Medical data used to train AI is often “anonymized” to protect private health information, a practice crucial for HIPAA compliance. To address the limitations of traditional anonymization methods that may compromise accuracy and realism, Johns Hopkins researchers have developed DREAM, an AI system capable of generating synthetic patient portal messages that can be used to train large language models. DREAM is publicly available on GitHub.

Their approach, described in the Journal of Biomedical Informatics, overcomes a critical challenge in medical AI: maintaining the privacy of patient records while preserving the accuracy of patient data.

“High-quality synthetic medical data can significantly advance health research and improve patient care,” said the study’s senior author Casey Taylor, an associate professor of biomedical engineering and medicine at Johns Hopkins University. “By using large language models to create realistic datasets, we can develop potentially useful and meaningful AI models without the patient privacy concerns that come from using real data.”

Taylor says the study is one of the first to utilize large language models (LLMs) to generate realistic patient portal communications. Collaborators on the study include Ayah Zirikly, an assistant research scientist in the Whiting School of Engineering’s Center for Language and Speech Processing, and Natalie Wang, a PhD student in computer science.

Read the full story here.