# Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHRs

arXiv: https://arxiv.org/abs/2412.16178 · HTML: https://mlsanity.com/paper/2412.16178/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Placed in Core SSM architectures for language, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 39 of its 55 references that are in the map.
- First posted on arXiv 9 Dec 2024.

## Placed in

- State-space sequence models (S4, Mamba) / [Core SSM architectures for language](https://mlsanity.com/ssm/core-ssm-architectures-for-language/)

## Builds on (most cited first, 30 of 39)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation](https://mlsanity.com/paper/2108.12409/) (2021)
- [Efficient Transformers: A Survey](https://mlsanity.com/paper/2009.06732/) (2020)
- [Extending Context Window of Large Language Models via Positional Interpolation](https://mlsanity.com/paper/2306.15595/) (2023)
- [YaRN: Efficient Context Window Extension of Large Language Models](https://mlsanity.com/paper/2309.00071/) (2023)
- [Recurrent Neural Networks for Multivariate Time Series with Missing Values](https://mlsanity.com/paper/1606.01865/) (2016)
- [Jamba: A Hybrid Transformer-Mamba Language Model](https://mlsanity.com/paper/2403.19887/) (2024)
- [Hyena Hierarchy: Towards Larger Convolutional Language Models](https://mlsanity.com/paper/2302.10866/) (2023)
- [Med-BERT: pre-trained contextualized embeddings on large-scale structured electronic health records for disease prediction](https://mlsanity.com/paper/2005.12833/) (2020)
- [ClimaX: A foundation model for weather and climate](https://mlsanity.com/paper/2301.10343/) (2023)
- [Effective Long-Context Scaling of Foundation Models](https://mlsanity.com/paper/2309.16039/) (2023)
- [BEHRT: Transformer for Electronic Health Records](https://mlsanity.com/paper/1907.09538/) (2019)
- [Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models](https://mlsanity.com/paper/2402.19427/) (2024)
- [Simple linear attention language models balance the recall-throughput tradeoff](https://mlsanity.com/paper/2402.18668/) (2024)
- [HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution](https://mlsanity.com/paper/2306.15794/) (2023)
- [It's Raw! Audio Generation with State-Space Models](https://mlsanity.com/paper/2202.09729/) (2022)
- [EHRSHOT: An EHR Benchmark for Few-Shot Evaluation of Foundation Models](https://mlsanity.com/paper/2307.02028/) (2023)
- [Language Models Are An Effective Patient Representation Learning Technique For Electronic Health Record Data](https://mlsanity.com/paper/2001.05295/) (2020)
- [MOTOR: A Time-To-Event Foundation Model For Structured Medical Records](https://mlsanity.com/paper/2301.03150/) (2023)
- [Zero Shot Health Trajectory Prediction Using Transformer](https://mlsanity.com/paper/2407.21124/) (2024)
- [CEHR-BERT: Incorporating temporal information from structured EHR data to improve prediction tasks](https://mlsanity.com/paper/2111.08585/) (2021)
- [Integrated multimodal artificial intelligence framework for healthcare applications](https://mlsanity.com/paper/2202.12998/) (2022)

## Built on by (most cited first, 30 of 39)

- [MedHELM: Holistic Evaluation of Large Language Models for Medical Tasks](https://mlsanity.com/paper/2505.23802/) (2025)
- [TIMER: Temporal Instruction Modeling and Evaluation for Longitudinal Clinical Records](https://mlsanity.com/paper/2503.04176/) (2025)
- [Clinical ModernBERT: An efficient and long context encoder for biomedical text](https://mlsanity.com/paper/2504.03964/) (2025)
- [Beyond Sensor Data: Foundation Models of Behavioral Data from Wearables Improve Health Predictions](https://mlsanity.com/paper/2507.00191/) (2025)
- [Foundation models for electronic health records: representation dynamics and transferability](https://mlsanity.com/paper/2504.10422/) (2025)
- [A Collection of Innovations in Medical AI for patient records in 2024](https://mlsanity.com/paper/2503.05768/) (2025)
- [Tokenization Tradeoffs in Structured EHR Foundation Models](https://mlsanity.com/paper/2603.15644/) (2026)
- [MedCoT-RAG: Causal Chain-of-Thought RAG for Medical Question Answering](https://mlsanity.com/paper/2508.15849/) (2025)
- [One Loss to Rule Them All: Marked Time-to-Event for Structured EHR Foundation Models](https://mlsanity.com/paper/2602.00541/) (2026)
- [CEHR-XGPT: A Scalable Multi-Task Foundation Model for Electronic Health Records](https://mlsanity.com/paper/2509.03643/) (2025)
- [Retrieval-aligned Tabular Foundation Models Enable Robust Clinical Risk Prediction in Electronic Health Records Under Real-world Constraints](https://mlsanity.com/paper/2604.01841/) (2026)
- [EHR2Path: Comprehensive Pathway-Level Modeling of Longitudinal Patient Trajectories from Multimodal Electronic Health Records](https://mlsanity.com/paper/2506.04831/) (2025)
- [Quantifying surprise in clinical care: Detecting highly informative events in electronic health records with foundation models](https://mlsanity.com/paper/2507.22798/) (2025)
- [Count-Based Approaches Remain Strong: A Benchmark Against Transformer and LLM Pipelines on Structured EHR](https://mlsanity.com/paper/2511.00782/) (2025)
- [Traj-CoA: Patient Trajectory Modeling via Chain-of-Agents for Lung Cancer Risk Prediction](https://mlsanity.com/paper/2510.10454/) (2025)
- [Efficient Generative Prediction for EHR Foundation Models: The SCOPE and REACH Estimators](https://mlsanity.com/paper/2602.03730/) (2026)
- [Learning Clinical Representations Under Systematic Distribution Shift](https://mlsanity.com/paper/2603.07348/) (2026)
- [Discriminative Representation Learning for Clinical Prediction](https://mlsanity.com/paper/2603.20921/) (2026)
- [Agentifying Patient Dynamics within LLMs through Interacting with Clinical World Model](https://mlsanity.com/paper/2605.14723/) (2026)
- [Integrating Genomics into Multimodal EHR Foundation Models](https://mlsanity.com/paper/2510.23639/) (2025)
- [Learning Longitudinal Health Representations from EHR and Wearable Data](https://mlsanity.com/paper/2601.12227/) (2026)
- [Vital Trace: Protocol-Constrained Patient-State Reasoning for Longitudinal Clinical Trajectories](https://mlsanity.com/paper/2602.12833/) (2026)
- [Uncertainty-Aware Foundation Models for Clinical Data](https://mlsanity.com/paper/2604.04175/) (2026)
- [TrajOnco: a multi-agent framework for temporal reasoning over longitudinal EHR for multi-cancer early detection](https://mlsanity.com/paper/2604.10386/) (2026)
- [Handling and Interpreting Missing Modalities in Patient Clinical Trajectories via Autoregressive Sequence Modeling](https://mlsanity.com/paper/2604.18753/) (2026)
- [Stable Prediction of Adverse Events in Medical Time-Series Data](https://mlsanity.com/paper/2510.14286/) (2025)
- [Trajectory-guided discharge stratification for heart failure using short-context electronic health record sequence modeling](https://mlsanity.com/paper/2511.16839/) (2025)
- [A pipeline for enabling path-specific causal fairness in observational health data](https://mlsanity.com/paper/2601.09841/) (2026)
- [Dense Feature Learning via Linear Structure Preservation in Medical Data](https://mlsanity.com/paper/2602.07706/) (2026)
- [Risk Horizons: Structured Hypothesis Spaces for Longitudinal Clinical Prediction](https://mlsanity.com/paper/2602.12828/) (2026)

## Abstract (arXiv)

Foundation Models (FMs) trained on Electronic Health Records (EHRs) have achieved state-of-the-art results on numerous clinical prediction tasks. However, most existing EHR FMs have context windows of <1k tokens. This prevents them from modeling full patient EHRs which can exceed 10k's of events. Recent advancements in subquadratic long-context architectures (e.g., Mamba) offer a promising solution. However, their application to EHR data has not been well-studied. We address this gap by presenting the first systematic evaluation of the effect of context length on modeling EHR data. We find that longer context models improve predictive performance -- our Mamba-based model surpasses the prior state-of-the-art on 9/14 tasks on the EHRSHOT prediction benchmark. For clinical applications, however, model performance alone is insufficient -- robustness to the unique properties of EHR is crucial. Thus, we also evaluate models across three previously underexplored properties of EHR data: (1) the prevalence of "copy-forwarded" diagnoses which creates artificial repetition of tokens within EHR sequences; (2) the irregular time intervals between EHR events which can lead to a wide range of timespans within a context window; and (3) the natural increase in disease complexity over time which makes later tokens in the EHR harder to predict than earlier ones. Stratifying our EHRSHOT results, we find that higher levels of each property correlate negatively with model performance, but that longer context models are more robust to more extreme levels of these properties. Our work highlights the potential for using long-context architectures to model EHR data, and offers a case study for identifying new challenges in modeling sequential data motivated by domains outside of natural language. We release our models and code at: https://github.com/som-shahlab/long_context_clues