Natural Language Understanding Engine for Clinical Order Intent
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current electronic medical record systems require clinicians to manually enter structured data, which can be time-consuming and restrictive, especially for those who prefer to dictate notes verbally, as they need to conform to structured formats and learn the interface, limiting the efficiency of medical documentation.
Innovation Solution
A method and apparatus that utilize natural language understanding engines to process free-form narrations from clinicians, extracting clinical facts and determining the intent to order items, thereby automating the generation of orders and enhancing the documentation process by allowing unconstrained input while maintaining the benefits of structured data storage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If clinicians manually enter structured data into electronic medical record systems, then data storage and retrieval are efficient, but the documentation process becomes time-consuming and restrictive
Solution Approach 1:
A natural language processing intermediary system is introduced between the clinician's verbal dictation and the electronic medical record system. This intermediary automatically processes free-form narration, extracts clinical facts, determines ordering intent, and generates structured orders, eliminating the need for clinicians to directly interact with complex structured interfaces while maintaining efficient data storage
Solution Approach 2:
The system enables self-service by allowing clinicians to dictate notes in their own words without requiring them to learn or navigate complex structured interfaces. The natural language processing system automatically converts their unstructured speech into properly formatted medical orders and documentation, making the system adapt to the clinician's workflow rather than requiring the clinician to adapt to the system
2Productivity
If clinicians use free-form verbal dictation, then documentation is faster and more natural, but extracting accurate clinical facts and determining intent becomes challenging
Solution Approach 1:
The manual mechanical process of structuring data is replaced with an automated natural language processing system that uses computational algorithms to analyze verbal dictation, extract clinical facts, and determine ordering intent. This substitution enables the system to handle free-form input while maintaining high accuracy in fact extraction and intent determination
Solution Approach 2:
The system incorporates feedback mechanisms where the natural language processing engine continuously refines its analysis of clinician dictation based on extracted clinical context and ordering patterns. This feedback loop improves the accuracy of fact extraction and intent determination over time, allowing the system to better understand nuanced medical language while maintaining documentation speed
Data Source
AI summary
Techniques for determining a clinician's intent to order an item may include processing a free-form narration, of an encounter with a patient, narrated by a clinician, using a natural language understanding engine implemented by one or more processors, to extract at least one clinical fact corresponding to a mention of an orderable item from the free-form narration. The processing may comprise distinguishing between whether the at least one clinical fact indicates an intent to order the orderable item or does not indicate an intent to order the orderable item. In response to determining that the at least one clinical fact indicates an intent to order the orderable item, an order may be generated for the orderable item.