Block Diffusion for Longitudinal EHR: Accuracy, Efficiency, and Representation Trade-offs

arXiv:2610.29533v1 Announce Type: new Abstract: Autoregressive (AR) models have proved effective for zero-shot prediction from longitudinal electronic health records, but impose strictly sequential generation on trajectories containing temporally clustered and interdependent clinical events. We investigate block-based masked diffusion (BD) as an alternative on MIMIC-IV under matched tokenisation, context length, model capacity, and evaluation conditions. Across block sizes, BD exhibits a clear quality--efficiency trade-off, with small-block configurations retaining much of the predictive performance of AR while enabling substantially faster inference. A representative B{=}8 configuration achieves approximately 1.43imes faster evaluation. Although generative rollout remains below AR in most settings, frozen linear probes on BD and AR representations achieve near-identical performance across clinical prediction tasks, indicating that BD learns comparably informative clinical representations. Increasing the denoising budget yields diminishing returns, while alternative decoding strategies provide limited gains. Overall, our results show that block diffusion is a viable and computationally attractive approach to longitudinal EHR modelling, with further improvements in iterative decoding offering a promising route toward closing the remaining generative performance gap.

Related

• Provably adaptive sampling with uniform and remasking discrete diffusion models
• Steering Diffusion Models to Rare Events with Sequential Monte Carlo
• Graph-Enhanced Disease Trajectory Discovery and Temporal Endpoint Forecasting from Longitudinal Electronic Health Records

Source: arXiv cs.LG | 2026-10-22