Clinical Order Set Standardization via AI Natural Language Processing

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current Computerized Provider Order Entry (CPOE) and Electronic Medical Records (EMR) systems face challenges in managing and standardizing clinical orders due to the vast number of possible orders and the use of natural language, which can lead to errors, duplication, and incorrect interpretation.

Innovation Solution

A system and method for validating and standardizing order sets by reconciling them against an authoritative catalogue, using artificial intelligence to interpret natural language, recognize synonyms, and canonical matching, thereby reducing manual searching time and improving confidence in match results.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If natural language orders are used in CPOE or EMR systems, then clinicians can freely express clinical intent, but errors, duplication, and incorrect interpretation may be introduced into the system

Engineering Contradiction:

Improveflexibility in expressing clinical intentVSAvoidaccuracy of order interpretation

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The patent introduces an intermediary processing layer between natural language input and system interpretation. This layer includes natural language processing modules, terminology services, and validation mechanisms that mediate between the clinician's free-form expression and the structured order inventory, thereby maintaining both flexibility and accuracy

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system implements feedback mechanisms where order interpretations are validated against the authoritative catalogue, and discrepancies are flagged for review. This feedback loop ensures that natural language orders are correctly mapped to standardized orders, reducing errors while preserving clinical intent

Inventive Principle:

Principle #23Feedback

2Adaptability or versatility

If the order inventory contains all possible orders (10,000-100,000 orders), then comprehensive clinical coverage is achieved, but system complexity and difficulty in managing the inventory increase

Engineering Contradiction:

Improvecomprehensive clinical coverageVSAvoidcomplexity of order inventory management

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent segments the large order inventory into organized categories and hierarchies (e.g., by clinical domain, by body system, by procedure type). This segmentation makes the inventory more manageable while maintaining comprehensive coverage, allowing clinicians to navigate and select orders more efficiently

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system implements a universal authoritative catalogue that serves multiple functions: it acts as the master order inventory, provides terminology standardization, enables validation against standard nomenclature, and supports natural language interpretation. This multi-functional approach reduces overall system complexity while maintaining comprehensive coverage

Inventive Principle:

Principle #6Universality (Multi-functionality)

3Ease of operation

If free-form English names and descriptions are used for orders, then ease of entry is improved, but validation against the authoritative catalogue becomes difficult

Engineering Contradiction:

Improveease of order entryVSAvoidprecision of order matching

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The patent replaces manual, mechanical matching processes with automated natural language processing and computer-based validation systems. These systems use algorithms to interpret free-form English descriptions and automatically match them against the authoritative catalogue, maintaining ease of entry while improving matching precision through intelligent processing

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS8346698B2System and method for optimizing development, implementation and management of orders

Publication Date: 2013.01.01 PLEXINA

AI summary

A system and method is provided for developing, implementing and managing orders whereby a raw order set can be resolved into a canonical order set to identify at least one order within the one raw order set. A commonality analysis can be performed by comparing one canonical order set with another canonical order set to determine at least one common order subset. The canonical order sets sharing at least one common order subset can then be restructured into a hierarchical structure, and prioritized to minimize downstream processing.