Automated Review of Patient Records: Privacy-Preserving Large Language Models for Identifying Incident Nonarteritic Anterior Ischemic Optic Neuropathy at Scale.

Privacy-preserving agentic large language models approaches can achieve high positive predictive value for acute nonarteritic anterior ischemic optic neuropathy case identification using unstructured ophthalmology longitudinal electronic health records.

These results exceed the performance of using structured International Classification of Diseases codes to identify cases, offering a scalable, efficient method for case identification in retrospective research while maintaining patient confidentiality and local data control.