Decreasing the Medication Burden With iDose TR

John P. Berdahl, MD; Natalia Morales, MD; and Justin Schweitzer, OD, FAAO

Eyetube

John P. Berdahl, MD; Natalia Morales, MD; and Justin Schweitzer, OD, FAAO, review the case of a 78-year-old patient who previously underwent cataract surgery and stent implantation for severe glaucoma in his left eye. The patient returned to the office with a cataract and ocular hypertension in his right eye. He was already prescribed a topical prostaglandin analogue, had an IOP of 28 mm Hg OD, and showed no evidence of optic nerve damage. The panelists weigh insurance coverage, quality-of-life improvements, and other factors to consider when choosing an option for lowering IOP alongside cataract surgery.

Finding the Right Fit in Ophthalmology Residency

Bradford L. Tannen, MD, JD, MBA; Daniel B. Moore, MD; Jackson Laureano, MD; Gary Wörtz, MD; and Blake K. Williamson, MD, MPH

Eyetube

Blake K. Williamson, MD, MPH, and Gary Wörtz, MD, speak with Bradford Tannen, MD, JD, MBA; Daniel B. Moore, MD; and Jackson Laureano, MD, about ophthalmology residency training at the University of Kentucky. The group weighs what matters beyond a strong application, including authentic research interests, away rotations, and the interpersonal qualities that make someone a good resident. They also discuss early surgical experience, how operative volume builds confidence, and why finding the right fit may matter more than reputation alone.

AI Chatbots in the Retina Clinic

Large language models are not coming for your job. But they may redefine what your job looks like.

Fares Antaki, MDCM

Retina Today

KEY TAKEAWAYS Large language models have embedded ophthalmic knowledge that is improving rapidly with each model generation. Practical applications for retina specialists span two categories: workflow improvement (electronic health record documentation, report generation) and clinical assistance (triage, decision support). Vibe coding allows retina specialists without programming experience to build custom clinical tools using large language models. AI has been in ophthalmology for years, and most retina specialists are familiar with AI as it relates to image analysis. Algorithms that detect diabetic retinopathy (DR) from fundus photographs or segment fluid on OCT have received the most attention and, in the case of autonomous DR screening, regulatory clearance.1,2 However, a second wave of AI is reaching the clinic, and this version can read, write, and reason with text. These large language models (LLMs) power the chatbots that are quietly changing how physicians work.3 WHAT ARE LARGE LANGUAGE MODELS? LLMs are a class of AI designed to understand and generate human language. The technology behind products such as ChatGPT (OpenAI), Gemini (Google), and Claude (Anthropic) is conceptually straightforward. During training, a model is shown massive amounts of text and learns to predict the next word in a sequence.4 Consider the phrase attributed to Heraclitus: “The only constant in life is change.”5 A model in training would see “The only constant in life is…” and learn to predict “change.” This process is repeated billions of times across the entirety of the internet, books, and encyclopedias. The result is a system with a broad representation of human knowledge.