GRAIL: Geometry-Aware Retrieval-Augmented Inference with LLMs over Hyperbolic Representations of Patient Trajectories

• URL: http://arxiv.org/abs/2602.12828v1
• Date: Fri, 13 Feb 2026 11:30:37 GMT
• Title: GRAIL: Geometry-Aware Retrieval-Augmented Inference with LLMs over Hyperbolic Representations of Patient Trajectories
• Abstract summary: We study next-visit event prediction, which aims to forecast a patient's upcoming clinical events based on prior visits.<n>We propose GRAIL, a framework that models longitudinal EHRs using structured geometric representations and structure-aware retrieval.<n>Experiments on MIMIC-IV show that GRAIL consistently improves multi-type next-visit prediction and yields more hierarchy-consistent forecasts.
• Score: 7.2159153945746795
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: 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.

Related papers

• HoT-SSM:Higher-order Temporal Knowledge Graph Reasoning with State Space Models for Health Care [4.959832547805051]
  We propose HoT-SSM, a parameter efficient and higher-order temporal graph reasoning with state space models.<n>For each visit, HoT-SSM constructs hypergraphs by grouping semantically related clinical concepts into hyperedges using domain knowledge.<n>Experiments on MIMIC-III and MIMIC-IV datasets shows significant performance improvement over the current state-of-the-art models.
  arXiv  Detail & Related papers  (2026-06-04T10:42:18Z)
• Multimodal Graph-based Classification of Esophageal Motility Disorders [73.90451172929117]
  Diagnosing esophageal motility disorders pose significant challenges due to the complexity of high-resolution impedance manometry data and variability in clinical interpretation.<n>This work explores the feasibility of a multimodal Machine Learning-based classification approach that combines HRIM recordings with patient-specific information and incorporates a graph-based modeling of esophageal physiology.
  arXiv  Detail & Related papers  (2026-05-13T14:52:12Z)
• DT-BEHRT: Disease Trajectory-aware Transformer for Interpretable Patient Representation Learning [29.777694695551606]
  Disease Trajectory-aware Transformer for EHR (DT-BEHRT)<n>We propose a graph-enhanced sequential architecture that disentangles disease trajectories by explicitly modeling diagnosis-centric interactions within organ systems and capturing asynchronous progression patterns.<n>Experiments on multiple benchmark datasets demonstrate that DT-BEHRT achieves strong predictive performance and provides interpretable patient representations that align with clinicians' disease-centered reasoning.
  arXiv  Detail & Related papers  (2026-03-10T19:21:40Z)
• Serialized EHR make for good text representations [1.585843510099207]
  SerialBEHRT is a domain aligned foundation model that extends SciBERT through additional pretraining on structured EHR sequences.<n>We evaluate its effectiveness on the task of antibiotic susceptibility prediction, a clinically meaningful problem in antibiotic stewardship.
  arXiv  Detail & Related papers  (2025-10-11T17:16:15Z)
• Building the EHR Foundation Model via Next Event Prediction [5.378917071184147]
  Next Event Prediction (NEP) is a framework that enhances Large Language Models' temporal reasoning.<n>NEP explicitly models disease progression patterns and causal relationships.<n>Our analyses reveal dual benefits: state-of-the-art prediction accuracy combined with clinically interpretable attention patterns.
  arXiv  Detail & Related papers  (2025-09-29T23:27:51Z)
• Time-Aware Attention for Enhanced Electronic Health Records Modeling [8.4225455796455]
  TALE-EHR is a Transformer-based framework featuring a novel time-aware attention mechanism that explicitly models continuous temporal gaps.<n>Our approach outperforms state-of-the-art baselines on tasks such as disease progression forecasting.
  arXiv  Detail & Related papers  (2025-07-20T07:32:41Z)
• Foundation Models for Clinical Records at Health System Scale [40.88151645546234]
  We present a novel generative pretraining strategy for sequential EHR data using next-visit event prediction.<n>Our model learns to autoregressively generate various tokenized clinical events for the next visit based on patient history.
  arXiv  Detail & Related papers  (2025-07-01T08:52:33Z)
• HC-LLM: Historical-Constrained Large Language Models for Radiology Report Generation [89.3260120072177]
  We propose a novel Historical-Constrained Large Language Models (HC-LLM) framework for Radiology report generation.<n>Our approach extracts both time-shared and time-specific features from longitudinal chest X-rays and diagnostic reports to capture disease progression.<n> Notably, our approach performs well even without historical data during testing and can be easily adapted to other multimodal large models.
  arXiv  Detail & Related papers  (2024-12-15T06:04:16Z)
• Deep State-Space Generative Model For Correlated Time-to-Event Predictions [54.3637600983898]
  We propose a deep latent state-space generative model to capture the interactions among different types of correlated clinical events. Our method also uncovers meaningful insights about the latent correlations among mortality and different types of organ failures.
  arXiv  Detail & Related papers  (2024-07-28T02:42:36Z)
• SHAPE: A Sample-adaptive Hierarchical Prediction Network for Medication Recommendation [22.899946140205962]
  We propose a novel Sample-adaptive Hierarchical medicAtion Prediction nEtwork, termed SHAPE, to tackle the challenges in the medication recommendation task. Specifically, we design a compact intra-visit set encoder to encode the relationship in the medical event for obtaining visit-level representation. To endow the model with the capability of modeling the variable visit length, we introduce a soft curriculum learning method to assign the difficulty of each sample automatically by the visit length.
  arXiv  Detail & Related papers  (2023-09-09T08:28:04Z)
• Time Associated Meta Learning for Clinical Prediction [78.99422473394029]
  We propose a novel time associated meta learning (TAML) method to make effective predictions at multiple future time points. To address the sparsity problem after task splitting, TAML employs a temporal information sharing strategy to augment the number of positive samples. We demonstrate the effectiveness of TAML on multiple clinical datasets, where it consistently outperforms a range of strong baselines.
  arXiv  Detail & Related papers  (2023-03-05T03:54:54Z)
• T-Phenotype: Discovering Phenotypes of Predictive Temporal Patterns in Disease Progression [82.85825388788567]
  We develop a novel temporal clustering method, T-Phenotype, to discover phenotypes of predictive temporal patterns from labeled time-series data. We show that T-Phenotype achieves the best phenotype discovery performance over all the evaluated baselines.
  arXiv  Detail & Related papers  (2023-02-24T13:30:35Z)
• BiteNet: Bidirectional Temporal Encoder Network to Predict Medical Outcomes [53.163089893876645]
  We propose a novel self-attention mechanism that captures the contextual dependency and temporal relationships within a patient's healthcare journey. An end-to-end bidirectional temporal encoder network (BiteNet) then learns representations of the patient's journeys. We have evaluated the effectiveness of our methods on two supervised prediction and two unsupervised clustering tasks with a real-world EHR dataset.
  arXiv  Detail & Related papers  (2020-09-24T00:42:36Z)
• Trajectories, bifurcations and pseudotime in large clinical datasets: applications to myocardial infarction and diabetes data [94.37521840642141]
  We suggest a semi-supervised methodology for the analysis of large clinical datasets, characterized by mixed data types and missing values. The methodology is based on application of elastic principal graphs which can address simultaneously the tasks of dimensionality reduction, data visualization, clustering, feature selection and quantifying the geodesic distances (pseudotime) in partially ordered sequences of observations.
  arXiv  Detail & Related papers  (2020-07-07T21:04:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.