A Study to Evaluate the Clinical Performance of VeriSee GLC for Screening of Glaucoma Suspect Using Color Fundus Images

Status

Completed

Phases

Unknown

Study type

Observational

Source

ClinicalTrials.gov

Registry ID

NCT07550712

Enrollment

773

Registered

2026-04-24

Start date

2024-08-26

Completion date

2024-12-27

Last updated

2026-06-25

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Glaucoma

Keywords

Glaucoma suspect

Brief summary

The goal of this observational study is to evaluate the clinical performance of VeriSee GLC for identifying glaucoma suspects using color fundus images in adult participants. The main questions it aims to answer are: * What are the sensitivity and specificity of VeriSee GLC for detecting glaucoma suspects based on fundus images? * How does the performance of VeriSee GLC compare with the reference standard defined by the majority consensus of three independent evaluators? Researchers will compare the screening results generated by VeriSee GLC with the reference standard to assess its diagnostic performance. This retrospective study will use previously collected fundus images. VeriSee GLC performs automated image analysis to identify glaucomatous signs, including retinal nerve fiber layer (RNFL) defects, vertical cup-to-disc ratio (VCDR) enlargement, and rim-to-disc ratio (RDR) changes. The output is intended to assist healthcare professionals in identifying glaucoma suspects for referral, rather than providing a definitive diagnosis.

Interventions

None listed

Study design

Observational model

CASE_ONLY

Time perspective

RETROSPECTIVE

Eligibility

Sex/Gender

ALL

Age

20 Years to No maximum

Inclusion criteria

1. The adult color fundus image (aged 20 and above) 2. The requirements of color fundus image * The resolution of image is 1024 × 1024 pixels or higher; * The angle view of image is 45-or 50-degree. * Images captured from eyes with myopia not exceeding -10 diopters. 3. The color fundus image includes the optic disc and RNFL areas, and one of these areas is evaluable, as judged by the healthcare professionals.

Exclusion criteria

1. The color fundus images previously used by VeriSee GLC during the development process and pre-clinical test. 2. A color fundus image of patients with cataracts, acute angle closure glaucoma or those who have undergone retinal laser surgery. 3. The optic disc and RNFL areas in the color fundus images is invisible to determine the disease condition as judged by the healthcare professionals.

Design outcomes

Primary

Measure	Time frame	Description
Sensitivity and Specificity of the VeriSee GLC for Screening Glaucoma Suspects	1 Day	The primary outcome is the sensitivity and specificity of the VeriSee GLC in identifying glaucoma suspects based on color fundus images, compared against the reference standard defined by the majority consensus of three independent evaluators.

Secondary

Measure	Time frame	Description
Positive Predictive Value (PPV), Negative Predictive Value (NPV), and Accuracy of VeriSee GLC for Screening Glaucoma Suspects	1 Day	Evaluate the PPV, NPV, and overall accuracy of the VeriSee GLC in identifying glaucoma suspects relative to the reference standard.
Accuracy of Detection for 3 Glaucomatous Signs - VCDR and RDR	1 Day	Assess the accuracy of VeriSee GLC in detecting three glaucomatous signs: * Vertical cup-to-disc ratio (VCDR ≥ 0.7) * Rim-to-disc ratio (RDR ≤ 0.1) * Retinal nerve fiber layer (RNFL) defect
Accuracy of Detection for 3 Glaucomatous Signs - RNFL Defect	1 Day	Assess the accuracy of VeriSee GLC in detecting three glaucomatous signs: * Vertical cup-to-disc ratio (VCDR ≥ 0.7) * Rim-to-disc ratio (RDR ≤ 0.1) * Retinal nerve fiber layer (RNFL) defect
Dice Coefficient of Disc and Cup Contours	1 Day	Dice coefficient measures the similarity between contours generated by VeriSee GLC and evaluator annotations. The Dice coefficient ranges from 0 (no overlap) to 1 (perfect agreement).

Countries

Taiwan

Participant flow

Recruitment details

\[Not Specified\]

Pre-assignment details