Automated Healthcare Semantic Mapping via ML Distribution Analysis

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Manual mapping of data codes in healthcare systems is costly, time-consuming, and error-prone, hindering semantic interoperability between different healthcare entities.

Innovation Solution

An automated method using machine learning to create semantic maps by comparing distributions of variables and values across different healthcare databases, facilitating the translation of data between disparate systems.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual mapping or translation is used to exchange information between healthcare entities, then semantic interoperability can be achieved, but the process becomes costly, time consuming, and error prone

Engineering Contradiction:

Improveaccuracy of data mappingVSAvoidtime required for manual mapping

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent replaces the manual mechanical process of code mapping with an automated computer-based system that uses natural language processing and machine learning algorithms to automatically translate between different healthcare data terminologies, eliminating manual intervention while maintaining high accuracy

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service mapping by allowing healthcare entities to automatically map their own data codes using the automated translation system, which learns from the data distributions and semantic relationships without requiring external expert intervention for each mapping task

Inventive Principle:

Principle #25Self-service

2Reliability

If manual mapping or translation is used to exchange information between healthcare entities, then semantic interoperability can be achieved, but the process becomes costly and resource intensive

Engineering Contradiction:

Improveaccuracy of data mappingVSAvoidcost of implementation

Core Design Contradiction:

ReliabilityVSEase of manufacture

Solution Approach 1:

The patent replaces expensive manual expert mapping with an automated computational system that uses natural language processing and statistical analysis to perform mapping tasks at minimal marginal cost, significantly reducing implementation and operational expenses

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system changes the parameters of the mapping process by using statistical distributions and semantic similarity metrics instead of manual expert judgment, enabling automated decision-making that is both accurate and cost-effective at scale

Inventive Principle:

Principle #35Parameter changes

3Adaptability or versatility

If different semantic systems are used in different healthcare entities, then each entity can maintain its own data structure, but semantic interoperability and seamless data exchange are hindered

Engineering Contradiction:

Improveflexibility of data systemsVSAvoidinteroperability between systems

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The patent introduces an automated translation system as an intermediary that mediates between different healthcare data semantic systems, translating codes and terminology between systems while preserving the flexibility of each individual system's internal structure

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system creates a universal mapping capability that can translate between multiple different semantic systems simultaneously, allowing each healthcare entity to maintain its own data structure while enabling seamless interoperability across the entire network through the automated translation layer

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS10565315B2Automated mapping of service codes in healthcare systems

Publication Date: 2020.02.18 CERNER INNOVATION INC

AI summary

Mapping of semantics in healthcare may involve accessing first transaction data in a first database, the first transaction data corresponding to a collection of a first number of fields defined for a condition using a first semantic system to store information and calculating a first distribution of information in the first transaction data. Mapping may also involve accessing second transaction data in a second database, the second transaction data corresponding to a second semantic system different than the first semantic system and the second database comprising a second number of fields using the second semantic system to store information, and calculating a second distribution of information in the second transaction data. The distributions may then be compared and a map relating the semantic systems may be generated and used to communicate between the first and second semantic systems.