MedLatentDx: Latent Multi-Agent Communication for Cross-Hospital Rare-Disease Diagnosis
For hospitals needing to collaborate on rare-disease diagnosis under privacy constraints, MedLatentDx offers a method to share diagnostic evidence without exposing identifiable clinical text.
MedLatentDx proposes a latent multi-agent communication framework for cross-hospital rare-disease diagnosis that preserves privacy by exchanging compact latent KV blocks instead of raw clinical text. On the CrossRare-Bench benchmark, it improves diagnostic performance while reducing reconstructable clinical content compared to raw-latent baselines.
Rare diseases affect over $300$ million patients across more than $7{,}000$ conditions, yet no single hospital encounters enough cases of any one condition for reliable diagnosis. Cross-hospital collaboration could help by allowing a diagnosing institution to use distributed, case-specific diagnostic evidence, but privacy regulations restrict the transmission of identifiable clinical text across institutional boundaries. This setting raises two challenges: existing medical agent systems often rely on textual evidence exchange, while raw latent states such as hidden states and KV caches may still reveal prompt-derived clinical content. We introduce MedLatentDx, a latent multi-agent communication framework in which hospital agents keep private clinical records and retrieved cases local, and send compact latent KV blocks to a host agent for rare-disease diagnosis. MedLatentDx supports two deployment settings: same-backbone hospital agents use latent KV distillation, while hospitals with different LLM backbones use cross-family latent alignment. On CrossRare-Bench, a self-built large-scale rare-disease benchmark with hospital-level partitions, MedLatentDx improves cross-hospital diagnostic performance while reducing reconstructable clinical content relative to raw-latent communication baselines.