Validation Study of RETINA-AI Galaxy™, an Automated Diabetic Retinopathy Screening Device

Completed

• Conditions: Diabetic Retinopathy; Diabetic Eye Problems; Diabetic Macular Edema
• Interventions: Procedure: Color Fundus Photography; Drug: Mydriatics Agent; Procedure: Optical Coherence Tomography (OCT)

• Registration Number: NCT04774822
• Lead Sponsor: RETINA-AI Health, Inc.

Brief Summary

Diabetes affects approximately 35 million Americans, each of whom needs at least one retinal exam per year. However, majority do not get their eye exam due to multiple prohibitive factors such as cost, transportation, difficulty of taking time off from work, and inconvenience, amongst others. The standard of care in diabetes requires at least an annual eye exam to detect onset of diabetic retinopathy and to treat when indicated. This is important as diabetes is the most common cause of visual impairment and blindness in working age adults in the United States. There are too few trained professionals to diagnose diabetic retinopathy, this prompted the development of RETINA-AI Galaxy an automated software as a medical device which screens for diabetic retinopathy in the primary care setting. This observational study is designed to validate the safety and efficacy of the device.

Detailed Description

This study is a prospective, multicenter, observational study to assess the safety and efficacy of RETINA-AI Galaxy in screening for diabetic retinopathy in the primary care setting. The study design conforms to an Intent to Screen (ITS) paradigm \[1\]. The Galaxy is a software medical device designed to analyze digital color fundus photographs and rapidly screen for the presence of more than mild diabetic retinopathy or vision-threatening diabetic retinopathy in the primary care setting.

The study will enroll 360 subjects after exclusions. Subjects who meet eligibility criteria will be recruited from three sites staffed by primary care providers. Eligibility will be assessed and informed consent obtained, after which digital color fundus photographs will be taken using U.S. Food and Drug Administration (FDA) cleared non-mydriatic fundus cameras, by an operator using the Galaxy photography manual.

There will be a total of 5 non-mydriatic robotic screening cameras used in the AI system protocol part of the study. There will be a dedicated validation camera used in the Validation Reading Center Protocol part of the study. Primary care clinical staff (e.g. medical assistant) with no prior professional ophthalmic photography experience and only a 4 hour training will operate the RETINA-AI Galaxy device and the screening cameras. The Retina Reading Center - certified professional ophthalmic photographers will operate the validation fundus cameras according the the 4W-D stereo protocol.

Study Timeline

• Study First Submitted: 2021-02-24
• Study First Submitted QC: 2021-02-24
• Study First Posted: 2021-03-01
• Study Start: 2021-03-25
• Primary Completion: 2021-05-28
• Study Completion: 2021-08-31
• Status Verified: 2021-09
• Last Update Submitted: 2021-09-14
• Last Update Posted: 2021-09-16

Recruitment & Eligibility

• Status: COMPLETED
• Sex: All
• Target Recruitment: 397

Inclusion Criteria

1. Patient age 22 or above

2. Patient with documented diagnosis of diabetes as defined by:

   A. Hemoglobin A1c (HbA1c)>= 6.5% based on repeated assessments

   B. Fasting Plasma Glucose (FPG) >= 126 mg/dL (7.0 mmol/L) based on repeated assessments

   C. Oral Glucose Tolerance test with 2 hr plasma glucose >= 200 mg/dL (11.1mmol/L) using equivalent of 75g anhydrous glucose dose in water.

   D. Symptoms of hyperglycemia or hyperglycemic crisis with random plasma glucose >=200mg/dL (11.1 mmol/L)

   E. Per World Health Organization (WHO) or American Diabetes Association diabetes criteria

3. Understanding of the Study and willingness and ability to sign informed consent

Exclusion Criteria

1. Persistent vision loss in one or both eyes
2. Diagnosis with macula edema, severe non-proliferative diabetic retinopathy, proliferative diabetic retinopathy, radiation retinopathy, or retinal vein occlusion
3. History of retinal laser treatment or intraocular injections of other eye; or any prior history of retinal surgery.
4. Current enrolled in another interventional study of an investigational device or drug and actively receiving investigational product for DR or DME
5. Subject has a condition that in the principal investigator's opinion would preclude participation in the study (e.g it may confound study results or result in ungradable photographs for clinical reference standard)
6. Subject has contraindication to mydriatic agent (dilating drops) or is unwilling or unable to dilate
7. Subject is contraindicated from fungus photography (e.g. subject is hypersensitivity to light).

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Arm && Interventions

Group	Intervention	Description
Sequential Enrollment	Color Fundus Photography	Enrollment based on default inclusion criteria listed below
Sequential Enrollment	Mydriatics Agent	Enrollment based on default inclusion criteria listed below
Sequential Enrollment	Optical Coherence Tomography (OCT)	Enrollment based on default inclusion criteria listed below
Enrichment Enrollment	Color Fundus Photography	Enrollment based periodic statistician-activated inclusion criteria adjustment to attain statistically adequate distribution
Enrichment Enrollment	Mydriatics Agent	Enrollment based periodic statistician-activated inclusion criteria adjustment to attain statistically adequate distribution
Enrichment Enrollment	Optical Coherence Tomography (OCT)	Enrollment based periodic statistician-activated inclusion criteria adjustment to attain statistically adequate distribution

Primary Outcome Measures

Name	Time	Method
To determine the sensitivity and specificity of RETINA-AI Galaxy to detect more than mild diabetic retinopathy in the primary care setting	1 visit (1 day)	To determine the sensitivity and specificity of RETINA-AI Galaxy for detecting more than mild diabetic retinopathy (mtmDR) defined as moderate non-proliferative diabetic retinopathy, severe non-proliferative diabetic retinopathy, proliferative diabetic retinopathy, or clinically significant diabetic macula edema.
To determine the sensitivity and specificity of RETINA-AI Galaxy to detect vision-threatening diabetic retinopathy in the primary care setting	1 visit (1 day)	To determine the sensitivity and specificity of RETINA-AI Galaxy for detecting vision threatening diabetic retinopathy (vtDR) defined as severe non-proliferative diabetic retinopathy, proliferative diabetic retinopathy, or clinically significant diabetic macula edema.

Trial Locations

Locations (3)

Clinical Trial Network; 🇺🇸 Houston, Texas, United States

Biopharma Informatic LLC; 🇺🇸 Houston, Texas, United States

Biopharma Informatic, LLC; 🇺🇸 Houston, Texas, United States