Medical Service Support Device for Natural Language Data Structuring

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Unstructured natural language data in medical records and reports makes it difficult to use and analyze, particularly for statistical purposes, and existing input procedures can be burdensome for users, requiring changes that are not user-friendly.

Innovation Solution

A medical service support device that processes natural language input data using medical ontology to generate structured data, allowing for analysis and confirmation in a user-friendly manner, minimizing changes to the input procedure by converting unstructured data into structured data for easier statistical use.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If natural language processing is applied to convert unstructured data into structured data, then statistical usability is improved, but processing time and complexity increase

Engineering Contradiction:
Improvestatistical usabilityVSAvoidprocessing complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system performs preliminary action by pre-processing and structuring medical record data before statistical analysis is needed. The natural language processing and structured data generation are conducted in advance, creating ready-to-use structured datasets that can be quickly queried and analyzed without requiring complex processing at the time of statistical use.

Inventive Principle:
Principle #10Preliminary action

2Productivity

If input procedure is changed to structure data at input time, then data usability is improved, but user burden increases

Engineering Contradiction:
Improvedata usabilityVSAvoiduser burden
Core Design Contradiction:
ProductivityVSEase of operation

Solution Approach 1:

The system applies self-service by automatically performing the data structuring process without requiring user intervention. The medical staff simply input data in natural language through the existing interface, and the system autonomously processes the text, extracts relevant information, and generates structured data in the background, eliminating the need for users to learn new complex input procedures.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system introduces an intermediary processing layer between the natural language input and the structured data output. This intermediary automatically performs text processing, entity recognition, and data structuring, acting as a mediator that translates user-friendly natural language input into machine-usable structured formats without requiring users to directly interact with the complex structuring mechanisms.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Measurement precision

If confirmation data is generated and displayed, then data accuracy is improved, but processing time increases

Engineering Contradiction:
Improvedata accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system applies partial action by selectively generating confirmation data based on the specific needs of the user and the context. Rather than always displaying complete confirmation data for every input, the system intelligently determines what confirmation is necessary, reducing unnecessary processing and display time while still ensuring data accuracy where it matters most.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS20220102013A1Medical service support device and medical service support system
Publication Date: 2022.03.31 CANON KK
  • US20220102013A1 patent drawing
  • US20220102013A1 patent drawing
  • US20220102013A1 patent drawing

AI summary

According to one embodiment, a medical service support device includes processing circuitry configured to: acquire medical ontology and input data entered in a remarks field of a medical record in a natural language; generate analysis data of the input data by executing natural language processing upon the input data; generate structured data in which the medical ontology is associated with the analysis data; generate confirmation data that expresses the structured data in the natural language; and display the confirmation data on a display.