Facial Image Prediction for Thyroid Eye Disease Visit Guidance

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Early diagnosis of thyroid eye disease is difficult due to the lack of clear prognostic symptoms, requiring in-person hospital visits for clinical activity score evaluation, which limits continuous monitoring and timely intervention.

Innovation Solution

A method and system using a digital camera to capture facial images, processing them to predict clinical activity scores for thyroid eye disease through conjunctival hyperemia, conjunctival edema, lacrimal edema, eyelid redness, and eyelid edema prediction models, enabling remote monitoring and hospital visit recommendations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If in-person hospital visits are required for clinical activity score evaluation, then diagnostic accuracy is improved, but accessibility and continuous monitoring capability deteriorate

Engineering Contradiction:

Improvediagnostic accuracyVSAvoidaccessibility

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The patent uses smartphone cameras to capture facial images that copy the visual characteristics needed for clinical evaluation. These images serve as substitutes for in-person medical examinations, allowing patients to monitor their thyroid eye disease symptoms remotely while maintaining diagnostic accuracy through automated image analysis algorithms.

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent replaces the mechanical process of in-person doctor-patient interaction and manual clinical examination with an automated digital image analysis system. The system uses algorithms to objectively measure clinical activity score parameters from smartphone images, eliminating the need for physical hospital visits while maintaining evaluation accuracy.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If in-person hospital visits are required for clinical activity score evaluation, then diagnostic accuracy is improved, but continuous monitoring capability deteriorates

Engineering Contradiction:

Improvediagnostic accuracyVSAvoidcontinuous monitoring capability

Core Design Contradiction:

Measurement precisionVSDuration of action of moving object

Solution Approach 1:

The patent enables continuous monitoring by allowing patients to repeatedly capture and upload facial images at different time points. The system continuously processes these images to track changes in clinical activity score over time, providing ongoing monitoring without requiring intermittent in-person visits. This continuous digital tracking maintains both accuracy and monitoring capability.

Inventive Principle:

Principle #20Continuity of useful action

Solution Approach 2:

The system creates a continuous digital record of patients' facial features through repeated smartphone photography. These copied images serve as permanent monitors of disease progression, allowing patients to track their condition continuously over time without leaving the home environment, thus maintaining both diagnostic accuracy and continuous monitoring capability.

Inventive Principle:

Principle #26Copying

3Measurement precision

If professional medical diagnostic devices are used for evaluation, then measurement precision is improved, but device complexity and cost deteriorate

Engineering Contradiction:

Improvemeasurement precisionVSAvoiddevice complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent employs smartphone cameras, which are simple and widely available devices, to capture the facial images needed for clinical evaluation. These smartphone images, rather than requiring complex professional medical diagnostic equipment, provide sufficient precision for automated analysis through carefully designed algorithms that process the captured images to determine clinical activity scores.

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent changes the approach from using complex hardware to using software algorithms for measurement. By transforming the evaluation process into a computational task that processes simple smartphone images through machine learning models, the system achieves measurement precision without requiring expensive or complex diagnostic devices, thus reducing device complexity while maintaining accuracy.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS20250322519A1Method for hospital visit guidance for medical treatment for active thyroid eye disease, and system for performing same

Publication Date: 2025.10.16 THYROSCOPE INC

AI summary

According to the present application, a computer-implemented method of predicting thyroid eye disease is disclosed. The method comprising: preparing a conjunctival hyperemia prediction model, a conjunctival edema prediction model, a lacrimal edema prediction model, an eyelid redness prediction model, and an eyelid edema prediction model, obtaining a facial image of an object, obtaining a first processed image and a second processed image from the facial image, wherein the first processed image is different from the second processed image, obtaining predicted values for each of a conjunctival hyperemia, a conjunctival edema and a lacrimal edema by applying the first processed image to the conjunctival hyperemia prediction model, the conjunctival edema prediction model, and the lacrimal edema prediction model, and obtaining predicted values for each of an eyelid redness and an eyelid edema by applying the second processed image to the eyelid redness prediction model and the eyelid edema prediction model.