Automated Medical Documentation Query System

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current medical documentation systems face inefficiencies in extracting information from physicians, leading to incomplete and inaccurate patient records, as they rely on manual processes that are time-consuming and prone to errors, especially in updating problem lists and billing codes.

Innovation Solution

A computer-implemented system that automatically identifies missing or ambiguous information in medical documentation, generates queries to solicit user input, and updates documentation accordingly, using natural language processing to analyze and map patient data to standardized codes, thereby reducing the need for manual intervention and improving data accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If manual processes are used to extract information from physicians and update documentation, then flexibility and adaptability in handling diverse medical scenarios are maintained, but time consumption and error rates increase significantly

Engineering Contradiction:
Improvedocumentation efficiencyVSAvoidtime for information extraction
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical processes (physicians typing or dictating encounters, specialists reading documentation, coders reviewing records) with an automated computer-implemented system that uses natural language processing and pattern recognition to extract information, identify undocumented items, generate codes, and create queries automatically

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service by automatically performing documentation review, code generation, and query creation without requiring manual intervention from specialists or coders, allowing the system to serve itself in identifying issues and soliciting necessary information from physicians

Inventive Principle:
Principle #25Self-service

2Productivity

If manual review processes are used by specialists and coders, then accuracy in identifying documentation issues can be maintained through human judgment, but productivity and throughput are significantly reduced

Engineering Contradiction:
Improvedocumentation review speedVSAvoidaccuracy of code generation
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The system incorporates feedback mechanisms where generated queries are sent to physicians for confirmation, and the system learns from physician responses to improve future automated coding accuracy, creating a closed-loop system that continuously refines its reliability

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system acts as an intermediary between the raw medical documentation and the final coded output, using natural language processing and pattern recognition as intermediate steps to bridge the gap between unstructured physician notes and standardized medical codes, thereby improving both speed and accuracy

Inventive Principle:
Principle #24Intermediary (Mediator)

3Loss of time

If automated code generation is implemented without human review, then productivity and speed are improved, but errors and inaccuracies in coding increase

Engineering Contradiction:
Improvetime for code generationVSAvoidaccuracy of billing codes
Core Design Contradiction:
Loss of timeVSManufacturing precision

Solution Approach 1:

The system performs preliminary automated code generation based on analyzed documentation, preparing draft codes and identifying undocumented items before physician review, so that when physicians do review, they are confirming or correcting pre-prepared options rather than creating codes from scratch, thereby maintaining accuracy while improving speed

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP2962184B1Systems and methods for requesting medical information
Publication Date: 2021.05.26 3M INNOVATIVE PROPERTIES CO
  • EP2962184B1 patent drawingFigure 1A
  • EP2962184B1 patent drawingFigure 1B
  • EP2962184B1 patent drawingFigure 1C

AI summary

This disclosure describes systems, devices, and techniques for automatically identifying missing or ambiguous information in documentation associated with a patient. In one example, a computerized system for updating medical documentation may include one or more computing devices configured to receive a code representative of one or more undocumented items determined from a plurality of documented items related to the patient. The one or more computing devices may be configured to generate, based on the code, query that solicits user input addressing the one or more undocumented items and output, for display, the query.