ML Rule Engine Auto-Populates Documentation Vectors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic documentation systems rely on copy-and-paste functionalities, pre-written templates, and hard-coded auto-texts, which are limited by their inability to utilize patient contextual data and historical data, leading to inaccuracies and inefficiencies.
Innovation Solution
A system that uses a machine learning engine and a rule engine to automatically identify, select, and auto-populate suggested documentation into a graphical user interface (GUI) by generating vectors from historical data, reducing data sparsity, and clustering text blocks for relevance scoring.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If copy-and-paste functionalities and pre-written templates are used for electronic documentation, then ease of operation is improved, but accuracy and contextual relevance deteriorate
Solution Approach 1:
The system automatically generates and selects appropriate text blocks based on patient data and encounter context without requiring manual copy-paste operations. The machine learning model processes historical data and contextual information to autonomously populate documentation fields, eliminating the need for users to manually select from templates while maintaining high accuracy through intelligent data processing
Solution Approach 2:
The patent replaces the mechanical copy-and-paste system with an automated machine learning-based text generation system. Instead of manually selecting and copying pre-written templates, the system uses natural language processing and machine learning models to generate contextually relevant text blocks automatically, substituting manual mechanical operations with automated intelligent processing
2Ease of manufacture
If pre-written templates and hard-coded auto-texts are used, then ease of manufacture is improved, but adaptability to individual patient contexts deteriorates
Solution Approach 1:
The system dynamically adapts text block generation based on individual patient contexts, encounter types, and historical data patterns. Rather than using static pre-written templates, the machine learning model processes varying patient data and encounter contexts to generate dynamically appropriate text blocks, allowing the system to adapt to unique patient situations while maintaining ease of implementation through automated processing
Solution Approach 2:
The patent changes the parameters of text generation by using machine learning models that process patient-specific data characteristics, encounter context, and historical patterns. Instead of fixed templates, the system adjusts text generation parameters based on input data features, enabling adaptability to different patient contexts while maintaining ease of manufacture through automated parameter adjustment
3Measurement precision
If machine learning models process historical and contextual data to generate text blocks, then accuracy and contextual relevance are improved, but device complexity increases
Solution Approach 1:
The system segments the complex text generation task into distinct processing stages: historical data processing, contextual data processing, vector generation, similarity calculation, and text block selection. By dividing the complex machine learning pipeline into manageable segments, the patent reduces perceived system complexity while maintaining high accuracy through coordinated processing of multiple data types
Solution Approach 2:
The patent introduces intermediary components including vector representations and similarity calculation modules that mediate between raw historical and contextual data and the final text block generation. These intermediary elements simplify the relationship between complex input data and output text, making the overall system more manageable while maintaining accuracy through structured data transformation
4Productivity
If automated text block selection based on machine learning is implemented, then productivity is improved, but reliability requires continuous monitoring and updates
Solution Approach 1:
The system incorporates feedback mechanisms where user interactions with generated text blocks are monitored and used to refine the machine learning model. This continuous feedback loop improves reliability by allowing the model to learn from actual usage patterns and correct errors, while maintaining high productivity through automated text block selection that improves over time
Data Source
AI summary
Methods, systems, and computer-readable media are disclosed herein for a machine learning engine and rule engine that leverage historical and contextual data to intelligently identify, score, and suggest one or more documents for auto-population of a graphical user interface. The machine learning and rule engine employ vectorization and clustering technique to identify, score, and suggest the most factually accurate and contextually relevant documents as selectable candidates for electronic documentation. Further, the selection, rejection, or modification of the candidate documents are ingested by the machine learning engine and/or the rule engine to update a clustering algorithm and/or to update a relevance scoring algorithm, which are then utilized for subsequent instances.