Assessment of Hypertensive Retinopathy Using Keith Wagener Barker's Classification, Based on Neural Network "RetinAIcheck"
试验速览
- 阶段
- 不适用
- 状态
- 已完成
- 入组人数
- 755
- 试验地点
- 1
- 主要终点
- Accuracy
研究概览
简要总结
The current study is aimed at estimating the diagnostic effectiveness of a developed neural network "RetinAIcheck" in grading the severity of hypertensive retinopathy in patients of the Russian population.
The training data set was obtained from an open source and relabeled by seven independent retina specialists, the sample size was 30,000 fundus photographs. The test sample included 755 patients (1374 eyes). Among the 1.374 eyes, 94 were without HR (class 0), 330 had class 1, 660 had class 2, 280 had class 3, and 10 had class 4 HR.The reference standard was the result of independent grading of HR stage by two ophthalmologists, controversial clinical cases were evaluated with the involvement of a third ophthalmologist.
研究设计
- 研究类型
- Observational
- 观察模型
- Other
- 时间视角
- Cross Sectional
入排标准
- 年龄范围
- 18 Years 至 —（Adult, Older Adult）
- 性别
- All
- 接受健康志愿者
- 是
入选标准
- •- Patients with and without a diagnosis of arterial hypertension, based on medical records
排除标准
- •anophthalmia,
- •optic nerve atrophy,
- •eyeball injuries,
- •age-related macular degeneration,
- •central serous chorioretinopathy,
- •central serous chorioretinitis,
- •clouding of the optical media of the eye, which affects the quality of the image.
研究组 & 干预措施
Class 0 without signs of hypertensive retinopathy
干预措施: Convolutional neural network "RetinAIcheck" (Diagnostic Test)
Class 1 hypertensive retinopathy
干预措施: Convolutional neural network "RetinAIcheck" (Diagnostic Test)
Class 2 hypertensive retinopathy
干预措施: Convolutional neural network "RetinAIcheck" (Diagnostic Test)
Class 3 hypertensive retinopathy
干预措施: Convolutional neural network "RetinAIcheck" (Diagnostic Test)
Class 3+4 hypertensive retinopathy
干预措施: Convolutional neural network "RetinAIcheck" (Diagnostic Test)
结局指标
主要结局
Accuracy
时间窗: The ability to correctly identify the presence or absence of condition
The ability of a test to correctly identify the proportion of true positive cases
次要结局
- Positive predictive value(February 2026)
- Negative predictive value(February 2026)
- AUROC, area under the ROC curve (one-versus-rest)(February 2026)
- Quadratically weighted kappa(February 2026)
- Sensitivity(February 2026)
- Specificity(February 2026)