Eye Movement Analysis for Remote Patient Recovery Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for estimating a patient's recovery level, especially in convalescent rehabilitation, are time-consuming, labor-intensive, and require hospital visits, limiting frequency and accuracy, and are not suitable for early detection of recurrence or monitoring outside a medical setting.
Innovation Solution
A recovery level estimation device that captures images of a patient's eyes to extract eye movement features using a machine learning-based model, allowing for remote and objective assessment of recovery level without the need for medical professionals or hospital visits.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional methods using medical professionals to evaluate patients are used, then measurement accuracy is improved, but loss of time and productivity deteriorate
Solution Approach 1:
The system enables automatic recovery level estimation through eye movement analysis without requiring medical professionals to conduct tests. The estimation device automatically captures images, extracts eye movement features, and estimates recovery levels using machine learning models, allowing the system to serve itself rather than relying on human operators for each measurement.
Solution Approach 2:
The patent replaces the mechanical system of manual evaluation by medical professionals with an automated image processing and machine learning system. The estimation device uses computer vision to capture eye movements and algorithms to analyze them, substituting human visual and manual assessment with automated computational analysis.
2Measurement precision
If traditional methods requiring hospital visits are used, then measurement accuracy is improved, but ease of operation deteriorates
Solution Approach 1:
The system creates a virtual copy of the hospital-based evaluation process that can be performed remotely. By capturing eye movement images and processing them through the same analytical algorithms used in clinical settings, the system replicates the accuracy of in-person evaluations while eliminating the need for physical hospital visits.
Solution Approach 2:
The estimation device is designed to perform recovery level assessment in multiple settings - both in hospitals and in home environments. The system can process eye movement images captured by various devices (cameras, smartphones) and provide consistent evaluation results regardless of location, making it universally applicable.
3Reliability
If frequent measurements are conducted using traditional methods, then reliability of recovery monitoring is improved, but loss of time and productivity worsen
Solution Approach 1:
The automated estimation device enables continuous and frequent recovery level measurements without the time constraints of manual evaluation. The system can process multiple measurements rapidly and consistently, maintaining continuous monitoring of patient progress rather than relying on periodic assessments spaced out due to resource limitations.
4Productivity
If walking-based evaluation methods are used, then productivity is improved, but object-generated harmful factors worsen due to fall risk
Solution Approach 1:
The system extracts the essential measurement component (eye movement) from the problematic activity (walking). By focusing solely on eye movement analysis rather than requiring full-body movement or walking tasks, the system eliminates the fall risk while preserving the ability to assess recovery level through a safe, stationary alternative.
Data Source
AI summary
In a recovery level estimation device, an image acquisition means acquires images in which eyes of a patient are captured. An eye movement feature extraction means extracts an eye movement feature which is a feature of an eye movement based on the images. A recovery level estimation means estimates a recovery level of the patient based on the eye movement feature by using a recovery level estimation model which has been learned by machine learning in advance.