Patient-Specific Physical Condition Estimation Model Using Reference Images

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods for monitoring a patient's physical condition after discharge require specialized equipment and do not account for individual differences in reaction to physical condition deterioration or pain.

Innovation Solution

An information processing system that includes registration, model generation, physical condition information generation, and output control means to estimate a patient's physical condition using reference images and state information, allowing for personalized estimation with simple equipment.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If dedicated devices for acquiring cell image data or quantifying symptoms are used, then measurement precision is improved, but device complexity increases

Engineering Contradiction:

Improvephysical condition estimation accuracyVSAvoidequipment requirements

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent uses copied image data from existing photographs (reference images and current images) instead of requiring dedicated specialized devices. The system copies visual information from standard cameras and processes it through AI models to estimate physical conditions, thereby achieving measurement precision without complex dedicated equipment.

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent replaces mechanical/dedicated measurement devices with an information processing system that uses AI machine learning models. Instead of physical measurement instruments, the system uses computational models trained on image data to estimate physical conditions, substituting mechanical complexity with computational intelligence.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Device complexity

If generic symptom quantification methods are used, then device complexity is reduced, but measurement precision deteriorates due to lack of individualization

Engineering Contradiction:

Improveequipment simplicityVSAvoidindividualized estimation accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent applies local quality by creating patient-specific estimation models tailored to individual characteristics. Each model is trained on a patient's reference image and associated physical condition data, allowing the system to account for individual variations in appearance and response to treatment, thereby improving measurement precision for each specific patient.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system performs preliminary action by acquiring and storing reference images and physical condition data for each patient before the actual estimation process. This preliminary data collection and model training enables the system to achieve accurate individualized estimates without requiring complex real-time measurement devices.

Inventive Principle:

Principle #10Preliminary action

3Ease of operation

If standardized physical condition monitoring is used, then ease of operation is improved, but loss of information increases due to failure to capture individual differences

Engineering Contradiction:

Improvemonitoring simplicityVSAvoidindividual variation data

Core Design Contradiction:

Ease of operationVSLoss of information

Solution Approach 1:

The patent implements dynamics by making the estimation model adaptable and flexible for each patient. Instead of a rigid standardized approach, the system dynamically adjusts the estimation parameters and model characteristics to match individual patient characteristics, thereby capturing individual variations while maintaining ease of operation through automated processing.

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS20250037872A1Information processing system, information processing method, and non-transitory computer readable medium

Publication Date: 2025.01.30 NEC CORP

AI summary

An information processing system includes: a registration unit that acquires, for each patient, a reference image obtained by photographing a patient and state information related to at least one of a physical condition state or a progress status of the patient at the time of photographing; a model generation unit that generates, for each patient, a physical condition estimation model for estimating a physical condition of the patient based on the reference image and the state information; a physical condition information generation unit that generates information related to the physical condition of the target patient by inputting a photographed image or predetermined state information of the target patient to the physical condition estimation model for the target patient; and an output control unit that outputs the information related to the physical condition of the target patient.