Yousefi Siamak

Nabavi Amin, Haddock Luis J, Mahmoudi Alireza, Salabati Mirataollah, Yousefi Siamak

This review found active uveitis causes reversible retinal nerve fiber layer thickening, suggesting it's a promising biomarker for monitoring uveitis activity and treatment response, especially in posterior uveitis.

Raja Hina, Huang Xiaoqin, Delsoz Mohammad, Madadi Yeganeh, Poursoroush Asma, Munawar Asim et al.

ChatGPT 4.0 showed promising accuracy (87%) in diagnosing glaucoma from OHTS data, outperforming ChatGPT 3.5. This suggests LLMs could aid in analyzing ocular hypertension data to explore disease status.

Huang Xiaoqin, Poursoroush Asma, Sun Jian, Boland Michael V, Johnson Chris A, Yousefi Siamak

Machine learning identified four OHT subtypes, revealing fast progressors linked to higher baseline IOP, age, and systemic comorbidities, guiding personalized glaucoma treatment to slow vision loss.

Huang Xiaoqin, Raja Hina, Madadi Yeganeh, Delsoz Mohammad, Poursoroush Asma, Kahook Malik Y et al.

Huang Xiaoqin, Raja Hina, Madadi Yeganeh, Delsoz Mohammad, Poursoroush Asma, Kahook Malik Y et al.

ChatGPT4.0 reasonably predicted glaucoma onset from ocular hypertension using OHTS data, showing promise for large language models in augmenting glaucoma research and clinical care.

Yousefi Siamak, Huang Xiaoqin, Poursoroush Asma, Majoor Julek, Lemij Hans, Vermeer Koen et al.

An AI system objectively staged glaucoma severity using RNFL thickness, finding optimal thresholds for normal, early, moderate, and advanced loss, offering a consistent clinical tool.

Hussain Zain S, Andoh Joana E, Loya Asad, Yousefi Siamak, Boland Michael V

COVID-19 significantly reduced glaucoma and cataract surgeries, with MIGS most affected. However, rural trabeculectomies increased, highlighting varied impacts and potential care shifts for future planning.

Sabouri Samaneh, Haem Elham, Masoumpour Masoumeh, Vermeer Koenraad A, Lemij Hans G, Yousefi Siamak et al.

Simulating glaucoma progression, researchers found that initially frequent (e.g., 4-monthly) visual fields, followed by longer intervals, effectively detected progression. This optimizes monitoring strategies.

Chen Dinah, Ran Ran An, Fang Tan Ting, Ramachandran Rithu, Li Fei, Cheung Carol Y et al.

AI for glaucoma mostly uses single imaging modalities for diagnosis/screening or visual fields for progression. No AI for treatment response or prospective testing exists, highlighting the need for more comprehensive, clinically usable tools.

Yousefi Siamak, Pasquale Louis R, Boland Michael V, Johnson Chris A

Machine learning identified visual field loss patterns, finding one predicted rapid glaucoma progression, offering an objective tool for early detection and risk assessment.

Sabouri Samaneh, Pourahmad Saeedeh, Vermeer Koenraad A, Lemij Hans G, Yousefi Siamak

This study found nonlinear models (exponential/sigmoid) better track glaucoma visual field loss than linear models, especially sigmoid for early loss, and region-wise analysis improved assessment.

Huang Xiaoqin, Saki Fatemeh, Wang Mengyu, Elze Tobias, Boland Michael V, Pasquale Louis R et al.

AI developed a glaucoma staging system using visual fields, finding four severity levels based on specific MD thresholds. This objective, easy-to-use system aids clinical practice and research.

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.

Wang Mengyu, Shen Lucy Q, Pasquale Louis R, Wang Hui, Li Dian, Choi Eun Young et al.

AI identified 16 distinct RNFLT patterns in glaucoma. These patterns better predicted visual field loss than traditional methods, potentially improving clinical assessment of RNFLT damage.

Yousefi Siamak, Elze Tobias, Pasquale Louis R, Saeedi Osamah, Wang Mengyu, Shen Lucy Q et al.

An AI dashboard effectively mapped diverse glaucoma visual field loss patterns, showing 77% sensitivity for progression. This offers clinicians a user-friendly tool to monitor disease severity and progression.

Yousefi Siamak

Yousefi Siamak, Sakai Hiroshi, Murata Hiroshi, Fujino Yuri, Matsuura Masato, Garway-Heath David et al.

This study found POAG eyes lose superior visual field faster than inferior, unlike PACG eyes, suggesting different progression patterns for these glaucoma types.

Yousefi Siamak, Kiwaki Taichi, Zheng Yuhui, Sugiura Hiroki, Asaoka Ryo, Murata Hiroshi et al.

This study found a machine learning index detects glaucoma progression in visual fields earlier than current methods, potentially allowing for faster clinical intervention and improved patient outcomes.

Yousefi Siamak, Sakai Hiroshi, Murata Hiroshi, Fujino Yuri, Garway-Heath David, Weinreb Robert et al.

This study found primary open-angle glaucoma causes more pronounced superior visual field loss than primary angle-closure glaucoma, which can aid in differentiating these conditions clinically.

Yarmohammadi Adeleh, Zangwill Linda M, Diniz-Filho Alberto, Suh Min Hee, Yousefi Siamak, Saunders Luke J et al.

OCT-A vessel density strongly correlated with glaucoma visual field loss, even independent of nerve structure. This suggests OCT-A is promising for glaucoma management, emphasizing vascular factors in the disease.

Suh Min Hee, Zangwill Linda M, Manalastas Patricia Isabel C, Belghith Akram, Yarmohammadi Adeleh, Medeiros Felipe A et al.

Glaucoma patients with focal lamina cribrosa defects showed significantly lower OCT-A vessel density, even with similar disease severity, suggesting these defects impact ocular blood flow.

Yarmohammadi Adeleh, Zangwill Linda M, Diniz-Filho Alberto, Suh Min Hee, Manalastas Patricia Isabel, Fatehee Naeem et al.

OCT-A vessel density effectively differentiated glaucoma from healthy eyes, showing similar diagnostic accuracy to RNFL thickness, suggesting its utility in assessing glaucoma-related tissue damage.