Clinically informed semi-supervised learning improves disease annotation and equity from electronic health records: a glaucoma case study.

These limitations constrain the accuracy of datasets used to investigate disease pathogenesis and progression and to develop robust artificial intelligence (artificial intelligence) systems.

To address this challenge, we introduce Ci-SSGAN (Clinically Informed Semi-Supervised Generative Adversarial Network), a novel framework that leverages large-scale unlabeled clinical text to reannotate patient conditions with improved accuracy and equity.