Comparison of the DRISTi -Artificial Intelligence System with Ophthalmologist grading for Detection of Diabetic Retinopathy from fundus images.
试验速览
- 阶段
- 不适用
- 状态
- 尚未招募
- 入组人数
- 760
- 试验地点
- 1
- 主要终点
- The primary outcome is the sensitivity and specificity of the AI system in detecting eyes with mtmDR or vtDR, compared to the reference standard
研究概览
简要总结
India currently has 101 million people with diabetes, expected to rise to 134 million by 2045. Diabetic retinopathy affects about 35 percent of people with diabetes for over five years. Due to limited eye care access and few ophthalmologists, only a small percentage of diabetics receive regular screening. AI-based tools like DRISTi can help scale DR detection. This study aims to compare the diagnostic performance of Artificial Intelligence System with that of expert ophthalmologists.
To compare the sensitivity and specificity of DRISTi in detecting mtmDR and vtDR from fundus images versus ophthalmologist grading.
Retrospective observational study to be done over Three months for data collection, analysis, and reporting. 800 images in total Single-field images from different non-mydriatic cameras (Crystal Vue, Zeiss, Canon, Topcon) .
Data will be de-identified with secure storage and Ophthalmologist will be blinded to AI results. Metrics calculated at the eye level with 95 percent confidence intervals and Subgroup analysis by camera and for DME .
研究设计
- 研究类型
- Observational
入排标准
- 年龄范围
- 18.00 Year(s) 至 80.00 Year(s)（—）
- 性别
- All
入选标准
- •patients presenting for DR screening collected from multiple secondary and tertiary eye care hospitals and community screening site.
排除标准
- •patients attending hospital for reasons other than DR screening.
结局指标
主要结局
The primary outcome is the sensitivity and specificity of the AI system in detecting eyes with mtmDR or vtDR, compared to the reference standard
The primary outcome is the sensitivity and specificity of the AI system in detecting eyes with mtmDR or vtDR, compared to the reference standard
时间窗: NA
次要结局
- The primary outcome is the sensitivity and specificity of the AI system in detecting eyes with mtmDR or vtDR, compared to the reference standard. The secondary outcomes include the sensitivity and specificity of the AI system in identifying eyes with DME relative to the reference standard.
研究者
jyothsna rajagopal
ARTELUS-Artificial Learning Systems India Private Limited,