Clinical Language Understanding Engine for Structured Data Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Clinical documentation in healthcare institutions faces challenges in efficiently extracting and structuring clinical facts from free-form narrations by clinicians, leading to inefficiencies in data entry, storage, and retrieval, especially with the transition from paper to electronic medical records.
Innovation Solution
A method and system that utilize a clinical language understanding (CLU) engine to automatically extract discrete clinical facts from free-form narrations, re-format the text, and maintain linkages between extracted facts and their original text portions, allowing for efficient storage and retrieval of clinical data in electronic medical records.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If free-form narration is used for clinical documentation, then ease of operation is improved, but data extraction and structuring efficiency deteriorates
Solution Approach 1:
The patent extracts discrete clinical facts from free-form narration using a CLU engine, separating structured data elements from the narrative text. This allows the system to maintain ease of free-form documentation while automatically extracting structured clinical facts for efficient storage and retrieval in electronic medical records.
2Measurement precision
If manual transcription is used for clinical notes, then measurement precision is improved, but loss of time increases
Solution Approach 1:
The system uses automatic speech recognition and CLU engines to self-process clinical narrations, converting spoken or written narratives into structured clinical facts without requiring manual transcription. This maintains accuracy through automated extraction while significantly reducing the time clinicians spend on documentation.
Solution Approach 2:
The patent replaces the mechanical process of manual transcription with automated computational systems including speech recognition and natural language understanding engines, eliminating the time-consuming manual typing process while maintaining documentation accuracy.
3Productivity
If electronic medical records are implemented, then productivity is improved, but device complexity increases
Solution Approach 1:
The patent segments the complex EHR system into distinct functional components: free-form narration input, automated speech recognition processing, CLU-based fact extraction, and structured data storage. This modular segmentation manages system complexity while maintaining productivity benefits of electronic records.
Data Source
AI summary
Based on a free-form narration of a patient encounter provided by a clinician, it may be determined that one or more clinical facts could possibly be ascertained from the patient encounter. One or more options corresponding to the one or more clinical facts may be provided to a user. A selection of a first option of the one or more options may be received from the user. The first option may correspond to a first fact of the one or more clinical facts. A textual representation of the free-form narration may be updated to identify the first fact as having been ascertained from the patient encounter.