Glaucoma Diagnostic Data Harmonization via Common Scale Conversion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current diagnostic tests for glaucoma, when used in isolation, lack sufficient accuracy and applicability across the patient population and disease dynamic range, leading to inconsistent and subjective clinical assessments due to test-retest variability and confounding factors.
Innovation Solution
The development of combinatorial analysis techniques that transform measurements from multiple diagnostic tests into a common distribution and scale, using conversion functions and machine learning methods to simplify interpretation, improve diagnostic accuracy, and provide a reliable and objective assessment of glaucoma stage and progression.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple diagnostic tests are used in isolation, then each test provides useful information for diagnosis and progression, but the diagnostic accuracy and applicability across patient population and disease dynamic range is insufficient
Solution Approach 1:
The patent combines multiple diagnostic tests (visual field testing, RNFL analysis, ONH analysis) into a unified combinatorial analysis system. The system integrates data from different test modalities by converting them to a common distribution and scale, then analyzes them together to produce comprehensive diagnostic assessments that improve accuracy across diverse patient populations and disease stages.
Solution Approach 2:
The combinatorial analysis system serves multiple functions simultaneously: it detects glaucoma presence, assesses disease stage, monitors progression over time, and provides simplified interpretation of complex multi-test data. This universal approach applies across the entire patient population spectrum from early to advanced disease stages.
2Ease of operation
If clinicians correlate results from different tests manually, then clinical assessment can be made, but the task is difficult and subjective with high variability across observers
Solution Approach 1:
The system performs automated combinatorial analysis that self-interprets complex multi-test data without requiring manual clinician correlation. The automated algorithm consistently applies the same conversion functions and analysis criteria, eliminating observer variability and providing reliable, reproducible assessments that are easier to operate while maintaining high diagnostic accuracy.
3Loss of information
If test results are presented in their original formats, then detailed information is available, but the interpretation process becomes complex and time-consuming
Solution Approach 1:
The system extracts key diagnostic information from the complex multi-test data by converting all test results to a common distribution and scale, then identifies and presents only the most clinically relevant findings. This extraction process maintains complete diagnostic information while significantly reducing interpretation time through automated synthesis and simplified presentation of critical results.
Data Source
Figure 1a
Figure 1b
Figure 2~3
AI summary
The subject invention relates to combinatorial analyses of data from two or more diagnostic tests for the detection of eye diseases, simplified interpretation of test results, and assessment of disease stage and rate of change. Of particular interest is to develop combinatorial analyses to improve glaucoma detection and progression rate assessment based on combinations of structural and functional tests. More specifically, approaches are described where data of one or more tests and their normative database are converted to the distribution and scale of another test for further analysis to detect glaucomatous damage; approaches are also described where data of more than one tests are used to assess stage index and rate of change; in addition, methods for displaying the combinatorial analysis results are disclosed.