Glaucoma Algorithm Validation Study in African Population - the MAGIC Study

Centro Hospitalar Universitário Lisboa Norte

Status: Not yet enrolling

Conditions: Glaucoma; Diabetic Retinopathy

Treatments: Diagnostic Test: Fundus Picture AI testing

Study type: Interventional

Funder types: Other; Industry

Identifiers

NCT06552247

Collaboration Mozambique 2

Details and patient eligibility

About

Artificial Intelligence (AI) algorithms require validation in a variety of populations to ensure widespread clinical applicability. In Ophthalmology, AI algorithms are reaching maturity in diagnosis such as diabetic retinopathy and glaucoma. Higher-at-risk subjects of African descent are nevertheless usually under-represented in training datasets and therefore unclear about representativity.

A small scale validation study in consecutive patients in a large Eyesore unit in Mozambique will be performed to determine the diagnostic ability of these AI softwares in this population

Full description

Artificial Intelligence (AI) algorithm's are the next frontier in medical management, usually meant to improve diagnostic capabilities and to optimize the existing resources. They are particularly relevant in settings where there is a lack of specialised Human Resources such as physicians.

Ensuring these algorithms can be used in a wide population is therefore crucial to clinical implementation. Validation studies in specific segments of populations are needed to ensure all patients are represented and the results are therefore reliable. Higher-at-risk subjects of African descent are nevertheless usually under-represented in training datasets and therefore unclear about representativity.

A pilot study for validation of an AI algorithm for Glaucoma and Diabetic Retinopathy will be done for the MONA G-RISK® and diabetic retinopathy. Consecutive patients from a large Eye Unit in Mozambique's capital will be screened using these AI algorithms and validated using clinical standard as ground truth.

Enrollment: 100 estimated patients

Sex: All

Ages: 18+ years old

Volunteers: Accepts Healthy Volunteers

Inclusion criteria

• subjects age above 18 years old presenting at the Eye Unit
• willingness to sign an informed consent for the screening process

Exclusion criteria

• none
• Poor quality in screening image will be included in the intention to treat analysis, but excluded from the diagnostic comparator outcome.
• Patients with a known glaucoma diagnosis will not be excluded from the screening

Trial design

Primary purpose: Diagnostic

Allocation: N/A

Interventional model: Single Group Assignment

Masking: None (Open label)

---

100 participants in 1 patient group

AI-based fundus picture screening

Experimental group

Description:

Volunteers will performed a full study visit as part of their regular Ophthalmology assessment. This will include a fundus picture, an Optic-disc entered OCT, a Visual Field exam and a clinical examination by a clinical expert. Fundus picture will be assessed by an AI algorithm (G-Risk) and labelled with referral vs non-referrable and compared with the clinical gold standard

Treatment:

Diagnostic Test: Fundus Picture AI testing