Fine-tuning medical AI can improve diagnosis but also creates privacy risks

Qingyu Chen, PhD, and his team set out to study how artificial intelligence language models are adapted for medicine and found that what these models memorize can be both useful and risky. A model may retain valuable medical knowledge, but in a controlled study using real hospital records, the same fine-tuning—the added training that adapts a model to a specific task—that improved diagnostic performance also made it more likely to reproduce material it had seen during training, including sensitive patient information.

≈