DISCERN: Identifiable Disease Evidence for Generalizable Medical Multimodal Learning
arXiv:2610.23952v1 Announce Type: new Abstract: Clinical multimodal models can learn enrollment shortcuts shared across modalities and fail on new cohorts. We model these data through a latent structural causal model: disease state and background factors generate physiology through shared mechanism…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-10-20 04:00 · arXiv cs.LG
DISCERN: Identifiable Disease Evidence for Generalizable Medical Multimodal Learning