GlaukomAI: Clinical Validation of an AI System for Early Glaucoma Screening

NCT07668193 | Not Yet Recruiting

• 2 other identifiers: GLC 02-26101095654
• Study Type: interventional
• Target: 1,200
• Locations: 0 countries
• Sites: N/A

Brief Summary

Glaucoma is one of the leading causes of irreversible blindness worldwide. Early diagnosis is crucial to prevent vision loss, but current diagnostic pathways require multiple specialist visits and tests, leading to long waiting times and delayed diagnosis. This study aims to evaluate the accuracy of GlaukomAI, an artificial intelligence (AI)-based software that analyzes fundus photographs of the eye to detect glaucoma at an early stage. The study is conducted at IRCCS Fondazione G. B. Bietti (Rome, Italy) and is structured in two phases:

• Phase 1 enrolls 200 participants (100 with diagnosed glaucoma and 100 healthy controls) to assess how accurately GlaukomAI can distinguish between glaucoma and healthy eyes, compared to the judgment of a panel of three expert glaucoma specialists.
• Phase 2 enrolls 1,000 consecutive outpatients to evaluate whether GlaukomAI can correctly identify patients who need referral to a glaucoma specialist, and to compare its performance with that of non-specialist ophthalmologists. Participants undergo a single study visit including standard ophthalmic examinations (visual acuity, eye pressure measurement, visual field test, OCT, and fundus photography). No investigational drugs or invasive procedures are involved. The results of this study will provide evidence to support the integration of AI-based tools into routine glaucoma screening pathways, with the goal of reducing diagnostic delays and improving access to care.

Conditions

Glaucoma

Keywords

Glaucoma; Artificial Intelligence; Fundus Photography; Glaucoma Screening; Early Diagnosis; Optic Nerve; GlaukomAI

Outcome Measures

Primary Outcomes (1)

• Diagnostic Accuracy of GlaukomAI - Sensitivity and Specificity

  Sensitivity and specificity of GlaukomAI in the diagnosis of glaucoma, calculated against the gold standard defined by the consensus of a panel of three expert glaucoma specialists based on multimodal assessment (fundus photography, OCT, and visual field). Additional metrics include positive predictive value (PPV), negative predictive value (NPV), and area under the ROC curve (AUC) with 95% confidence intervals. The optimal diagnostic cut-off will be identified using the Youden index.

  At enrollment visit (single visit, or two consecutive visits within 1 week)

Secondary Outcomes (2)

• Referral Accuracy of GlaukomAI vs. Non-Specialist Ophthalmologists

  At enrollment visit

• Diagnostic Agreement - Cohen's Kappa

  At enrollment visit

Study Arms (2)

Glaucoma Patients

OTHER

Participants with diagnosed glaucoma (primary open-angle, primary angle-closure or secondary glaucoma) undergoing standard ophthalmological examination and AI-based image analysis.

Device: GlaukomAI (Sens-vue GlaukomAI)

Healthy Controls

OTHER

Participants without ocular pathology and with normal ophthalmological examination undergoing standard ophthalmological examination and AI-based image analysis.

Device: GlaukomAI (Sens-vue GlaukomAI)

Interventions

GlaukomAI (Sens-vue GlaukomAI) DEVICE

GlaukomAI is an AI-based diagnostic software (Sens-vue ApS) that analyzes standard fundus photographs to detect glaucomatous changes. The system uses deep learning with Convolutional Neural Network and Transformer architecture to evaluate key glaucoma biomarkers, including neuroretinal rim appearance in the inferior and superior sectors. It accepts standard fundus images acquired with conventional fundus cameras or portable devices and provides a diagnostic classification (Referable Glaucoma / Non-Referable Glaucoma) within 2-8 seconds per image. The system is not CE-marked. Fundus images are acquired using a widefield TrueColor Confocal fundus imaging system (iCare DRS Plus), pseudonymized, and uploaded to the GlaukomAI secure platform by an operator blinded to the clinical diagnosis.

Glaucoma Patients; Healthy Controls

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Age \>18 years
• Freely given informed consent obtained prior to study initiation
• The participant has the capacity to understand and the willingness to follow study instructions and is likely to complete all required visits and procedures
• Patients affected by any type of glaucoma (primary open-angle, primary angle-closure, secondary glaucoma) on pharmacological therapy
• Absence of ocular pathologies
• IOP \<21 mmHg
• Visual field and OCT within normal limits
• Optic disc of normal appearance on clinical evaluation

You may not qualify if:

• Presence of media opacities preventing the acquisition of adequate quality fundus imaging (e.g., advanced cataract, vitreous hemorrhage, severe corneal opacities)
• Retinal or optic nerve pathologies that could confound the diagnosis (e.g., non-glaucomatous optic neuropathies (ischemic, inflammatory, compressive), moderate-to-severe diabetic retinopathy, advanced macular degeneration, retinal vascular occlusions)
• Having undergone any ocular surgery in the past 3 months
• Inability to cooperate with perimetric examination

Sponsors & Collaborators

• Fondazione G.B. Bietti, IRCCS: lead

Related Publications (6)

• Li Z, He Y, Keel S, Meng W, Chang RT, He M. Efficacy of a Deep Learning System for Detecting Glaucomatous Optic Neuropathy Based on Color Fundus Photographs. Ophthalmology. 2018 Aug;125(8):1199-1206. doi: 10.1016/j.ophtha.2018.01.023. Epub 2018 Mar 2.

  PMID: 29506863 RESULT

• Lemij HG, Vente C, Sanchez CI, Vermeer KA. Characteristics of a Large, Labeled Data Set for the Training of Artificial Intelligence for Glaucoma Screening with Fundus Photographs. Ophthalmol Sci. 2023 Mar 17;3(3):100300. doi: 10.1016/j.xops.2023.100300. eCollection 2023 Sep.

  PMID: 37113471 RESULT

• Michelessi M, Quaranta L, Riva I, Martini E, Figus M, Frezzotti P, Agnifili L, Manni G, Miglior S, Posarelli C, Fazio S, Oddone F. Exploring the gap between diagnostic research outputs and clinical use of OCT for diagnosing glaucoma. Br J Ophthalmol. 2020 Aug;104(8):1114-1119. doi: 10.1136/bjophthalmol-2019-314607. Epub 2019 Nov 15.

  PMID: 31732524 RESULT

• Oddone F, Lucenteforte E, Michelessi M, Rizzo S, Donati S, Parravano M, Virgili G. Macular versus Retinal Nerve Fiber Layer Parameters for Diagnosing Manifest Glaucoma: A Systematic Review of Diagnostic Accuracy Studies. Ophthalmology. 2016 May;123(5):939-49. doi: 10.1016/j.ophtha.2015.12.041. Epub 2016 Feb 15.

  PMID: 26891880 RESULT

• Tham YC, Li X, Wong TY, Quigley HA, Aung T, Cheng CY. Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis. Ophthalmology. 2014 Nov;121(11):2081-90. doi: 10.1016/j.ophtha.2014.05.013. Epub 2014 Jun 26.

  PMID: 24974815 RESULT

• Quigley HA, Broman AT. The number of people with glaucoma worldwide in 2010 and 2020. Br J Ophthalmol. 2006 Mar;90(3):262-7. doi: 10.1136/bjo.2005.081224.

  PMID: 16488940 RESULT

MeSH Terms

Conditions

Glaucoma; Disease

Condition Hierarchy (Ancestors)

Ocular Hypertension; Eye Diseases; Pathologic Processes; Pathological Conditions, Signs and Symptoms

Study Officials

• Francesco Oddone, MD, PhD

  IRCCS Fondazione G. B. Bietti, Rome, Italy

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Francesco Oddone, MD, PhD

CONTACT

+39 06 84009442; francesco.oddone@fondazionebietti.it

Carmela Carnevale, MD

CONTACT

+39 06 84009442; carmela.carnevale@fondazionebietti.it

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: NON RANDOMIZED
• Masking: DOUBLE
• Who Masked: INVESTIGATOR, OUTCOMES ASSESSOR
• Masking Details: Multiple levels of masking are applied. The panel of three glaucoma experts defining the gold standard is blinded to the GlaukomAI output and to each other's assessments; final classification is determined by majority vote. The operator uploading fundus images to the GlaukomAI platform is blinded to the clinical diagnosis. In Phase 2, non-glaucoma-specialist ophthalmologists evaluate pseudonymized fundus images presented in randomized order, blinded to both the expert panel classification and the GlaukomAI output. Participants are not masked, as this is a diagnostic device study with no therapeutic intervention.
• Purpose: DIAGNOSTIC
• Intervention Model: SINGLE GROUP
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Model Details: The study is structured in two sequential phases. In Phase 1, a case-control design is used to assess diagnostic accuracy: 100 participants with diagnosed glaucoma and 100 healthy controls all undergo fundus photography analysis with GlaukomAI, compared against a gold standard defined by a panel of three expert glaucoma specialists. In Phase 2, 1,000 consecutive outpatients attending a tertiary ophthalmological centre undergo the same AI-based fundus image analysis; results are compared both to the expert panel gold standard and to the independent assessment of non-glaucoma-specialist ophthalmologists evaluating the same images.

Study Record Dates

• First Submitted: June 19, 2026
• First Posted: June 25, 2026
• Study Start: June 1, 2026
• Primary Completion (Estimated): November 1, 2027
• Study Completion (Estimated): May 1, 2028
• Last Updated: June 25, 2026

Record last verified: 2026-06

Data Sharing

• IPD Sharing: Will not share