块扩散模型用于纵向电子健康记录：准确性、效率与表征权衡

View PDF HTML (experimental)

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 $1.43\times$ 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.

Subjects:	Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
Cite as:	arXiv:2610.29533 [cs.LG]
	(or arXiv:2610.29533v1 [cs.LG] for this version)
	https://doi.org/10.48550/arXiv.2610.29533 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Ashvin Gupta [view email]
[v1] Wed, 21 Oct 2026 10:23:34 UTC (443 KB)