Related Experiment Video
Updated: Mar 19, 2026
06:29
Comparing Objective Conjunctival Hyperemia Grading and the Ocular Surface Disease Index Score in Dry Eye Syndrome During COVID-19
Published on: May 25, 2022
2.9K
Evaluation of an automatic dry eye test using MCDM methods and rank correlation.
Diego Peteiro-Barral1, Beatriz Remeseiro2, Rebeca Méndez1
1Departamento de Computación, Universidade da Coruña, Campus de Elviña s/n, 15071, A Coruña, Spain.
Medical & Biological Engineering & Computing
|June 18, 2016
Summary
This study introduces a new machine learning methodology to improve dry eye disease diagnosis using automated tear film lipid layer classification. The approach optimizes classification performance for better clinical application.
Area of Science:
- Ophthalmology
- Medical Imaging
- Machine Learning
Background:
- Dry eye disease is prevalent, impacting daily activities.
- Current diagnosis relies on automated tear film lipid layer classification via image analysis.
- Existing methods have limitations in machine learning optimization.
Purpose of the Study:
- To present a methodology for optimizing machine learning in dry eye diagnosis.
- To enhance the accuracy of tear film lipid layer classification.
- To establish a baseline for other classification problems.
Main Methods:
- Class binarization
- Feature selection
- Classification optimization
- Conflict handling for decision-making methods
Main Results:
- The proposed methodology effectively improves dry eye diagnosis.
- Experimental results validate the methodology's performance.
- The approach demonstrates generalizability to other classification tasks.
Conclusions:
- The developed methodology significantly enhances dry eye disease classification.
- This approach offers a robust framework adaptable to various medical and biological classification problems.
Keywords:
Dry eye syndromeImage analysisMultiple criteria decision-makingPattern recognitionRank correlation
