# Risk Horizons: Structured Hypothesis Spaces for Longitudinal Clinical Prediction

arXiv: https://arxiv.org/abs/2602.12828 · HTML: https://mlsanity.com/paper/2602.12828/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 50 references that are in the map.
- First posted on arXiv 13 Feb 2026.

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Poincar'e Embeddings for Learning Hierarchical Representations](https://mlsanity.com/paper/1705.08039/) (2017)
- [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://mlsanity.com/paper/2306.08302/) (2023)
- [Capabilities of GPT-4 on Medical Challenge Problems](https://mlsanity.com/paper/2303.13375/) (2023)
- [Recurrent Neural Networks for Multivariate Time Series with Missing Values](https://mlsanity.com/paper/1606.01865/) (2016)
- [Hyperbolic Neural Networks](https://mlsanity.com/paper/1805.09112/) (2018)
- [Hyperbolic Graph Convolutional Neural Networks](https://mlsanity.com/paper/1910.12933/) (2019)
- [Med-BERT: pre-trained contextualized embeddings on large-scale structured electronic health records for disease prediction](https://mlsanity.com/paper/2005.12833/) (2020)
- [RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism](https://mlsanity.com/paper/1608.05745/) (2016)
- [Benchmarking Retrieval-Augmented Generation for Medicine](https://mlsanity.com/paper/2402.13178/) (2024)
- [Multitask learning and benchmarking with clinical time series data](https://mlsanity.com/paper/1703.07771/) (2017)
- [Scalable and accurate deep learning for electronic health records](https://mlsanity.com/paper/1801.07860/) (2018)
- [MEDITRON-70B: Scaling Medical Pretraining for Large Language Models](https://mlsanity.com/paper/2311.16079/) (2023)
- [BEHRT: Transformer for Electronic Health Records](https://mlsanity.com/paper/1907.09538/) (2019)
- [Hyperbolic Graph Neural Networks](https://mlsanity.com/paper/1910.12892/) (2019)
- [Doctor AI: Predicting Clinical Events via Recurrent Neural Networks](https://mlsanity.com/paper/1511.05942/) (2015)
- [GRAM: Graph-based Attention Model for Healthcare Representation Learning](https://mlsanity.com/paper/1611.07012/) (2016)
- [Pre-training of Graph Augmented Transformers for Medication Recommendation](https://mlsanity.com/paper/1906.00346/) (2019)
- [Learning to Diagnose with LSTM Recurrent Neural Networks](https://mlsanity.com/paper/1511.03677/) (2015)
- [MOTOR: A Time-To-Event Foundation Model For Structured Medical Records](https://mlsanity.com/paper/2301.03150/) (2023)
- [Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHRs](https://mlsanity.com/paper/2412.16178/) (2024)
- [DeepCare: A Deep Dynamic Memory Model for Predictive Medicine](https://mlsanity.com/paper/1602.00357/) (2016)
- [Self-Supervised Graph Learning with Hyperbolic Embedding for Temporal Health Event Prediction](https://mlsanity.com/paper/2106.04751/) (2021)
- [MedGCN: Medication recommendation and lab test imputation via graph convolutional networks](https://mlsanity.com/paper/1904.00326/) (2019)

## Abstract (arXiv)

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.