Biomedical Data Element Knowledge Graphs for Semantic Interoperability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current biomedical data standards are not machine-readable and lack standardized regulations, leading to unclear data semantics and difficulties in integrating or analyzing datasets across different sources, hindering data sharing and utilization.
Innovation Solution
A method and system for constructing a knowledge graph of standard data elements in biomedical datasets, involving data collection, analysis, and semantic association to enhance machine readability and interoperability, using optical character recognition (OCR) and natural language processing (NLP) to extract and standardize data elements and their relationships.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If biomedical data standards are published in unstructured forms such as PDFs, then the standards can be easily stored and accessed, but machine readability and semantic interoperability are poor
Solution Approach 1:
The patent creates a knowledge graph that copies and transforms unstructured standard documents into a structured machine-readable format. The knowledge graph replicates the essential information from PDF documents while organizing it into standardized nodes and relationships that machines can process, thus preserving accessibility while enabling machine reading.
Solution Approach 2:
The patent changes the structural parameters of the data representation by converting unstructured text into structured graph data. This transformation modifies the data format from human-readable documents to machine-readable knowledge graph structures with standardized schemas, improving both machine readability and semantic interoperability.
2Ease of operation
If text-based search and reading are provided for data standards, then human understanding is facilitated, but process ability and usability for creating data elements are limited
Solution Approach 1:
The knowledge graph serves as an intermediary between human-readable standard documents and automated data element creation processes. It mediates by providing both human-accessible information and machine-processable structured data, enabling automated systems to extract, validate, and utilize standard information without requiring direct human intervention.
Solution Approach 2:
The patent replaces manual text-based processing with automated knowledge graph-based processing. Instead of requiring humans to manually parse and interpret standard documents, the system uses automated algorithms that query and process the structured knowledge graph to extract and validate data element information.
3Adaptability or versatility
If multiple data elements are defined differently across datasets, then each dataset can maintain its own structure, but integration and joint analysis become difficult
Solution Approach 1:
The patent creates a universal knowledge graph structure that can accommodate multiple data elements from different datasets while maintaining their individual characteristics. The standardized knowledge graph schema acts as a universal framework that can represent various data elements consistently, enabling integration and joint analysis across diverse datasets.
Solution Approach 2:
The patent standardizes the representation parameters of data elements across different datasets by mapping them to a common knowledge graph schema. This parameter standardization transforms diverse data element definitions into a unified representation format, preserving dataset flexibility while enabling reliable integration and analysis.
4Ease of manufacture
If data elements are not standardized, then each dataset can be created independently, but semantic clarity and comparability are reduced
Solution Approach 1:
The knowledge graph acts as an intermediary that provides standardized semantic definitions and relationships for data elements. It mediates between independent dataset creation and semantic standardization by offering a common reference framework that maintains semantic clarity while allowing datasets to be created independently according to their specific needs.
Data Source
AI summary
The present disclosure discloses a method and system for constructing a knowledge graph of a standard data element of a biomedical dataset, comprising collecting relevant standard texts of data elements of different types of biomedical datasets and data of a relevant standard of the biomedical dataset; analyzing and summarizing the relevant standard texts of the data elements of the different types of biomedical datasets and the data of the relevant standard of the biomedical dataset; constructing a knowledge model of the knowledge graph of the standard data element of the biomedical dataset; extracting entity type data and attribute data from structured data and an unstructured text in the structured data; and obtaining the knowledge graph of the standard data element of the biomedical dataset by performing knowledge fusion on a plurality of types of data based on an a plurality of types of semantic associative relationships between one or more entity types.