Status-Aware Self-Supervised Forecasting for Irregular Clinical Time Series

Kwanhyung Lee, Joohyung Lee, Jong-Heon Kim, Sangchul Hahn, Eunho Yang

Presentation Attendance: Yes, we will present in-person

Keywords: Irregular time series, Electronic health records (EHR), Self-supervised learning, Clinical forecasting

TL;DR: We introduce EHR-SPC, an event-aligned self-supervised framework that learns from irregular EHR event streams to forecast future status representations without discretization, improving downstream prediction.

Abstract: Electronic health record (EHR) time series are irregular event streams, and many clinical tasks require forecasting a patient’s future state from their history. Because labeled outcomes in EHR are often limited and class-imbalanced, self-supervised learning (SSL) on large unlabeled cohorts is attractive. However, most existing EHR SSL methods first convert irregular event streams into discretized time grids, thereby losing the native event-set structure of observations. We propose a downstream task-aligned pretraining framework that models EHR trajectories as event sets and learns representations by forecasting future clinical states in latent space from the full past context. Our framework combines a momentum teacher for stable targets, a query-based Transformer decoder to predict variable future event sets, and an auxiliary masked event objective to improve local robustness. Across multiple ICU prediction tasks, our approach consistently improves downstream performance.

Track: Research Track (max 4 pages)

Submission Number: 39