MoRGEN: Mixture-of-Resolutions Generative Forecasting for Irregularly Sampled Medical Time-Series Data

Abstract

Autoregressive generative models for irregularly sampled clinical time-series data are increasingly used for zero-shot risk forecasting. Prior work typically adopts a single fine-grained discretization of time, where tokens are generated at one fixed, pre-determined, temporal resolution. We demonstrate that zero-shot accuracy for a given task varies depending on the temporal dynamics of the task in question, where performance will be low when the temporal dynamics is not well-matched to temporal resolution of the generative model. We then propose MoRGen (Mixture-of-Resolutions Generation), which fuses zero-shot generative experts trained at multiple resolutions, to improve zero-shot performance across tasks with very different temporal dynamics. Across multiple horizons and outcomes on three independent clinical datasets, MoRGen achieves lower binary-cross entropy (BCE) and statistically significant AUROC gains over autoregressive generative models that forecast tokens at a fixed temporal resolution.