At Aga Khan University Hospital, I evaluated AI chatbot performance in healthcare and orthodontics, including comparative work involving ChatGPT and Microsoft Copilot.
I developed structured question sets and reviewed AI-generated responses for factual accuracy, completeness, clarity, and clinical appropriateness. I identified omissions, overstatements, and potentially inaccurate information.
I compared outputs using structured scoring and applied evidence-based reasoning to assess whether healthcare information was scientifically supportable. I also prepared scientific manuscripts and revised text in response to peer review.
My research has included assessments of ChatGPT-4 and Copilot on 3D-printed orthodontic appliances, with findings published in International Orthodontics in 2025. I use Microsoft Excel, IBM SPSS Statistics, and R to organize research data and conduct statistical analysis.
