Clinical Efficacy of Implementing an AI-SaMD for Funduscopy Analysis in Patients With Diabetes Mellitus
SAFE-DM
1 other identifier
interventional
340
1 country
1
Brief Summary
The objective of this study is to investigate the efficacy of implementing the AI-SaMD(VUNO Med®-Fundus AI™) alongside routine clinical practice for the detection of diabetic retinopathy.
Trial Health
Trial Health Score
Automated assessment based on enrollment pace, timeline, and geographic reach
participants targeted
Target at P75+ for not_applicable
Started Apr 2026
1 active site
Health score is calculated from publicly available data and should be used for screening purposes only.
Trial Relationships
Click on a node to explore related trials.
Study Timeline
Key milestones and dates
First Submitted
Initial submission to the registry
January 23, 2026
CompletedFirst Posted
Study publicly available on registry
January 30, 2026
CompletedStudy Start
First participant enrolled
April 7, 2026
CompletedPrimary Completion
Last participant's last visit for primary outcome
August 31, 2027
ExpectedStudy Completion
Last participant's last visit for all outcomes
August 31, 2027
April 13, 2026
April 1, 2026
1.4 years
January 23, 2026
April 8, 2026
Conditions
Outcome Measures
Primary Outcomes (1)
True Referral Rate
The true referral rate is defined as the proportion of subjects who were diagnosed with diabetic retinopathy by an ophthalmologist among those referred to ophthalmology with suspected diabetic retinopathy. The true referral rate will be compared between the intervention and control groups.
within 6 months
Secondary Outcomes (7)
Diabetic Retinopathy (DR) Diagnosis Rate
Within 6 months
Odds Ratio
Within 6 months
Referral Rate
Within 6 months
Time to Diabetic Retinopathy Diagnosis
Within 6 months
Performance of the AI System in Detecting Diabetic Retinopathy
Within 6 months
- +2 more secondary outcomes
Other Outcomes (1)
Interim Analysis
Within 6 months
Study Arms (2)
Intervention group
EXPERIMENTALFor participants assigned to the intervention group, VUNO Med®-Fundus AI™ will be applied to the acquired fundus images, and the AI-generated outputs will be shown to clinicians during routine care.
Control group
NO INTERVENTIONFor participants assigned to the control group, fundus images will be interpreted according to usual clinical care without AI assistance.
Interventions
VUNO Med®-Fundus AI™ is an artificial intelligence-based fundus image detection and diagnostic support software. The software automatically identifies abnormal retinal findings and provides information on the type and location of detected abnormalities to aid clinical decision-making.
Eligibility Criteria
You may qualify if:
- Adults aged 19 years or older.
- A documented diagnosis of type 2 diabetes mellitus.
- Ability to communicate adequately and provide written informed consent for participation in the study.
You may not qualify if:
- A prior diagnosis of diabetic retinopathy at the time of screening.
- A history of ophthalmic surgery within 6 months prior to the screening date.
- A diagnosis of type 1 diabetes mellitus.
- Pregnancy at the time of screening.
- Any condition that, in the opinion of the investigator, would make participation in the study infeasible or inappropriate.
Contact the study team to confirm eligibility.
Sponsors & Collaborators
- VUNO Inc.lead
Study Sites (1)
Inha University Hospital
Incheon, Gyeonggi-do, 22332, South Korea
MeSH Terms
Conditions
Condition Hierarchy (Ancestors)
Central Study Contacts
Study Design
- Study Type
- interventional
- Phase
- not applicable
- Allocation
- RANDOMIZED
- Masking
- NONE
- Purpose
- SCREENING
- Intervention Model
- PARALLEL
- Sponsor Type
- INDUSTRY
- Responsible Party
- SPONSOR
Study Record Dates
First Submitted
January 23, 2026
First Posted
January 30, 2026
Study Start
April 7, 2026
Primary Completion (Estimated)
August 31, 2027
Study Completion (Estimated)
August 31, 2027
Last Updated
April 13, 2026
Record last verified: 2026-04
Data Sharing
- IPD Sharing
- Will share
- Shared Documents
- STUDY PROTOCOL, SAP, ICF
The institutional dataset used in this study, along with de-identified results, is available upon reasonable request for purposes such as systematic review or meta-analysis, only with approval from the corresponding author and the official approval of local IRB.