Trial Outcomes & Findings for Efficacy and Safety of AEYE-DS Software Device for Automated Detection of Diabetic Retinopathy From Digital Fundus Images (NCT NCT04612868)

NCT ID: NCT04612868

Last Updated: 2023-08-01

Results Overview

Sensitivity and specificity of the AEYE-DS device to detect mtmDR on digital funduscopic images, acquired by the Topcon NW400 fundoscopy device, based on two macula-centered images (one image from each eye of the patient). Sensitivity and specificity were calculated by comparing the output results of the AEYE-DS device to the ground truth (diagnostic determination by an independent, blinded panel of expert ophthalmologists at a reading center). The worst of two eyes was compared with the AEYE-DS output at the participant level.

Recruitment status

COMPLETED

Study phase

NA

Target enrollment

531 participants

Primary outcome timeframe

1 day

Results posted on

2023-08-01

Participant Flow

Participant milestones

Participant milestones
Measure
AEYE Software Device
An AI software device (AEYE-DS) to be used as a diagnostic tool to assist primary care clinicians in screening for diabetic retinopathy using digital funduscopic images. The device automatically detects more than mild diabetic retinopathy (mtmDR) in adults diagnosed with diabetes who have not been previously diagnosed with diabetic retinopathy. AEYE Software Device: Eligible participants will undergo the following procedures: * Photographic imaging of each eye using a funduscopy camera device. Images obtained will be sent to the AEYE-DS software for analysis. * Additional photographic and OCT images will be obtained using a second funduscopy/OCT camera device. Images obtained will be sent to a professional reading center for analysis. * All study subjects will have their pupils dilated using dilation drops.
Overall Study
STARTED
531
Overall Study
Analyzable
468
Overall Study
COMPLETED
462
Overall Study
NOT COMPLETED
69

Reasons for withdrawal

Withdrawal data not reported

Baseline Characteristics

Efficacy and Safety of AEYE-DS Software Device for Automated Detection of Diabetic Retinopathy From Digital Fundus Images

Baseline characteristics by cohort

Baseline characteristics by cohort
Measure
AEYE Software Device
n=468 Participants
An AI software device (AEYE-DS) to be used as a diagnostic tool to assist primary care clinicians in screening for diabetic retinopathy using digital funduscopic images. The device automatically detects more than mild diabetic retinopathy (mtmDR) in adults diagnosed with diabetes who have not been previously diagnosed with diabetic retinopathy. AEYE Software Device: Eligible participants will undergo the following procedures: * Photographic imaging of each eye using a funduscopy camera device. Images obtained will be sent to the AEYE-DS software for analysis. * Additional photographic and OCT images will be obtained using a second funduscopy/OCT camera device. Images obtained will be sent to a professional reading center for analysis. * All study subjects will have their pupils dilated using dilation drops.
Age, Continuous
55 years
n=5 Participants
Sex: Female, Male
Female
246 Participants
n=5 Participants
Sex: Female, Male
Male
222 Participants
n=5 Participants
Ethnicity (NIH/OMB)
Hispanic or Latino
138 Participants
n=5 Participants
Ethnicity (NIH/OMB)
Not Hispanic or Latino
329 Participants
n=5 Participants
Ethnicity (NIH/OMB)
Unknown or Not Reported
1 Participants
n=5 Participants
Race (NIH/OMB)
American Indian or Alaska Native
1 Participants
n=5 Participants
Race (NIH/OMB)
Asian
9 Participants
n=5 Participants
Race (NIH/OMB)
Native Hawaiian or Other Pacific Islander
0 Participants
n=5 Participants
Race (NIH/OMB)
Black or African American
132 Participants
n=5 Participants
Race (NIH/OMB)
White
323 Participants
n=5 Participants
Race (NIH/OMB)
More than one race
2 Participants
n=5 Participants
Race (NIH/OMB)
Unknown or Not Reported
1 Participants
n=5 Participants
Region of Enrollment
United States
440 Participants
n=5 Participants
Region of Enrollment
Israel
28 Participants
n=5 Participants

PRIMARY outcome

Timeframe: 1 day

Population: Completed subjects with valid ground truth and AEYE-DS results

Sensitivity and specificity of the AEYE-DS device to detect mtmDR on digital funduscopic images, acquired by the Topcon NW400 fundoscopy device, based on two macula-centered images (one image from each eye of the patient). Sensitivity and specificity were calculated by comparing the output results of the AEYE-DS device to the ground truth (diagnostic determination by an independent, blinded panel of expert ophthalmologists at a reading center). The worst of two eyes was compared with the AEYE-DS output at the participant level.

Outcome measures

Outcome measures
Measure
AEYE Software Device
n=462 Participants
An AI software device (AEYE-DS) to be used as a diagnostic tool to assist primary care clinicians in screening for diabetic retinopathy using digital funduscopic images. The device automatically detects more than mild diabetic retinopathy (mtmDR) in adults diagnosed with diabetes who have not been previously diagnosed with diabetic retinopathy. AEYE Software Device: Eligible participants will undergo the following procedures: * Photographic imaging of each eye using a funduscopy camera device. Images obtained will be sent to the AEYE-DS software for analysis. * Additional photographic and OCT images will be obtained using a second funduscopy/OCT camera device. Images obtained will be sent to a professional reading center for analysis. * All study subjects will have their pupils dilated using dilation drops.
Sensitivity and Specificity, Based on Two Macula-centered Images (One Image From Each Eye of the Patient)
Sensitivity
92.98 percentage of participants
Interval 83.3 to 97.24
Sensitivity and Specificity, Based on Two Macula-centered Images (One Image From Each Eye of the Patient)
Specificity
91.36 percentage of participants
Interval 88.22 to 93.72

SECONDARY outcome

Timeframe: 1 day

Population: completed subjects with valid ground truth and AEYE-DS results

Sensitivity and specificity of the AEYE-DS device to detect mtmDR from digital funduscopic images, acquired by the Topcon NW400 fundoscopy device, based on four images (one macula centered image and one optic disc centered image per eye). Sensitivity and specificity were calculated by comparing the output results of the AEYE-DS device to the ground truth (diagnostic determination by an independent, blinded panel of expert ophthalmologists at a reading center). The worst of two eyes was compared with the AEYE-DS output at the participant level.

Outcome measures

Outcome measures
Measure
AEYE Software Device
n=462 Participants
An AI software device (AEYE-DS) to be used as a diagnostic tool to assist primary care clinicians in screening for diabetic retinopathy using digital funduscopic images. The device automatically detects more than mild diabetic retinopathy (mtmDR) in adults diagnosed with diabetes who have not been previously diagnosed with diabetic retinopathy. AEYE Software Device: Eligible participants will undergo the following procedures: * Photographic imaging of each eye using a funduscopy camera device. Images obtained will be sent to the AEYE-DS software for analysis. * Additional photographic and OCT images will be obtained using a second funduscopy/OCT camera device. Images obtained will be sent to a professional reading center for analysis. * All study subjects will have their pupils dilated using dilation drops.
Sensitivity and Specificity, Based on Four Images (One Macula Centered Image and One Optic Disc Centered Image Per Eye)
Sensitivity
94.74 percentage of participants
Interval 85.63 to 98.19
Sensitivity and Specificity, Based on Four Images (One Macula Centered Image and One Optic Disc Centered Image Per Eye)
Specificity
88.64 percentage of participants
Interval 85.18 to 91.38

SECONDARY outcome

Timeframe: 1 day

To assess the imageability of AEYE-DS, defined as the percentage of participants with a diagnostic output (positive for more than mild DR or negative for more than mild DR) from the AEYE-DS device. Participants with no diagnostic output (i.e., AEYE-DS output of "Insufficient Quality") lowers the imageability of the AEYE-DS.

Outcome measures

Outcome measures
Measure
AEYE Software Device
n=462 Participants
An AI software device (AEYE-DS) to be used as a diagnostic tool to assist primary care clinicians in screening for diabetic retinopathy using digital funduscopic images. The device automatically detects more than mild diabetic retinopathy (mtmDR) in adults diagnosed with diabetes who have not been previously diagnosed with diabetic retinopathy. AEYE Software Device: Eligible participants will undergo the following procedures: * Photographic imaging of each eye using a funduscopy camera device. Images obtained will be sent to the AEYE-DS software for analysis. * Additional photographic and OCT images will be obtained using a second funduscopy/OCT camera device. Images obtained will be sent to a professional reading center for analysis. * All study subjects will have their pupils dilated using dilation drops.
Imageability, Based on Two Macula-centered Images (One Image From Each Eye of the Patient)
99.1 percentage of participants
Interval 97.8 to 99.7

SECONDARY outcome

Timeframe: 1 day

To assess the imageability of AEYE-DS, defined as the percentage of participants with a diagnostic output (positive for more than mild DR or negative for more than mild DR) from the AEYE-DS device. Participants with no diagnostic output (i.e., AEYE-DS output of "Insufficient Quality") lowers the imageability of the AEYE-DS.

Outcome measures

Outcome measures
Measure
AEYE Software Device
n=462 Participants
An AI software device (AEYE-DS) to be used as a diagnostic tool to assist primary care clinicians in screening for diabetic retinopathy using digital funduscopic images. The device automatically detects more than mild diabetic retinopathy (mtmDR) in adults diagnosed with diabetes who have not been previously diagnosed with diabetic retinopathy. AEYE Software Device: Eligible participants will undergo the following procedures: * Photographic imaging of each eye using a funduscopy camera device. Images obtained will be sent to the AEYE-DS software for analysis. * Additional photographic and OCT images will be obtained using a second funduscopy/OCT camera device. Images obtained will be sent to a professional reading center for analysis. * All study subjects will have their pupils dilated using dilation drops.
Imageability, Based on Four Images (One Macula Centered Image and One Optic Disc Centered Image Per Eye)
99.1 percentage of participants
Interval 97.8 to 99.7

Adverse Events

AEYE Software Device

Serious events: 0 serious events
Other events: 0 other events
Deaths: 0 deaths

Serious adverse events

Adverse event data not reported

Other adverse events

Adverse event data not reported

Additional Information

Zack Dvey-Aharon, PhD

AEYE Health Inc.

Phone: 8662627343

Results disclosure agreements

  • Principal investigator is a sponsor employee
  • Publication restrictions are in place