Privacy aware agent system improves medical chat accuracy and safety
PrivMeSA: Privacy-Aware Self-Evolving Multi-Agent System for Medicine via Local-Remote LLM Collaboration
Artificial Intelligence
Summary
Accessing powerful medical AI tools remotely risks revealing sensitive patient information. The authors designed a system where a local agent learns to share information carefully to balance getting accurate advice and protecting privacy. This system remembers lessons from past cases to improve future decisions without needing to ask remote models again. Tests on emergency room data showed it gave more accurate advice while greatly reducing patient privacy risks.
What this means in practice
- •For hospital data teams: Enable safe medical AI consultations that minimize patient data exposure while retaining access to powerful remote models.
- •For healthcare software developers: Build privacy-focused AI assistants that learn from past cases to reduce repeated external data queries and protect sensitive information.
Authors
Dannong Wang, Yuran Zhang, Bian Sun, Alex Stinard, Yuzhang Shang, Song Wang, Yu Tian
Abstract
Clinical large language model (LLM) agents deployed locally can consult more capable remote models, but doing so risks exposing patient information. Privacy-conscious delegation places disclosure decisions with a local agent, yet removing explicit identifiers is insufficient: quasi-identifiers can accumulate across multi-turn consultations and repeated patient visits to enable re-identification. We introduce PrivMeSA, a privacy-aware self-evolving multi-agent system that learns to control disclosure and retains remote expertise for local reuse. A local agent manages each encounter and consults remote specialists that may request additional information. Reinforcement learning balances task accuracy against direct disclosure and registry-based re-identification risk, with privacy evaluated over the complete outbound transcript of each encounter. A local lesson memory distills completed consultations into generalized clinical guidance and retrieves relevant lessons before transmission, allowing subsequent cases to reuse expertise without another remote exchange. Memory grows without additional outcome labels or parameter updates. On an emergency-department benchmark built from MIMIC-IV-ED records, PrivMeSA improves mean task accuracy over delegation by up to 15.8 percentage points. In the same setting, PrivMeSA reduces the disclosure of personal details from 98.0% to 0.2% of cases and the share of cases in which the patient can be narrowed to ten or fewer registry patients from 74% to 0%.