Edalati Kiumars

Mohammadzadeh Vahid, Wu Sean, Besharati Sajad, Rafiee Mahshad, Banaei Yasamin, Martinyan Arthur et al.

A deep learning model significantly outperformed clinicians (AUC 0.839 vs 0.629-0.680) in predicting functional glaucoma progression. This AI offers superior, objective prognostication, enhancing personalized patient management, especially for fast progressors.

Mohammadzadeh Vahid, Wu Sean, Davis Tyler, Vepa Arvind, Morales Esteban, Besharati Sajad et al.

A deep learning model accurately predicted glaucoma visual field progression from serial optic disc photos, offering a promising tool for early clinical intervention.

Mohammadzadeh Vahid, Wu Sean, Besharati Sajad, Davis Tyler, Vepa Arvind, Morales Esteban et al.

A deep learning model using baseline RNFL thickness and serial optic disc photos accurately predicted visual field progression in glaucoma, showing promise as a clinical tool for identifying high-risk patients.

Mohammadzadeh Vahid, Vepa Arvind, Li Chuanlong, Wu Sean, Chew Leila, Mahmoudinezhad Golnoush et al.

Deep learning accurately predicts central visual field measures from macular OCT scans, offering a valuable tool to confirm and supplement central VF findings in glaucoma.

Mohammadzadeh Vahid, Cheng Melodyanne, Zadeh Sepideh Heydar, Edalati Kiumars, Yalzadeh Dariush, Caprioli Joseph et al.

New OCT macular shape measures effectively detect early glaucoma, showing high accuracy and potential as segmentation-independent biomarkers for clinical diagnosis.

Nouri-Mahdavi Kouros, Mohammadzadeh Vahid, Rabiolo Alessandro, Edalati Kiumars, Caprioli Joseph, Yousefi Siamak

This study found OCT structural changes, especially macular GCIPL, can predict visual field progression in moderate-advanced glaucoma with good accuracy, aiding earlier clinical intervention.