Meziane Silhadi

Meziane Silhadi

Auto-generated profile, based on publicly available information

Meziane Silhadi

Faculty of Medicine, University of Montreal, Montreal, Quebec, Canada

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 February 2025 in Canadian Journal of Ophthalmology
Verified
Journal Article
Open access
MSMeziane Silhadi
Meziane Silhadi
WNWissam Bassam Nassrallah
Wissam Bassam Nassrallah
DMDavid Mikhail
David Mikhail
DMDaniel Milad
Daniel Milad
MHMona Harissi-Dagher
Mona Harissi-Dagher
To evaluate the performance of large language models (LLMs), specifically Microsoft Copilot, GPT-4 (GPT-4o and GPT-4o mini), and Google Gemini (Gemini and Gemini Advanced), in answering ophthalmological questions and assessing the impact of prompting techniques on their accuracy. Prospective qualitative study. Microsoft Copilot, GPT-4 (GPT-4o and GPT-4o mini), and Google Gemini (Gemini and Gemini Advanced). A total of 300 ophthalmological questions from StatPearls were tested, covering a range of subspecialties and image-based tasks. Each question was evaluated using 2 prompting techniques: zero-shot forced prompting (prompt 1) and combined role-based and zero-shot plan-and-solve+ prompting (prompt 2). With zero-shot forced prompting, GPT-4o demonstrated significantly superior overall performance, correctly answering 72.3% of questions and outperforming all other models, including Copilot (53.7%), GPT-4o mini (62.0%), Gemini (54.3%), and Gemini Advanced (62.0%) (p < 0.0001). Both Copilot and GPT-4o showed notable improvements with Prompt 2 over Prompt 1, elevating Copilot's accuracy from the lowest (53.7%) to the second highest (72.3%) among the evaluated LLMs. While newer iterations of LLMs, such as GPT-4o and Gemini Advanced, outperformed their less advanced counterparts (GPT-4o mini and Gemini), this study emphasizes the need for caution in clinical applications of these models. The choice of prompting techniques significantly influences performance, highlighting the necessity for further research to refine LLMs capabilities, particularly in visual data interpretation, to ensure their safe integration into medical practice.

15 November 2025 in Canadian Journal of Ophthalmology
Verified
Journal Article
Closed access
ABAllison Bernstein
Allison Bernstein
MSMeziane Silhadi
Meziane Silhadi
PHPatrick Hamel
Patrick Hamel
NFNicole Fallaha
Nicole Fallaha
MRMarie-Claude Robert
Marie-Claude Robert

20 April 2026 in American Journal of Ophthalmology Case Reports
Verified
Journal Article
Open access
MSMeziane Silhadi
Meziane Silhadi
BNBibi Nuzha Noorah
Bibi Nuzha Noorah
David RobergeDavid Roberge
David Roberge
AOAlexandre N. Odashiro
Alexandre N. Odashiro
EMErika Massicotte
Erika Massicotte
MRMarie-Claude Robert
Marie-Claude Robert
To report a case of progressive conjunctival stromal tumor (COST) resistant to surgical debulking and radiotherapy (RT), resulting in orbital exenteration. A 43-year-old male presented with a hypervascularized nasal bulbar conjunctival lesion infiltrating the rectus muscles of the left eye. Despite three surgical debulking procedures, the tumor recurred and progressed, affecting the superior, nasal, and inferior bulbar conjunctiva and the lower eyelid. RT was administered (30 Gy in 10 fractions) with minimal tumor response. The tumor continued to expand, requiring orbital exenteration to prevent intracranial extension. Histopathology confirmed COST, and genomic testing revealed no actionable variants. The patient's postoperative course has been stable with no evidence of recurrence in the last 32 months. This case highlights the limitations of RT in managing progressive COST. It underscores the importance of considering more aggressive surgical management in progressive cases. Further studies are needed to establish optimal treatment strategies for COST.