R. Kamaleswaran

Capacity-Neutral Training Transfers Across Sites in Multimodal Sleep Prediction of Future Cognitive Impairment

Development of a machine-learning risk stratification tool for vasoactive medication need after two-bolus fluid resuscitation in pediatric suspected sepsis.

A machine-learning model using eight routinely available clinical variables accurately predicts vasoactive medication need after two fluid boluses in pediatric suspected sepsis, identifying children at risk for fluid-refractory septic shock.

Intervention Granularity Matters: Coherent Treatment Bundles in Counterfactual Simulation with Clinical World Models

Counterfactual simulation with a clinical world model means fixing a patient's history, changing the treatment, and reading off the predicted response. Doing so requires deciding what counts as one intervention. In clinical settings, interventions are documented as bundles: a co-occurrence audit of 945,707 patient-hour...

Clin-JEPA: A Multi-Phase Co-Training Framework for Joint-Embedding Predictive Pretraining on EHR Patient Trajectories

Clin-JEPA is presented, a five-phase curriculum that stably co-trains an LLM encoder with a latent trajectory predictor on MIMIC-IV, outperforming strong per-task tuned baselines and a pretrained EHR foundation model.