Clinical Validation of an Artificial Intelligence-Based Screening and Diagnostic Tool 3Nethra Ultima for chronic eye diseases compared to standard diagnostic methods
Overview
- Phase
- Not Applicable
- Status
- Not yet recruiting
- Sponsor
- Sankara Academy of Vision
- Enrollment
- 738
- Locations
- 1
- Primary Endpoint
- Comparison of clinical efficiency of AI tool in detecting Chronic eye conditions when compared to specialist (gold standard) diagnoses. For NIBUT, TMH, MGD, LLI, diabetic retinopathy (DR),age-related macular degeneration (AMD)
Overview
Brief Summary
This study aims to prospectively evaluate the diagnostic accuracy and clinical utility of the AI-based ophthalmic device 3Nethra Ultima for detecting Diabetic Retinopathy (DR), Age-Related Macular Degeneration (AMD), and Dry Eye Disease in a clinical setting. Diagnostic accuracy for DR and AMD will be assessed using fundus images from 3Nethra Ultima, 3Nethra Pico, and EIDON cameras, compared to a reference standard of independent dual expert grading and senior specialist adjudication. For Dry Eye Disease, the AI tool’s performance in measuring TBUT, TMH, LLI, and MGD will be evaluated against standard clinical diagnostic methods. The goal is to validate the AI system’s ability to support accurate, efficient, and scalable eye disease screening.To prospectively determine the diagnostic accuracy and clinical utility of the AI-driven 3nethra Ultima device for the automated detection of Diabetic Retinopathy (DR), Age-Related Macular Degeneration (AMD), and Dry Eye Disease, compared to established clinical diagnostic standards and masked expert evaluation.
Study Design
- Study Type
- Observational
Eligibility Criteria
- Ages
- 18.00 Year(s) to 75.00 Year(s) (—)
Inclusion Criteria
- •Participants who can understand and provide informed consent for participation in the study.
- •All Genders are included.
- •Adults with a diagnosis of Type 1 or Type 2 diabetes.
Exclusion Criteria
- •Participants with Active ocular infection Participants with Mature cataract Participants with Media opacities preventing good-quality retinal images History of Corneal surgery or trauma in past 6 months.
Outcomes
Primary Outcomes
Comparison of clinical efficiency of AI tool in detecting Chronic eye conditions when compared to specialist (gold standard) diagnoses. For NIBUT, TMH, MGD, LLI, diabetic retinopathy (DR),age-related macular degeneration (AMD)
Time Frame: first visit
Secondary Outcomes
- To test the sensitivity & specificity of AI tool in detecting the dry eye, retinal diseases like ARMD & Diabetic retinopathy(baseline one time visit)
Investigators
Dr. Kaushik Murali
sanakara Eye Foundation