Background: Large language models (LLMs) such as ChatGPT-4 and Google Gemini show potential for patient health education, but concerns about their accuracy require careful evaluation. This study evaluates the readability and accuracy of ChatGPT-4 and Google Gemini in answering questions about retinal detachment.
Methods: Comparative study analyzing responses from ChatGPT-4 and Google Gemini to 13 retinal detachment questions, categorized by difficulty levels (D1, D2, D3).
Br J Ophthalmol
August 2024
Purpose: To investigate changes to the vitreoretinal interface in uveitis with multimodal imaging including adaptive optics.
Methods: Four eyes (four patients) affected by fovea-attached (subtype 1A) or fovea-sparing epiretinal membranes (ERMs) on spectral-domain optical coherence tomography or visible internal limiting membrane (ILM) on infrared scanning laser ophthalmoscope (SLO) fundus imaging were recruited in this pilot study. The microstructure of the vitreoretinal interface was imaged using flood-illumination adaptive optics (FIAO), and the images were compared with the cross-sectional spectral-domain optical coherence tomography data.