Glaucoma Prediction via Archetypal Visual Field Decomposition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods fail to accurately predict clinical parameters related to glaucoma from central visual field patterns, which is crucial for early detection and intervention in glaucoma progression.
Innovation Solution
A system utilizing a processor and machine learning model that decomposes visual field data into archetypal patterns, generating decomposition coefficients to determine clinical parameters, including glaucoma severity, through archetypal analysis and pattern decomposition, enabling informed clinical decisions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If current methods are used to predict clinical parameters from central visual field patterns, then the prediction accuracy is insufficient, but the complexity of the system remains high
Solution Approach 1:
The patent segments the visual field data into distinct archetypal patterns (e.g., nasal step, temporal step, arcuate patterns) through archetypal analysis. This segmentation allows the complex visual field data to be broken down into manageable, interpretable components that can be systematically analyzed and correlated with clinical parameters, thereby improving prediction accuracy while maintaining manageable system complexity
Solution Approach 2:
The patent introduces archetypal patterns as intermediary representations between the raw visual field data and the clinical parameters. These archetypal patterns serve as a mediator that translates complex visual field measurements into meaningful clinical insights, enabling accurate prediction without requiring overly complex direct modeling approaches
2Adaptability or versatility
If archetypal analysis is applied to decompose visual field data, then the ability to categorize patterns improves, but the computational requirements increase
Solution Approach 1:
The patent performs archetypal analysis and pattern decomposition as preliminary actions during the data processing stage. By pre-computing the archetypal patterns and their decomposition coefficients, the system prepares the data in advance for subsequent clinical parameter prediction, thereby improving pattern categorization capability while managing computational resources through efficient preprocessing
Data Source
AI summary
Systems and methods are provided for predicting clinical parameters relating to glaucoma from central visual field patterns. A system includes a processor, an output device, and a computer readable medium that stores executable instructions. The instructions provide a pattern decomposition component that receives a set of visual field data for a patient representing, for each of a plurality of locations in the central region of an eye of the patient, a deviation in sensitivity to a visual stimulus from an age-adjusted normal value and decomposes the set of visual field data into a linear combination of a set of patterns defined via archetypal analysis over a corpus of visual field data to provide a set of decomposition coefficients. A machine learning model determines a clinical parameter for the patient from at least the set of decomposition coefficients, and a user interface provides the determined clinical parameter to a user.