Medical Report Coding with Acronym Disambiguation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current medical documentation systems face challenges in accurately extracting clinical facts from free-form narratives due to the ambiguity of acronyms and abbreviations, which can lead to incorrect coding and reimbursement issues.
Innovation Solution
A method and system that utilize a statistical acronym/abbreviation expansion model to identify the most likely expanded form of acronyms and abbreviations in medical reports, combined with statistical fact extraction models to accurately extract clinical facts and assign corresponding medical taxonomy codes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If free-form narrative medical reports are used for documentation, then ease of operation is improved, but measurement precision deteriorates due to acronym/abbreviation ambiguity
Solution Approach 1:
The patent introduces an intermediary disambiguation system that sits between the free-form narrative documentation and the coding process. This system uses statistical models trained on medical corpora to resolve acronym and abbreviation ambiguities, converting ambiguous text into precise coded data without requiring clinicians to change their documentation style
Solution Approach 2:
The patent replaces the manual mechanical process of reading and interpreting medical reports with automated statistical models. These models use probability calculations and pattern recognition to disambiguate acronyms and abbreviations, substituting human interpretation with computational analysis that can process documentation at scale
2Reliability
If manual coding processes are used, then reliability is improved through human judgment, but productivity deteriorates due to time-consuming review
Solution Approach 1:
The patent implements a self-service coding system where the automated disambiguation and extraction processes perform the coding work without requiring manual review. The system uses confidence scores to automatically accept or flag cases, allowing most documentation to be coded autonomously while minimizing human intervention to only exceptional cases
Solution Approach 2:
The patent changes the operational parameters of the coding system by introducing confidence threshold parameters. By adjusting these parameters, the system can operate in different modes ranging from high automation with lower thresholds to more conservative operation with higher thresholds, optimizing the balance between reliability and productivity based on specific needs
Data Source
AI summary
Techniques for coding a medical report include identifying an acronym or abbreviation in the medical report, and a plurality of phrases not explicitly included in the medical report that are possible expanded forms of the acronym or abbreviation in the medical report. From the plurality of phrases, a most likely expanded form of the acronym or abbreviation may be selected by applying to the medical report a statistical acronym/abbreviation expansion model trained on a corpus of medical reports. By applying to the medical report with the expanded acronym or abbreviation one or more statistical fact extraction models, a clinical fact may be extracted from the medical report based at least in part on the most likely expanded form of the acronym or abbreviation in the medical report, and a corresponding medical taxonomy code may be assigned to the extracted clinical fact from the medical report.