Automated Medical Coding System with Suppression Code Logic
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual medical record coding and review processes are time-consuming, labor-intensive, and prone to errors due to the complexity and incompleteness of medical records, requiring significant human intervention and physician review, which is costly and inefficient.
Innovation Solution
Automated systems and techniques that use predefined and adaptive rules, along with machine learning, to identify sufficient medical codes, suppression codes, and key terms within medical records, determining when to display clinical edit options and generate queries for further input, thereby reducing unnecessary physician review and streamlining the coding process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If automated systems use predefined rules and machine learning to identify sufficient medical codes, then coding accuracy is improved, but system complexity increases
Solution Approach 1:
The system segments the coding review process into multiple stages: initial automated code identification using predefined rules, suppression code checking, key term searching, and selective clinical edit option display. This segmentation allows the system to achieve high coding accuracy through layered processing while managing complexity by handling different aspects of code verification in separate, modular steps.
Solution Approach 2:
The system performs preliminary automated analysis of medical records using predefined rules and machine learning algorithms to identify potential codes and suppression codes before presenting clinical edit options to reviewers. This preliminary action filters out clearly sufficient codes, reducing the workload on reviewers while maintaining high accuracy through pre-processing intelligence.
2Reliability
If the system displays clinical edit options for all unspecified medical codes, then documentation completeness is improved, but processing time increases
Solution Approach 1:
The system applies local quality by selectively displaying clinical edit options only for specific unspecified medical codes that meet certain criteria (presence of suppression codes, absence of key terms). Rather than uniformly processing all unspecified codes, the system tailors its review intensity to individual code characteristics, improving documentation completeness where needed while minimizing processing time for sufficient codes.
Solution Approach 2:
The system performs partial action by avoiding display of clinical edit options for codes that are already sufficient or clearly insufficient. It applies excessive action (detailed review) only where necessary - when suppression codes are present and key terms are absent - thereby optimizing the balance between documentation completeness and processing efficiency.
3Reliability
If the system generates queries for further physician input on all uncertain codes, then coding reliability is improved, but workload increases
Solution Approach 1:
The system performs preliminary automated analysis using machine learning and predefined rules to determine which codes truly require physician input. By pre-filtering codes based on suppression code presence, key term absence, and code specificity, the system generates queries only for uncertain codes that genuinely need physician clarification, improving coding reliability while minimizing unnecessary physician workload.
Solution Approach 2:
The system serves itself by using automated algorithms to identify and resolve many coding issues without physician intervention. Through suppression code checking and key term searching, the system autonomously determines code sufficiency, reserving physician queries only for cases where automated analysis cannot determine adequacy, thereby improving reliability while reducing overall workload.
4Measurement precision
If manual review processes are used for all medical records, then documentation accuracy is improved, but productivity decreases
Solution Approach 1:
The system introduces an intermediary automated review layer between complete manual review and no review. This intermediary uses predefined rules and machine learning to perform initial code identification and sufficiency checking, providing accurate pre-analysis that reduces the burden on manual reviewers while maintaining high documentation accuracy through layered verification.
Solution Approach 2:
The system performs preliminary automated coding and suppression code checking before manual review is needed. This preliminary action identifies sufficient codes and prepares clinical edit options in advance, so that when manual review does occur, it focuses only on uncertain cases, thereby maintaining documentation accuracy while significantly improving overall productivity.
Data Source
AI summary
In one example, this disclosure describes a method of processing medical data via one or more computers. The method may comprise identifying a medical code within a medical record, and identifying whether the medical code is specified or unspecified. If the medical code is specified, editing may be avoided without generating any query for further input by a physician. If the medical code is unspecified, the method further includes determining whether a suppression code appears in the medical record. If a suppression code appears, editing may be avoided without generating any query for further input by the physician. However, if a suppression code does not appear, the method further includes searching for key terms in the medical record. If key terms are present in the medical record, a query may be generated for the physician for additional clarification.