Using LLMs to Help Prevent Pediatric Data Disclosures

Unintentional disclosures of adolescents’ protected health information are major privacy and security concerns that providers must navigate. Natalie Pageler, MD, chief health informatics officer and division chief of pediatric clinical informatics at Stanford Medicine Children’s Health, discusses how the use of large language models (LLMs) could help prevent these disclosures by identifying confidential content in clinical notes.