Trainee Rounds: Austin Barr and David Mikhail
DATE: July 16, 2025 (Wed.)
TIME: 12pm to 1pm ET
PRESENTERS: Austin Barr and David Mikhail
Learn more about the presenters
Austin Barr
Title of Talk
Zero-shot generation of synthetic neurosurgical data
Description
Clinical data is fundamental to advance neurosurgical research, but access is often constrained by data availability, small sample sizes, privacy regulations, and resource-intensive preprocessing and de-identification procedures. Synthetic data offers a potential solution to challenges associated with accessing and using real patient data. We present a novel zero-shot approach to synthetic data generation using the large language model (LLM) GPT-4o, which does not require access to real-world data, pre-training, or fine-tuning.
David Mikhail
Title of Talk
Multimodal Performance of GPT-4 in Complex Ophthalmology Cases
Description
The integration of multimodal capabilities into GPT-4 represents a trans-formative leap for artificial intelligence in ophthalmology, yet its utility in scenarios requiring advanced reasoning remains underexplored. This study evaluates GPT-4’s multimodal performance on open-ended diagnostic and next-step reasoning tasks in complex ophthalmology cases, comparing it against human expertise.
Learn more about the presenters
