GRAIL: Geometry-Aware Retrieval-Augmented Inference with LLMs over Hyperbolic Representations of Patient Trajectories
This work addresses the problem of clinical event prediction for healthcare applications, offering an incremental improvement by integrating geometric modeling with LLMs to reduce hallucinations and enhance accuracy.
The paper tackled the challenge of predicting future clinical events from longitudinal electronic health records by proposing GRAIL, a framework that models EHRs using hyperbolic representations and retrieval-augmented inference, resulting in improved multi-type next-visit prediction and more hierarchy-consistent forecasts on MIMIC-IV.
Predicting future clinical events from longitudinal electronic health records (EHRs) is challenging due to sparse multi-type clinical events, hierarchical medical vocabularies, and the tendency of large language models (LLMs) to hallucinate when reasoning over long structured histories. We study next-visit event prediction, which aims to forecast a patient's upcoming clinical events based on prior visits. We propose GRAIL, a framework that models longitudinal EHRs using structured geometric representations and structure-aware retrieval. GRAIL constructs a unified clinical graph by combining deterministic coding-system hierarchies with data-driven temporal associations across event types, embeds this graph in hyperbolic space, and summarizes each visit as a probabilistic Central Event that denoises sparse observations. At inference time, GRAIL retrieves a structured set of clinically plausible future events aligned with hierarchical and temporal progression, and optionally refines their ranking using an LLM as a constrained inference-time reranker. Experiments on MIMIC-IV show that GRAIL consistently improves multi-type next-visit prediction and yields more hierarchy-consistent forecasts.