are associated with same person, even in instances in which the records are created and stored by different entities. In a method, a plurality of records are received, each having attributes associated with a person. For each record, the method determines a digest by determining a fuzzy representation of one or more of the attributes for the person and then combining representations of the attributes. The method also receives a query relating to a record for the person and determines a digest based upon the attributes of the person. In response to the query, the method identifies one or more records that are associated with respective individuals who are candidates to match the person based upon a comparison of representations of the digests of the records and the person.


