Caroline A. Fisher

The Impact of Race, Ethnicity, and Sex on Fairness in Artificial Intelligence for Glaucoma Prediction Models.

AI models predicting glaucoma surgery progression show bias across sex, race, and ethnicity. Fairness and performance vary with sensitive attribute inclusion, highlighting the need for rigorous, population-specific fairness evaluations before deployment.

Using Electronic Health Record Data to Determine the Safety of Aqueous Humor Liquid Biopsies for Molecular Analyses.

Aqueous humor liquid biopsies during intraocular surgery are safe, with a 0.07% complication rate. This supports their use for molecular analyses, aided by efficient free-text EHR searches.