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.
Aperçu de l'étude
Statut
Statut
Les conditions
Les conditions
Intervention / Traitement
Intervention / Traitement
Description détaillée
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.
Type d'étude
Type d'étude
Inscription (Estimé)
Inscription
Phase
Phase
- N'est pas applicable
Contacts et emplacements
Coordonnées de l'étude
Coordonnées de l'étude
- Nom: Benjamin Y. Xu, MD, PhD
- Numéro de téléphone: 323-442-6425
- E-mail: benjamix@usc.edu
Critères de participation
Critère d'éligibilité
Critère d'éligibilité
Âges éligibles pour étudier
Accepte les volontaires sains
Sexes éligibles pour l'étude
La description
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
Plan d'étude
Comment l'étude est-elle conçue ?
Détails de conception
- Objectif principal: Diagnostique
- Répartition: Randomisé
- Modèle interventionnel: Affectation parallèle
- Masquage: Aucun (étiquette ouverte)
Nombre de bras
Armes et Interventions
Groupe de participants / BrasGroupe de participants / Bras |
Intervention / TraitementIntervention / Traitement |
|---|---|
|
Expérimental: 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. |
|
Comparateur actif: 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. |
Que mesure l'étude ?
Principaux critères de jugement
Principaux critères de jugement
Mesure des résultats |
Description de la mesure |
Délai |
|---|---|---|
|
Time to in-office diagnosis of glaucoma
Délai: 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
|
Mesures de résultats secondaires
Mesures de résultats secondaires
Mesure des résultats |
Description de la mesure |
Délai |
|---|---|---|
|
Visual field mean deviation (MD)
Délai: 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)
Délai: 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
Délai: 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
|
Collaborateurs et enquêteurs
Parrainer
Parrainer
Collaborateurs
Collaborateurs
Dates d'enregistrement des études
Dates principales de l'étude
Début de l'étude (Estimé)
Début de l'étude
Achèvement primaire (Estimé)
Achèvement primaire
Achèvement de l'étude (Estimé)
Achèvement de l'étude
Dates d'inscription aux études
Première soumission
Première soumission
Première soumission répondant aux critères de contrôle qualité
Première soumission répondant aux critères de contrôle qualité
Première publication (Réel)
Première publication
Mises à jour des dossiers d'étude
Dernière mise à jour publiée (Réel)
Dernière mise à jour publiée
Dernière mise à jour soumise répondant aux critères de contrôle qualité
Dernière mise à jour soumise répondant aux critères de contrôle qualité
Dernière vérification
Dernière vérification
Plus d'information
Termes liés à cette étude
Mots clés
Termes MeSH pertinents supplémentaires
Autres numéros d'identification d'étude
Autres numéros d'identification d'étude
- APP-26-03722
Plan pour les données individuelles des participants (IPD)
Prévoyez-vous de partager les données individuelles des participants (DPI) ?
Description du régime IPD
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.
Informations sur les médicaments et les dispositifs, documents d'étude
Étudie un produit pharmaceutique réglementé par la FDA américaine
Étudie un produit d'appareil réglementé par la FDA américaine
Ces informations ont été extraites directement du site Web clinicaltrials.gov sans aucune modification. Si vous avez des demandes de modification, de suppression ou de mise à jour des détails de votre étude, veuillez contacter register@clinicaltrials.gov. Dès qu'un changement est mis en œuvre sur clinicaltrials.gov, il sera également mis à jour automatiquement sur notre site Web .