Multimodal Survival Analysis with Locally Deployable Large Language Models

We study multimodal survival analysis integrating clinical text, tabular covariates, and genomic profiles using locally deployable LLMs. As many institutions face tight computational and privacy constraints, this setting motivates lightweight, on‑premises models. Our approach jointly estimates calibrated survival probabilities and generates concise, evidence‑grounded prognosis text via teacher–student distillation and principled multimodal fusion. On a TCGA cohort, it outperforms baselines, avoids reliance on cloud services and associated privacy concerns, and reduces the risk of hallucinated or miscalibrated estimates from base LLMs.