Study NCT04612868
Efficacy and Safety of AEYE-DS Software Device for Automated Detection of Diabetic Retinopathy From Digital Fundus Images
Submitted Date:  May 23, 2023 (v5)
Quality Control Review Has Not Concluded

Note: The results information displayed below has not completed the quality control (QC) review process. ClinicalTrials.gov must post results information for applicable clinical trials (ACTs) within 30 days of submission, even if the submission has not completed the QC review process. The study sponsor or investigator is responsible for ensuring the results information meets the QC review criteria.

This submission includes brief standardized QC review comments added by the National Library of Medicine (NLM). These comments indicate the location of apparent errors, deficiencies, or inconsistencies. For more information, see the Final Rule (42 CFR Part 11) Information page.
Open or close this module Study Identification
Unique Protocol ID: AEYE-DS-001
Brief Title: Efficacy and Safety of AEYE-DS Software Device for Automated Detection of Diabetic Retinopathy From Digital Fundus Images
Official Title: Pivotal Prospective Clinical Trial to Demonstrate the Efficacy and Safety of AEYE-DS Software Device for Automated Diabetic Retinopathy Detection From Digital Fundoscopic Images
Secondary IDs:
Open or close this module Study Status
Record Verification: May 2023
Overall Status: Completed
Study Start: October 16, 2020
Primary Completion: November 28, 2021 [Actual]
Study Completion: December 26, 2021 [Actual]
First Submitted: October 28, 2020
First Submitted that
Met QC Criteria:		 October 28, 2020
First Posted: November 3, 2020 [Actual]
Last Update Submitted that
Met QC Criteria:
Last Update Posted: June 22, 2023 [Actual]
Open or close this module Sponsor/Collaborators
Sponsor: AEYE Health Inc
Responsible Party: Sponsor
Collaborators:
Open or close this module Oversight
U.S. FDA-regulated Drug: No
U.S. FDA-regulated Device: Yes
Unapproved/Uncleared Device: Yes
Pediatric Postmarket Surveillance:
Data Monitoring:
Open or close this module Study Description
Brief Summary: AEYE-DS is a software device developed to increase compliance with diabetic retinopathy screening by automatically detecting more-than-mild diabetic retinopathy from digital fundus images using Artificial Intelligence (AI)-based software. This study has been designed to validate the safety and efficacy of the device at primary care and other point of care sites.
Detailed Description:
Open or close this module Conditions
Conditions: Diabetes Mellitus
Diabetic Retinopathy
Keywords:
Open or close this module Study Design
Study Type: Interventional
Primary Purpose: Diagnostic
Study Phase: Not Applicable
Interventional Study Model: Single Group Assignment
Number of Arms: 1
Masking: None (Open Label)
Allocation: N/A
Enrollment: 531 [Actual]
Open or close this module Arms and Interventions
Arms Assigned Interventions
Experimental: 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.
 Device: 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 Optical Coherence Tomography (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.
Open or close this module Outcome Measures
[See Results Section.]
Primary Outcome Measures:
1. Sensitivity and Specificity, Based on Two Macula-centered Images (One Image From Each Eye of the Patient)
[ Time Frame: 1 day ]

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).
Secondary Outcome Measures:
1. Sensitivity and Specificity, Based on Four Images (One Macula Centered Image and One Optic Disc Centered Image Per Eye)
[ Time Frame: 1 day ]

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)
2. Imageability, Based on Two Macula-centered Images (One Image From Each Eye of the Patient)
[ Time Frame: 1 day ]

To assess the imageability of AEYE-DS, defined as the percentage of participants with a disease level output (mtmDR+ or MTMDR-) from the AEYE-DS device.
3. Imageability, Based on Four Images (One Macula Centered Image and One Optic Disc Centered Image Per Eye)
[ Time Frame: 1 day ]

Quality Control Review Comment provided by the National Library of Medicine:

  1. The measure does not appear to include sufficient information to understand how outcomes are measured and reported.
Open or close this module Eligibility
Minimum Age: 22 Years
Maximum Age:
Sex: All
Gender Based:
Accepts Healthy Volunteers: No
Criteria:

Inclusion Criteria:

  • Age ≥22
  • Male or female
  • Documented diagnosis of diabetes mellitus, meeting the criteria established by the American Diabetes Association (ADA) and World Health Organization (WHO).
  • Understand the study and volunteer to sign the informed consent

Exclusion Criteria:

  • Uncorrectable vision loss (e.g., with the use of eyeglasses), blurred vision, or floaters.
  • Diagnosed with macular edema, severe non-proliferative retinopathy, proliferative retinopathy, radiation retinopathy, or retinal vein occlusion.
  • History of laser treatment of the retina or injections into either eye, or any history of retinal surgery.
  • Currently participating in another investigational eye study and actively receiving investigational product for Diabetic Retinopathy (DR) or Diabetic Macular Edema (DME).
  • Participant has a condition that, in the opinion of the investigator, would preclude participation in the study (e.g., unstable medical status including blood pressure or glycemic control, microphthalmia or previous enucleation).
  • Participant is contraindicated for imaging by fundus imaging systems used in the study:
    1. Participant is hypersensitive to light
    2. Participant recently underwent photodynamic therapy (PDT)
    3. Participant is taking medication that causes photosensitivity
    4. Participant has a history of angle-closure glaucoma or narrow anterior chamber angles
Open or close this module Contacts/Locations
Locations: United States, Kentucky
The Eye Care Institute
Louisville, Kentucky, United States, 40206
Open or close this module IPDSharing
Plan to Share IPD:
Open or close this module References
Citations:
Links:
Available IPD/Information:
Open or close this module Document Section
Study Protocol and Statistical Analysis Plan
Document Date: November 24, 2021
Uploaded: 05/23/2023 08:15
File Name: Prot_SAP_000.pdf
Study Results
Open or close this module Participant Flow
Recruitment Details
Pre-assignment Details
 
Arm/Group Title AEYE Software Device
Arm/Group Description

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.
Period Title: Overall Study
Started 531 [1]
Analyzable 468
Completed 462 [2]
Not Completed 69
[1]screened and enrolled
[2]included in statistical analysis (fully analyzable with valid ground truth and AEYE-DS results)
Open or close this module Baseline Characteristics
Arm/Group TitleAEYE Software Device
Arm/Group Description

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 Number of Baseline Participants 468
Baseline Analysis Population Description
Age, Continuous
Mean (Full Range)
Unit of measure: years
Number Analyzed468 Participants
55(21 to 88)
Sex: Female, Male
Measure Type: Count of Participants
Unit of measure: Participants
Number Analyzed468 Participants
Female
246
52.56%
Male
222
47.44%
Race/Ethnicity, Customized
Measure Type: Count of Participants
Unit of measure: Participants
Number Analyzed468 Participants
Rach and Ethnicity
African american
132
28.21%
White
186
39.74%
Hispanic or Latino
138
29.49%
other racial/ethnic origins
12
2.56%
Region of Enrollment
Measure Type: Count of Participants
Unit of measure: Participants
Number Analyzed468 Participants
United States
440
94.02%
Israel
28
5.98%
Open or close this module Outcome Measures
1. Primary Outcome:
Title Sensitivity and Specificity, Based on Two Macula-centered Images (One Image From Each Eye of the Patient)
Description 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).
Time Frame 1 day
Outcome Measure Data
Analysis Population Description
Completed subjects with valid ground truth and AEYE-DS results
 
Arm/Group TitleAEYE Software Device
Arm/Group Description

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 Number of Participants Analyzed462
Number (95% Confidence Interval)
Unit of Measure: percentage
Sensitivity
92.98(83.3 to 97.24)
Specificity
91.36(88.22 to 93.72)

Quality Control Review Comment provided by the National Library of Medicine:

  1. The number of participants analyzed appears inconsistent with data here or in other parts of the record.
2. Secondary Outcome:
Title Sensitivity and Specificity, Based on Four Images (One Macula Centered Image and One Optic Disc Centered Image Per Eye)
Description 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)
Time Frame 1 day
Outcome Measure Data
Analysis Population Description
completed subjects with valid ground truth and AEYE-DS results
 
Arm/Group TitleAEYE Software Device
Arm/Group Description

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 Number of Participants Analyzed462
Number (95% Confidence Interval)
Unit of Measure: percentage
Sensitivity
94.74(85.63 to 98.19)
Specificity
88.64(85.18 to 91.38)

Quality Control Review Comment provided by the National Library of Medicine:

  1. The number of participants analyzed appears inconsistent with data here or in other parts of the record.
3. Secondary Outcome:
Title Imageability, Based on Two Macula-centered Images (One Image From Each Eye of the Patient)
Description To assess the imageability of AEYE-DS, defined as the percentage of participants with a disease level output (mtmDR+ or MTMDR-) from the AEYE-DS device.
Time Frame 1 day
Outcome Measure Data
Analysis Population Description
[Not Specified]
 
Arm/Group TitleAEYE Software Device
Arm/Group Description

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 Number of Participants Analyzed462
Number (95% Confidence Interval)
Unit of Measure: percentage
99.1(97.8 to 99.7)
4. Secondary Outcome:
Title Imageability, Based on Four Images (One Macula Centered Image and One Optic Disc Centered Image Per Eye)
Description
Time Frame 1 day

Quality Control Review Comment provided by the National Library of Medicine:

  1. The measure does not appear to include sufficient information to understand how outcomes are measured and reported.
Outcome Measure Data
Analysis Population Description
[Not Specified]
 
Arm/Group TitleAEYE Software Device
Arm/Group Description

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 Number of Participants Analyzed462
Number (95% Confidence Interval)
Unit of Measure: percentage
99.1(97.8 to 99.7)
Open or close this module Adverse Events
 
Time Frame Since this study was non-interventional with regards to the AEYE-DS device (i.e., it did not come in contact with the study participants) and all interventions were conventional screening exams with FDA-cleared devices used to obtain all of the ophthalmic examinations, information about adverse events was not collected. No safety assessments were necessary.
Adverse Event Reporting Description Since this study was non-interventional with regards to the AEYE-DS device (i.e., it did not come in contact with the study participants) and all interventions were conventional screening exams with FDA-cleared devices used to obtain all of the ophthalmic examinations, information about adverse events was not collected. No safety assessments were necessary.
 
Arm/Group Title AEYE Software Device
Arm/Group Description

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.
All-Cause Mortality
  AEYE Software Device
 Affected / At Risk (%)
Total 0 / 0
Serious Adverse Events
  AEYE Software Device
 Affected / At Risk (%)
Total 0 / 0
Other (Not Including Serious) Adverse Events
Frequency Threshold for Reporting Other Adverse Events 0%
  AEYE Software Device
 Affected / At Risk (%)
Total 0 / 0
Open or close this module Limitations and Caveats
[Not specified]
Open or close this module More Information
Certain Agreements:
Principal Investigators are NOT employed by the organization sponsoring the study.

There is NOT an agreement between the Principal Investigator and the Sponsor (or its agents) that restricts the PI's rights to discuss or publish trial results after the trial is completed.
Results Point of Contact:
Name/Official Title:
 Zack Dvey-Aharon, PhD
Organization:
 AEYE Health Inc.
Phone:
 8662627343
Email:
 info@aeyehealth.com
Scroll to the Study top