Artificial-Intelligence-based Early Detection of Diabetic Retinopathy (FUNDUS AI)

Künstliche Intelligenz (KI)-gestützte Früherkennung Der Diabetischen Retinopathie (FUNDUS-KI)

Status

Enrolling by invitation

Phases

Unknown

Study type

Observational

Source

ClinicalTrials.gov

Registry ID

NCT07378891

Acronym

FUNDUS AI

Enrollment

100

Registered

2026-01-30

Start date

2025-12-01

Completion date

2028-12-15

Last updated

2026-02-10

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Diabetes (DM), Prediabetes

Keywords

Diabetic retinopathy, Prediabetes, Diabetes, EyeArt

Brief summary

Examination of individuals with prediabetes and established diabetes for early signs of diabetic retinopathy.

Detailed description

Fundus images are acquired and analyzed using an AI algorithm. The fundus images are captured using two devices: a stationary fundus camera (CenterVue DRSplus) and the Optomed Aurora IQ handheld fundus camera. Retinal images are examined using AI-based image analysis.

Interventions

None listed

Study design

Observational model

COHORT

Time perspective

CROSS_SECTIONAL

Eligibility

Sex/Gender

ALL

Age

18 Years to 80 Years

Healthy volunteers

Inclusion criteria

* Voluntary adults * Aged between 18 and 80 years * Understanding of the study explanations and instructions * Prediabetes (defined by elevated fasting glucose 100-125 mg/dL and/or 2-hour glucose in the oral glucose tolerance test of 140-199 mg/dL and/or HbA1c of 5.7-6.4%) * manifest diabetes (all types of diabetes according to Ahlqvist)

Exclusion criteria

* participants unable to give consent * Those who do not agree to be informed about incidentally detected pathological findings * Uncontrolled arterial hypertension (Stage III) despite multiple antihypertensive medications * Eye diseases that impair the interpretability of the fundus examination

Design outcomes

Primary

Measure	Time frame	Description
Assessment of retinal changes	Day 1	Assessment of retinal changes in individuals with prediabetes and diabetes, quantified using an AI algorithm.

Secondary

Measure	Time frame	Description
Image quality and comparison of the fundus cameras	Day 1	The automatically assessed image quality and the comparison of stationary and mobile fundus cameras
Influence of clinical parameters on retinal vascular changes	Day 1	Influence of clinical parameters such as anthropometric measurements (WHR, blood pressure, BMI) and laboratory parameters of glucose and lipid metabolism on retinal vascular changes
Association of medications with the ocular fundus	Day 1	Association of antidiabetic and lipid-lowering medications with the ocular fundus

Countries

Germany

Outcome results