Risk Horizons: Structured Hypothesis Spaces for Longitudinal Clinical Prediction

TL;DR

Risk Horizons is a geometry-aware framework that constructs patient-specific, structured hypothesis spaces for improved longitudinal clinical event prediction from EHR data.

Contribution

It introduces a novel hyperbolic embedding approach combining clinical hierarchies with data-driven associations for better prediction accuracy.

Findings

Achieved competitive next-visit prediction performance on MIMIC-IV and eICU datasets.

Improved hierarchy consistency across diagnoses, procedures, and medications.

Hyperbolic structured candidate retrieval significantly enhances prediction performance.

Abstract

Predicting future clinical events from longitudinal electronic health records (EHRs) requires selecting plausible outcomes from a large and structured event space under sparse observations. While clinical coding systems provide hierarchical organization of events, cross-modal and temporal relationships are not explicitly specified and must instead be inferred from data, making prediction difficult for weakly observed longitudinal transitions. We introduce Risk Horizons, a geometry-aware framework for constructing patient-specific candidate spaces for multi-modal next-visit prediction. Risk Horizons combines deterministic coding hierarchies with data-driven lagged cross-modal associations, embeds the resulting clinical graph in hyperbolic space, and retrieves candidate futures using directional risk cones. This reframes longitudinal prediction as ranking within a compact, clinically coherent hypothesis space rather than scoring an unconstrained vocabulary. Experiments on MIMIC-IV and eICU demonstrate competitive next-visit prediction performance, with consistently improved hierarchy consistency across diagnoses, procedures, and medications. Further analysis suggests that hyperbolic structured candidate retrieval is the primary driver of performance, while LLMs are effective as constrained inference-time rerankers operating over clinically grounded candidate sets.