Real-time Artificial Intelligence System for Detecting Multiple Ocular Fundus Lesions by Ultra-widefield Fundus Imaging: A Prospective Multicenter Study
Overview
- Phase
- Not Applicable
- Intervention
- Not specified
- Conditions
- Artificial Intelligence
- Sponsor
- Sun Yat-sen University
- Enrollment
- 2000
- Locations
- 1
- Primary Endpoint
- Accuracy
- Last Updated
- 5 years ago
Overview
Brief Summary
This prospective multicenter study will evaluate the efficacy of a real-time artificial intelligence system for detecting multiple ocular fundus lesions by ultra-widefield fundus imaging in real-world settings.
Detailed Description
The ocular fundus can show signs of both ocular diseases (e.g., lattice degeneration, retinal detachment and glaucoma) and systemic diseases (e.g., hypertension, diabetes and leukemia). The routine fundus examination is conducive for early detection of these diseases. However, manual conducting fundus examination needs an experienced retina ophthalmologist, and is time-consuming and labor-intensive, which is difficult for its routine implementation on large scale. This study will develop an artificial intelligence system integrating with ultra-widefield fundus imaging to automatically screen for multiple ocular fundus lesions in real time and evaluate its performance in different real-world settings. The efficacy of the system will compare to the final diagnoses of each participant made by experienced ophthalmologists.
Investigators
Haotian Lin
Professor
Sun Yat-sen University
Eligibility Criteria
Inclusion Criteria
- •All the participants who agree to take ultra-widefield fundus images.
Exclusion Criteria
- •Patients who cannot cooperate with a photographer such as some paralytics, the patients with dementia and severe psychopaths.
- •Patients who do not agree to sign informed consent.
Outcomes
Primary Outcomes
Accuracy
Time Frame: 8 months
Performance of artificial intelligence system for detecting multiple ocular fundus lesions based on ultra-widefield fundus imaging.
Secondary Outcomes
- False-positive rate(8 months)
- Sensitivity(8 months)
- Cohen's kappa coefficient(8 months)
- Specificity(8 months)
- False-negative rate(8 months)
- Data processing time of AI system(8 months)