Medical Coding System Using NLU Engine and Human Review
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual medical coding is time-consuming and prone to errors, as it requires human professionals to interpret clinical documentation to assign standardized codes, which can vary in language and complexity.
Innovation Solution
A natural language understanding engine is applied to derive medical billing codes from free-form clinical text, with a computer-assisted coding system that suggests codes to human coders, allowing for review, acceptance, rejection, or modification, and linking codes to corresponding text portions, while filtering overlapping engine-derived codes with user-approved codes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual medical coding is performed by human professionals, then coding accuracy can be maintained through expert interpretation, but the process becomes time-consuming and labor-intensive
Solution Approach 1:
A natural language processing system serves as an intermediary between clinical documentation and medical coding standards. The system automatically extracts entities, determines relationships, and maps them to appropriate codes, reducing the time burden on human coders while maintaining accuracy through multiple verification steps including human review of suggested codes.
Solution Approach 2:
The system performs preliminary coding actions by automatically generating suggested codes before human review. This preliminary action includes entity extraction, relationship determination, and code mapping, which prepares the work in advance and allows human coders to focus on verification and correction rather than starting from scratch.
2Productivity
If automated natural language processing is used to derive codes, then coding speed and consistency improve, but the system may generate overlapping or inaccurate code suggestions
Solution Approach 1:
The system implements feedback loops where human coder corrections and modifications to suggested codes are used to improve and retrain the natural language processing models. This continuous feedback mechanism allows the system to learn from errors and improve accuracy over time while maintaining high productivity.
Solution Approach 2:
The patent replaces manual mechanical coding processes with automated natural language processing and machine learning systems. This substitution handles the initial code generation automatically, freeing human coders from repetitive tasks while the system's computational power ensures consistent and rapid code suggestions.
3Measurement precision
If multiple code sets are generated and compared, then coding precision improves through validation, but system complexity increases
Solution Approach 1:
The coding system is segmented into distinct functional modules: entity extraction module, relationship determination module, code mapping module, and validation module. Each module handles a specific aspect of the coding process, making the overall complex system manageable and maintainable while ensuring thorough validation through multiple specialized components.
Data Source
AI summary
Techniques for medical coding include applying a natural language understanding (NLU) engine to a free-form text documenting a clinical patient encounter, to derive a first set of one or more medical billing codes for the clinical patient encounter and a link between each code in the first set and a corresponding portion of the free-form text. The first set of codes may be compared to a second set of one or more medical billing codes approved by one or more human users for the patient encounter, to identify at least one code in the first set that overlaps with at least one code in the second set. The code in the second set approved by the one or more human users may be retained instead of the overlapping code in the first set derived by the NLU engine.