Trial Outcomes & Findings for A Study to Evaluate the Clinical Performance of VeriSee GLC for Screening of Glaucoma Suspect Using Color Fundus Images (NCT NCT07550712)
NCT ID: NCT07550712
Last Updated: 2026-06-25
Results Overview
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.
COMPLETED
773 participants
1 Day
2026-06-25
Participant Flow
\[Not Specified\]
\[Not Specified\]
Participant milestones
| Measure |
Test Group
The 773 cases from the intended use population, having one qualified color fundus images determined by the ophthalmologist, were enrolled in this study. A total of 773 color fundus images from all enrolled cases were included for effectiveness analysis.
|
|---|---|
|
Overall Study
STARTED
|
773
|
|
Overall Study
COMPLETED
|
749
|
|
Overall Study
NOT COMPLETED
|
24
|
Reasons for withdrawal
| Measure |
Test Group
The 773 cases from the intended use population, having one qualified color fundus images determined by the ophthalmologist, were enrolled in this study. A total of 773 color fundus images from all enrolled cases were included for effectiveness analysis.
|
|---|---|
|
Overall Study
Insufficient image quality
|
6
|
|
Overall Study
Insufficient information
|
18
|
Baseline Characteristics
Race and Ethnicity were not collected from any participant.
Baseline characteristics by cohort
| Measure |
Test Group
n=773 Participants
The 773 cases from the intended use population, having one qualified color fundus images determined by the ophthalmologist, were enrolled in this study. A total of 773 color fundus images from all enrolled cases were included for effectiveness analysis.
|
|---|---|
|
Age, Continuous
|
60 years
STANDARD_DEVIATION 14.7 • n=773 Participants
|
|
Sex: Female, Male
Female
|
466 Participants
n=773 Participants
|
|
Sex: Female, Male
Male
|
307 Participants
n=773 Participants
|
|
Spherical Equivalent
|
-2.7 Diopter (D)
STANDARD_DEVIATION 3.1 • n=773 Participants
|
PRIMARY outcome
Timeframe: 1 DayPopulation: Of the 773 included cases, 24 were excluded from the analysis due to insufficient image quality or insufficient clinical information.
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.
Outcome measures
| Measure |
Test Group
n=749 Participants
The 773 cases from the intended use population, having one qualified color fundus images determined by the ophthalmologist, were enrolled in this study. A total of 773 color fundus images from all enrolled cases were included for effectiveness analysis.
|
|---|---|
|
Sensitivity and Specificity of the VeriSee GLC for Screening Glaucoma Suspects
Sensitivity
|
90.3 percent
Interval 86.8 to 93.8
|
|
Sensitivity and Specificity of the VeriSee GLC for Screening Glaucoma Suspects
Specificity
|
82.1 percent
Interval 78.7 to 85.8
|
SECONDARY outcome
Timeframe: 1 DayPopulation: Of the 773 included cases, 24 were excluded from the analysis due to insufficient image quality or insufficient clinical information.
Evaluate the PPV, NPV, and overall accuracy of the VeriSee GLC in identifying glaucoma suspects relative to the reference standard.
Outcome measures
| Measure |
Test Group
n=749 Participants
The 773 cases from the intended use population, having one qualified color fundus images determined by the ophthalmologist, were enrolled in this study. A total of 773 color fundus images from all enrolled cases were included for effectiveness analysis.
|
|---|---|
|
Positive Predictive Value (PPV), Negative Predictive Value (NPV), and Accuracy of VeriSee GLC for Screening Glaucoma Suspects
Positive predictive value (PPV)
|
73.8 percent
Interval 69.0 to 78.5
|
|
Positive Predictive Value (PPV), Negative Predictive Value (NPV), and Accuracy of VeriSee GLC for Screening Glaucoma Suspects
Negative predictive value (NPV)
|
93.8 percent
Interval 91.5 to 96.1
|
|
Positive Predictive Value (PPV), Negative Predictive Value (NPV), and Accuracy of VeriSee GLC for Screening Glaucoma Suspects
Overall Accuracy
|
85.0 percent
Interval 82.5 to 87.6
|
SECONDARY outcome
Timeframe: 1 DayPopulation: Of the 749 evaluable images, 733 images were of legible quality in the optic disc area, and 737 images were of legible quality in the RNFL area.
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
Outcome measures
| Measure |
Test Group
n=733 Participants
The 773 cases from the intended use population, having one qualified color fundus images determined by the ophthalmologist, were enrolled in this study. A total of 773 color fundus images from all enrolled cases were included for effectiveness analysis.
|
|---|---|
|
Accuracy of Detection for 3 Glaucomatous Signs - VCDR and RDR
Accuracy of VeriSee GLC in Detecting VCDR ≥ 0.7
|
95.2 percent
Interval 93.7 to 96.8
|
|
Accuracy of Detection for 3 Glaucomatous Signs - VCDR and RDR
Accuracy of VeriSee GLC in Detecting RDR ≤ 0.1
|
93.6 percent
Interval 91.8 to 95.4
|
SECONDARY outcome
Timeframe: 1 DayPopulation: Of the 749 evaluable images, 733 images were of legible quality in the optic disc area, and 737 images were of legible quality in the RNFL area.
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
Outcome measures
| Measure |
Test Group
n=737 Participants
The 773 cases from the intended use population, having one qualified color fundus images determined by the ophthalmologist, were enrolled in this study. A total of 773 color fundus images from all enrolled cases were included for effectiveness analysis.
|
|---|---|
|
Accuracy of Detection for 3 Glaucomatous Signs - RNFL Defect
|
83.3 percent
Interval 80.6 to 86.0
|
SECONDARY outcome
Timeframe: 1 DayPopulation: Of the 773 included cases, 24 were excluded from the analysis due to insufficient image quality or insufficient clinical information.
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).
Outcome measures
| Measure |
Test Group
n=749 Participants
The 773 cases from the intended use population, having one qualified color fundus images determined by the ophthalmologist, were enrolled in this study. A total of 773 color fundus images from all enrolled cases were included for effectiveness analysis.
|
|---|---|
|
Dice Coefficient of Disc and Cup Contours
Dice coefficient for disc contour
|
0.97 unitless
Interval 0.91 to 0.98
|
|
Dice Coefficient of Disc and Cup Contours
Dice coefficient for cup contour
|
0.87 unitless
Interval 0.63 to 0.97
|
Adverse Events
Test Group
Serious adverse events
Adverse event data not reported
Other adverse events
Adverse event data not reported
Additional Information
Manager of Regulatory Affairs & Quality Assurance
Acer Medical Inc.
Results disclosure agreements
- Principal investigator is a sponsor employee
- Publication restrictions are in place