Ontology Mapper for Health Information Interoperability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current health information systems lack interoperability due to the absence of a unified ontology or nomenclature standard, hindering the ability to reliably measure quality from unmapped electronic medical records and impeding real-time decision-support and health services research.
Innovation Solution
The development of a system and method for discovering and validating semantic structures and linkages between disparate health information systems using Latent Semantic Analysis (LSA) in conjunction with decision-tree induction and Pearson correlation coefficient, enabling automatic mapping of terms across different nomenclatures and coding systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If health information is maintained in multiple electronic health-record database systems with different nomenclatures, then the quantity and accessibility of health information increases, but interoperability and reliability of data mapping deteriorate
Solution Approach 1:
The patent introduces an intermediary ontology mapping system that acts as a mediator between disparate health information systems. This mapping system translates and aligns different nomenclatures (ICD-9, ICD-10, CPT, HCPCS) through a unified ontology framework, enabling reliable data exchange without requiring direct integration between all systems. The intermediary layer preserves data reliability while supporting multiple coding systems.
Solution Approach 2:
The patent creates a universal ontology framework that can handle multiple nomenclatures and coding systems simultaneously. This multi-functional system provides a common reference model that works across different health information systems, allowing the same ontology structure to map various coding standards (ICD-9, ICD-10, CPT, HCPCS) without requiring separate mapping mechanisms for each system.
2Measurement precision
If traditional randomized controlled trials are used to determine treatment effectiveness, then the scientific rigor is maintained, but the cost and time required increase significantly
Solution Approach 1:
The patent creates virtual copies of clinical trial data from existing electronic health records. Instead of conducting new prospective randomized controlled trials, the system extracts and replicates relevant historical data, applies standardized ontology mapping to ensure consistency, and performs retrospective analysis. This copying approach maintains scientific rigor through proper data validation while dramatically reducing time and cost.
Solution Approach 2:
The patent performs preliminary data preparation and ontology mapping in advance, creating ready-to-analyze datasets from existing health records. By pre-processing and standardizing data before analysis, the system eliminates the need for time-consuming prospective data collection, allowing rapid treatment evaluation while maintaining methodological rigor through systematic data validation.
3Measurement precision
If manual mapping of nomenclatures between systems is performed, then mapping accuracy improves, but the productivity and scalability deteriorate
Solution Approach 1:
The patent implements self-service automated ontology mapping that performs mapping operations without requiring manual intervention for each data element. The system automatically discovers relationships between nomenclatures, applies mapping rules, and validates results through algorithmic processes. This self-service approach maintains high mapping accuracy through systematic validation while achieving scalability by eliminating repetitive manual work.
Solution Approach 2:
The patent replaces manual mechanical mapping processes with automated computational systems. Instead of human experts manually aligning nomenclatures, the system uses algorithms, machine learning models, and ontology reasoning engines to perform mapping automatically. This substitution maintains accuracy through consistent application of mapping rules while dramatically improving productivity and enabling scaling to large datasets.
4Ease of operation
If a centralized database of patient information is created, then data accessibility improves, but system complexity and security risks increase
Solution Approach 1:
The patent segments the health information infrastructure into distributed components rather than creating a single centralized database. Each health information system maintains its own data locally, and the ontology mapping system provides virtual integration by translating between systems. This segmentation reduces system complexity and security risks associated with centralization while maintaining data accessibility through standardized translation interfaces.
Data Source
AI summary
Systems, methods and computer-readable media are provided for facilitating patient health care by providing discovery, validation, and quality assurance of nomenclatural linkages between pairs of terms or combinations of terms in databases extant on multiple different health information systems that do not share a set of unified codesets, nomenclatures, or ontologies, or that may in part rely upon unstructured free-text narrative content instead of codes or standardized tags. Embodiments discover semantic structures existing naturally in documents and records, including relationships of synonymy and polysemy between terms arising from disparate processes, and maintained by different information systems. In some embodiments, this process is facilitated by applying Latent Semantic Analysis in concert with decision-tree induction and similarity metrics. In some embodiments, data is re-mined and regression testing is applied to new mappings against an existing mapping base, thereby permitting these embodiments to “learn” ontology mappings as clinical, operational, or financial patterns evolve.