AI-Assisted vs Conventional Teleglaucoma Referral (GATES)
Artificial Intelligence-Assisted Teleophthalmology for Glaucoma Screening: A Randomized Controlled Trial
This randomized controlled trial will compare an artificial intelligence (AI)-assisted teleglaucoma referral pathway with conventional referral among adults identified with referable glaucoma through the Los Angeles County Department of Health Services (LAC DHS) Teleretinal Screening Program. The primary objective is to determine whether AI-assisted referral reduces time to in-office diagnosis of manifest glaucoma. Secondary outcomes include glaucoma severity, visual function, need for glaucoma surgery, patient-reported quality of life and satisfaction, health system resource utilization, and cost-effectiveness.
Studie Overzicht
Toestand
Toestand
Conditie
Conditie
Interventie / Behandeling
Interventie / Behandeling
Gedetailleerde beschrijving
Participants identified with referable glaucoma during routine teleretinal screening will be randomized 1:1 to an AI-assisted referral pathway or a conventional referral pathway.
In the AI-assisted arm, fundus photographs will be analyzed using validated deep learning models integrated within the Eye-AI platform. AI outputs, together with intraocular pressure and other clinical information, will be used to stratify referral urgency. AI-generated recommendations will undergo review by glaucoma specialists before referral.
In the conventional referral arm, fundus images will undergo manual review by LAC DHS optometrists, with referral and prioritization performed according to current clinical practice.
Participants in both groups will undergo comprehensive in-office glaucoma evaluation following referral and will be followed for up to 36 months. The primary outcome is time from screening to in-office diagnosis of manifest glaucoma. Secondary outcomes will evaluate disease severity and visual function, need for glaucoma surgery, patient-reported quality of life and satisfaction, health system resource utilization, and cost-effectiveness.
Studietype
Studietype
Inschrijving (Geschat)
Inschrijving
Fase
Fase
- Niet toepasbaar
Contacten en locaties
Studiecontact
Studiecontact
- Naam: Benjamin Y. Xu, MD, PhD
- Telefoonnummer: 323-442-6425
- E-mail: benjamix@usc.edu
Deelname Criteria
Geschiktheidscriteria
Geschiktheidscriteria
Leeftijden die in aanmerking komen voor studie
Accepteert gezonde vrijwilligers
Geslachten die in aanmerking komen voor studie
Beschrijving
Inclusion Criteria:
- Provision of signed and dated informed consent
- Age ≥18 years
- Receiving routine teleretinal screening through the Los Angeles County Department of Health Services (LAC DHS) Teleretinal Screening Program
- Positive prediction for referable glaucoma by the validated AI algorithm at the time of screening
- No prior ophthalmology or optometry follow-up within the past year
- Willingness and ability to comply with study procedures and follow-up
Exclusion Criteria:
- Inability to tolerate fundus photography or ungradable fundus images
- Acute vision loss or major ocular complaints requiring immediate in-person evaluation
- Prior glaucoma diagnosis or treatment within the past year
Studie plan
Hoe is de studie opgezet?
Ontwerpdetails
- Primair doel: Diagnostisch
- Toewijzing: Gerandomiseerd
- Interventioneel model: Parallelle opdracht
- Masker: Geen (open label)
Aantal wapens
Wapens en interventies
Deelnemersgroep / ArmDeelnemersgroep / Arm |
Interventie / BehandelingInterventie / Behandeling |
|---|---|
|
Experimenteel: AI-Assisted Teleglaucoma Referral
Participants will undergo AI-assisted referral using validated deep learning models integrated within the Eye-AI platform. AI outputs, together with intraocular pressure and other clinical information, will be used to stratify referral urgency. AI-generated recommendations will be reviewed by glaucoma specialists before referral. |
Fundus photographs acquired during routine teleretinal screening will be analyzed using validated deep learning models integrated within the Eye-AI platform. For participants identified with referable glaucoma, AI outputs will be combined with intraocular pressure and other clinical information to stratify referral urgency. All AI-generated recommendations will undergo review by a glaucoma specialist before referral. |
|
Actieve vergelijker: Conventional Teleglaucoma Referral
Participants will undergo conventional teleglaucoma referral based on manual grading of fundus photographs by LAC DHS optometrists, with referral and prioritization performed according to current clinical practice. |
Fundus photographs will undergo conventional manual grading by LAC DHS optometrists, with referral and prioritization performed according to current clinical practice. |
Wat meet het onderzoek?
Primaire uitkomstmaten
Primaire uitkomstmaten
Uitkomstmaat |
Maatregel Beschrijving |
Tijdsspanne |
|---|---|---|
|
Time to in-office diagnosis of glaucoma
Tijdsspanne: From screening through 36 months
|
Number of days from the initial teleophthalmology screening to the first in-office glaucoma evaluation at which manifest glaucoma is diagnosed. |
From screening through 36 months
|
Secundaire uitkomstmaten
Secundaire uitkomstmaten
Uitkomstmaat |
Maatregel Beschrijving |
Tijdsspanne |
|---|---|---|
|
Visual field mean deviation (MD)
Tijdsspanne: Baseline and 36 months
|
Glaucoma disease severity assessed using visual field mean deviation (MD), measured in decibels (dB), at baseline and 36 months. |
Baseline and 36 months
|
|
Visual field index (VFI)
Tijdsspanne: Baseline and 36 months
|
Glaucoma disease severity assessed using visual field index (VFI), expressed as a percentage (%), at baseline and 36 months. |
Baseline and 36 months
|
|
Mean retinal nerve fiber layer (RNFL) thickness
Tijdsspanne: Time Frame: Baseline and 36 months
|
Glaucoma disease severity assessed using mean retinal nerve fiber layer (RNFL) thickness measured by optical coherence tomography (OCT), expressed in micrometers (µm), at baseline and 36 months. |
Time Frame: Baseline and 36 months
|
Medewerkers en onderzoekers
Sponsor
Sponsor
Medewerkers
Medewerkers
Studie record data
Bestudeer belangrijke data
Studie start (Geschat)
Studie start
Primaire voltooiing (Geschat)
Primaire voltooiing
Studie voltooiing (Geschat)
Studie voltooiing
Studieregistratiedata
Eerst ingediend
Eerst ingediend
Eerst ingediend dat voldeed aan de QC-criteria
Eerst ingediend dat voldeed aan de QC-criteria
Eerst geplaatst (Werkelijk)
Eerst geplaatst
Updates van studierecords
Laatste update geplaatst (Werkelijk)
Laatste update geplaatst
Laatste update ingediend die voldeed aan QC-criteria
Laatste update ingediend die voldeed aan QC-criteria
Laatst geverifieerd
Laatst geverifieerd
Meer informatie
Termen gerelateerd aan deze studie
Trefwoorden
Aanvullende relevante MeSH-voorwaarden
Andere studie-ID-nummers
Andere studie-ID-nummers
- APP-26-03722
Plan Individuele Deelnemersgegevens (IPD)
Bent u van plan om gegevens van individuele deelnemers (IPD) te delen?
Beschrijving IPD-plan
Individual participant data will not be shared because patient-level health data from the Los Angeles County Department of Health Services (LAC DHS) are subject to HIPAA and LAC DHS data-sharing restrictions. Aggregate-level study results and derived analytic outputs will be shared in accordance with NIH policy and the approved Data Management and Sharing Plan.
Informatie over medicijnen en apparaten, studiedocumenten
Bestudeert een door de Amerikaanse FDA gereguleerd geneesmiddel
Bestudeert een door de Amerikaanse FDA gereguleerd apparaatproduct
Deze informatie is zonder wijzigingen rechtstreeks van de website clinicaltrials.gov gehaald. Als u verzoeken heeft om uw onderzoeksgegevens te wijzigen, te verwijderen of bij te werken, neem dan contact op met register@clinicaltrials.gov. Zodra er een wijziging wordt doorgevoerd op clinicaltrials.gov, wordt deze ook automatisch bijgewerkt op onze website .