Smartphone Eye-Marker Tracking for Neurodegeneration Risk Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for early detection of neurodegenerative diseases are expensive, intrusive, and impractical for wide population screening, lacking accessible and accurate biomarkers for cognitive decline.
Innovation Solution
A method utilizing image processing and machine learning to extract and analyze eye-markers from video streams, transforming them into derived features for use in a machine learning model to predict the risk of neurodegenerative diseases, employing Fourier transform, wavelet analysis, and fractal dimension analysis, and using a webcam or smartphone camera for data collection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If PET scan or CSF test is used for early detection of neurodegenerative diseases, then detection accuracy is improved, but cost and invasiveness increase
Solution Approach 1:
The patent replaces invasive medical imaging systems (PET scans, CSF tests) with a non-invasive optical system using smartphone cameras to capture eye movements. This substitution maintains detection capability while eliminating the need for intrusive procedures and expensive equipment, directly resolving the contradiction between accuracy and invasiveness/cost
Solution Approach 2:
The patent creates a digital copy of eye movement data from standard smartphone videos, transforming physiological signals into computational features that can be analyzed by machine learning models. This copying approach enables repeated, non-invasive measurements without the constraints of physical invasive tests
2Measurement precision
If PET scan or CSF test is used for early detection of neurodegenerative diseases, then detection accuracy is improved, but accessibility for wide population screening is reduced
Solution Approach 1:
The patent employs inexpensive smartphone cameras and standard video processing algorithms instead of expensive PET scanners. This cost reduction enables deployment in diverse settings including community screens, clinics, and homes, making early detection accessible to wide populations while maintaining accuracy through sophisticated data analysis
Solution Approach 2:
The system is designed to work with standard smartphone cameras and can detect multiple neurodegenerative disease types through unified eye movement feature analysis. This universal design allows the same system to screen for various conditions (Alzheimer's, Parkinson's, ALS) across different populations, greatly enhancing accessibility
3Measurement precision
If multiple eye-markers are collected and analyzed to improve detection accuracy, then measurement precision is improved, but data processing complexity increases
Solution Approach 1:
The patent divides the complex eye movement signal into distinct temporal segments and extracts specific features (fixation duration, saccade amplitude, blink rate) from each segment. This segmentation allows systematic analysis of multiple markers while managing complexity through structured feature extraction and separate processing of each eye-marker type
Solution Approach 2:
The system performs preliminary feature extraction and transformation of raw eye movement data into standardized computational features before final disease classification. This preliminary processing step simplifies subsequent analysis by preorganizing data into meaningful patterns, reducing the complexity of handling multiple eye-markers
Data Source
AI summary
A method and system for the early detection of neurodegeneration are described. The method comprises the steps of: a) extracting samples of a plurality of eye-markers of a user from a video stream captured by a visible light camera; b) loading said samples of said plurality of eye-markers to a big data repository, analyzing and consolidating them into one biomarker for detecting multiple disorders by means of training a machine learning model; and c) determining the risk of said user to develop a neurodegenerative disease using said trained machine learning model as part of an early detection screening or diagnosis process.