Vertigo Diagnosis via Eye Movement Neural Network

Solution Overview

Problem

Current methods for diagnosing vertigo often require patients to visit multiple specialists, leading to high costs and inefficiencies, as vertigo symptoms can have various causes, necessitating a more effective and cost-efficient referral system.

Innovation Solution

A method using a trained neural network to analyze eye movement video data, capturing and processing it to accurately assign patients to the most likely specialist capable of diagnosing the cause of vertigo, thereby reducing unnecessary consultations and costs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If patients are referred to multiple specialists for vertigo diagnosis, then the probability of diagnosing the correct cause increases, but the time and cost expenditure increases significantly

Engineering Contradiction:

Improvediagnosis accuracyVSAvoiddiagnosis time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary analysis of eye movement video data using a neural network before the patient sees specialists. This preliminary action identifies the most likely cause categories (neurological, inner ear, other) and recommends specific specialists, so that the first specialist consultation is highly targeted and likely to be the correct one, eliminating the need for multiple sequential consultations

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces the mechanical system of manual specialist selection by general practitioners with an automated neural network system that objectively analyzes eye movement patterns. This substitution provides more accurate and consistent specialist recommendations, reducing misreferrals and the need for multiple specialist visits

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If patients are referred to multiple specialists for vertigo diagnosis, then the probability of diagnosing the correct cause increases, but the cost expenditure increases significantly

Engineering Contradiction:

Improvediagnosis accuracyVSAvoidcost

Core Design Contradiction:

ReliabilityVSLoss of energy

Solution Approach 1:

The system performs preliminary analysis of eye movement video data using a neural network before the patient sees specialists. This preliminary action identifies the most likely cause categories (neurological, inner ear, other) and recommends specific specialists, so that the first specialist consultation is highly targeted and likely to be the correct one, eliminating the need for multiple sequential consultations

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces the mechanical system of manual specialist selection by general practitioners with an automated neural network system that objectively analyzes eye movement patterns. This substitution provides more accurate and consistent specialist recommendations, reducing misreferrals and the need for multiple specialist visits

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Productivity

If general practitioners make specialist referrals based on time-limited examinations, then referrals can be made quickly, but the accuracy of specialist assignment decreases

Engineering Contradiction:

Improvereferral speedVSAvoidspecialist assignment accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent replaces the mechanical system of manual specialist selection by general practitioners with an automated neural network system that objectively analyzes eye movement patterns. This substitution provides more accurate and consistent specialist recommendations, reducing misreferrals and the need for multiple specialist visits

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system introduces an intermediary automated analysis step between the general practitioner's initial examination and the specialist referral decision. The neural network acts as a mediator that processes eye movement video data and provides objective recommendations, bridging the gap between quick GP assessment and accurate specialist assignment

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS20230389793A1Method for assigning a vertigo patient to a medical specialty

Publication Date: 2023.12.07 VERTIFY GMBH

AI summary

The present invention relates to a method for assigning a dizzy patient (SP) to a medical specialty (MF), comprising the following steps:Capture of eye movements (AB) of the dizzy patient (SP) in the form of video data (VD),Processing the acquired video data (VD) in a neural network (NN),Determine at least one medical specialty (MF) based on the result of processing in the neural network (NN),Outputting an assignment of the dizzy patient (SP) to the specific at least one medical specialty (MF).