Assessment of Hypertensive Retinopathy Using Neural Network "RetinAIcheck"

N/ACompletedNCT07471971

I.M. Sechenov First Moscow State Medical University755 enrolled

Overview

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.

Study Type

OBSERVATIONAL

Enrollment

755

Conditions

Hypertensive Retinopathy

Interventions

Convolutional neural network "RetinAIcheck"DIAGNOSTIC_TEST

A convolutional neural network is a medical decision support system that processes digital fundus photographs obtained during mydriasis and determines the probability of the presence/absence of hypertensive retinopathy and it's grading due to Keith Wagener Barker's classification.

Eligibility

Sex: ALLMin age: 18 YearsHealthy volunteers:

Medical Language ↔ Plain English

Inclusion Criteria: \- Patients with and without a diagnosis of arterial hypertension, based on medical records Exclusion Criteria: * 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.

Outcomes

Primary Outcomes

Accuracy

The ability of a test to correctly identify the proportion of true positive cases

Time frame: The ability to correctly identify the presence or absence of condition

Secondary Outcomes

Sensitivity

The ability of a test to correctly identify the proportion of true positive cases

Time frame: February 2026

Specificity

The ability of a test to correctly identify the proportion of true negative cases

Time frame: February 2026

Positive predictive value

The probability that a person who tests positive for the condition actually has that one

Time frame: February 2026

Negative predictive value

The probability that a person who tests negative for the condition truly does not have it

Time frame: February 2026

AUROC, area under the ROC curve (one-versus-rest)

An average metric used to evaluate multi-class classification models by computing the Area Under the ROC Curve for each class separately against all other classes and then averaging the results

Time frame: February 2026

Quadratically weighted kappa

A statistical measure that evaluates the level of agreement between two raters or outcomes on an ordinal scale, penalizing errors based on the squared distance between categories

Time frame: February 2026

Assessment of Hypertensive Retinopathy Using Neural Network "RetinAIcheck"

Overview

Conditions

Interventions

Eligibility

Locations (1)

Outcomes

Primary Outcomes

Secondary Outcomes