PULSE: Self-Supervised Clinical Phase Discovery for Multimodal ICU Disease Progression Modeling

ICU disease progression often evolve through clinically distinct phases, characterized by different physiological states and diagnostic and treatment needs. These phases, however, are not explicitly delineated in routinely collected data and must be inferred from asynchronous multimodal observations. Observation intensity also varies substantially over time, leaving some phases densely sampled and others sparsely observed. Models that directly aggregate observed events can therefore be biased to densely sampled phases in the learned trajectory representations, potentially obscuring the underlying clinical dynamics. We propose $\text{PULSE}$, a self-supervised framework that explicitly discovers latent clinical phases from asynchronous multimodal observations. These phases are shared across patients and modalities and provide a common structure for representing evolving patient states. To reduce sensitivity to variations in observation intensity and timing, $\text{PULSE}$ encourages consistent phase assignments under sampling perturbations, including event duplication, timestamp jitter, and measurement removal. We evaluate $\text{PULSE}$ on MIMIC and eICU across five dynamic prediction tasks: AKI progression, sepsis progression, vasopressor initiation, intubation need, and remaining length of stay. $\text{PULSE}$ achieves the best overall performance among the evaluated baselines, supporting the value of phase-aware representations for modeling and predicting evolving patient states from irregular multimodal disease trajectories.