Automated EMR Query Generation for Heterogeneous Schema Integration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The varying schemas of electronic medical record (EMR) datasets from different hospitals or medical institutions make it labor-intensive and inefficient for health professionals to extract and evaluate clinical knowledge, as existing methods require manual schema changes and are not robust for data retrieval.
Innovation Solution
A method and system that automatically extracts clinical knowledge by constructing a knowledge tree and EMR graph, generating sub-queries based on the knowledge tree and EMR graph, and combining these sub-queries to create queries for extracting clinical features from EMR datasets, regardless of their arbitrary relational schema.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If manual schema changes are performed to integrate EMR datasets, then data integration can be achieved, but the process becomes labor-intensive and time-consuming
Solution Approach 1:
The system automatically performs schema integration by detecting relationships between EMR tables and generating queries without requiring manual intervention. The automated query generation system handles the entire process of integrating heterogeneous schemas, eliminating the need for manual schema transformation work.
Solution Approach 2:
The patent replaces manual mechanical operations (manual schema mapping and query construction) with an automated computational system. The system uses algorithms to detect table relationships, generate sub-queries, and combine them into final queries, substituting human labor with automated processing.
2Productivity
If manual feature extraction methods are used, then clinical knowledge can be extracted, but the process is labor-intensive and not scalable
Solution Approach 1:
The system automatically extracts clinical features by generating queries based on detected table relationships and clinical knowledge graphs. The automated process handles feature extraction without requiring manual intervention, making it scalable and efficient for processing large datasets.
Solution Approach 2:
The patent divides the complex feature extraction process into manageable segments: table relationship detection, sub-query generation, and query combination. This segmentation allows the system to handle complex extraction tasks by breaking them down into simpler, automated steps.
3Reliability
If heterogeneous EMR schemas are integrated manually, then data from multiple sources can be unified, but the process is not robust for automated retrieval
Solution Approach 1:
The system replaces manual query construction with automated query generation algorithms. The system automatically detects table relationships, generates appropriate sub-queries, and combines them into final queries, providing robust automated retrieval that works across heterogeneous schemas without manual intervention.
Data Source
AI summary
A method, device, and computer program storage product for generating a query to extract clinical features into a set of electronic medical record (EMR) tables based on clinical knowledge. A knowledge tree is constructed according to a set of clinical knowledge data. An EMR graph corresponding to a set of EMR tables is obtained. The EMR graph comprises at set of table nodes and a set of attribute nodes. The set of table nodes and the set of attribute nodes represent a structure of each EMR table in the set of EMR tables and a reference relationship among attributes of set of EMR tables. A plurality of sub-queries is generated based on the knowledge tree and the EMR graph. At least one query is generated by combining the plurality of sub-queries according to the knowledge tree.