# MIRA: Medical Time Series Foundation Model for Real-World Health Data

arXiv: https://arxiv.org/abs/2506.07584 · HTML: https://mlsanity.com/paper/2506.07584/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 54 of its 90 references that are in the map.
- First posted on arXiv 9 Jun 2025.

## Builds on (most cited first, 30 of 54)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis](https://mlsanity.com/paper/2210.02186/) (2022)
- [Simplified State Space Layers for Sequence Modeling](https://mlsanity.com/paper/2208.04933/) (2022)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [N-BEATS: Neural basis expansion analysis for interpretable time series forecasting](https://mlsanity.com/paper/1905.10437/) (2019)
- [Time-LLM: Time Series Forecasting by Reprogramming Large Language Models](https://mlsanity.com/paper/2310.01728/) (2023)
- [A decoder-only foundation model for time-series forecasting](https://mlsanity.com/paper/2310.10688/) (2023)
- [Unified Training of Universal Time Series Forecasting Transformers](https://mlsanity.com/paper/2402.02592/) (2024)
- [Large Language Models Are Zero-Shot Time Series Forecasters](https://mlsanity.com/paper/2310.07820/) (2023)
- [MOMENT: A Family of Open Time-series Foundation Models](https://mlsanity.com/paper/2402.03885/) (2024)
- [Multitask learning and benchmarking with clinical time series data](https://mlsanity.com/paper/1703.07771/) (2017)
- [Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts](https://mlsanity.com/paper/2409.16040/) (2024)
- [On Neural Differential Equations](https://mlsanity.com/paper/2202.02435/) (2022)
- [Foundation Models for Time Series Analysis: A Tutorial and Survey](https://mlsanity.com/paper/2403.14735/) (2024)
- [Timer: Generative Pre-trained Transformers Are Large Time Series Models](https://mlsanity.com/paper/2402.02368/) (2024)
- [Latent ODEs for Irregularly-Sampled Time Series](https://mlsanity.com/paper/1907.03907/) (2019)
- [Sundial: A Family of Highly Capable Time Series Foundation Models](https://mlsanity.com/paper/2502.00816/) (2025)
- [TimeGPT-1](https://mlsanity.com/paper/2310.03589/) (2023)
- [UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting](https://mlsanity.com/paper/2310.09751/) (2023)
- [TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2306.09364/) (2023)
- [Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting](https://mlsanity.com/paper/2310.08278/) (2023)
- [Modeling Irregular Time Series with Continuous Recurrent Units](https://mlsanity.com/paper/2111.11344/) (2021)
- [Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts](https://mlsanity.com/paper/2410.10469/) (2024)
- [Modeling Missing Data in Clinical Time Series with RNNs](https://mlsanity.com/paper/1606.04130/) (2016)
- [Foundation Model for Advancing Healthcare: Challenges, Opportunities, and Future Directions](https://mlsanity.com/paper/2404.03264/) (2024)

## Built on by (most cited first, 22 of 22)

- [EHR-RAG: Bridging Long-Horizon Structured Electronic Health Records and Large Language Models via Enhanced Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.21340/) (2026)
- [Data Mixing Agent: Learning to Re-weight Domains for Continual Pre-training](https://mlsanity.com/paper/2507.15640/) (2025)
- [Time Series Reasoning via Process-Verifiable Thinking Data Synthesis and Scheduling for Tailored LLM Reasoning](https://mlsanity.com/paper/2602.07830/) (2026)
- [TimeRFT: Stimulating Generalizable Time Series Forecasting for TSFMs via Reinforcement Finetuning](https://mlsanity.com/paper/2605.00015/) (2026)
- [TSFMAudit: Data Contamination Auditing in Forecasting Time Series Foundation Models](https://mlsanity.com/paper/2605.26161/) (2026)
- [Bridging the Last Mile of Time Series Forecasting with LLM Agents](https://mlsanity.com/paper/2606.02497/) (2026)
- [Diff-MN: Diffusion Parameterized MoE-NCDE for Continuous Time Series Generation with Irregular Observations](https://mlsanity.com/paper/2601.13534/) (2026)
- [Signal or Noise? Understanding Generative Models for Real-World Sensor Time Series](https://mlsanity.com/paper/2607.04245/) (2026)
- [EHR-MPC: Inference-Time Control for Sepsis Treatment with Generative Patient Digital Twins](https://mlsanity.com/paper/2607.08793/) (2026)
- [Privacy-Preserving Generation of Clinical Narratives from Medical Terminologies](https://mlsanity.com/paper/2509.10882/) (2025)
- [UTICA: Multi-Objective Self-Distllation Foundation Model Pretraining for Time Series Classification](https://mlsanity.com/paper/2603.01348/) (2026)
- [SOTER: A Generative Time-Series Foundation Model for Wearable Human Physiological Signals](https://mlsanity.com/paper/2609.16804/) (2026)
- [Arg-LLaDA: Argument Summarization via Large Language Diffusion Models and Sufficiency-Aware Refinement](https://mlsanity.com/paper/2507.19081/) (2025)
- [MuteBench: Modality Unavailability Tolerance Evaluation for Incomplete Multimodal Fusion](https://mlsanity.com/paper/2605.15235/) (2026)
- [PAMF: Prior-Aware Multimodal Fusion for Incomplete Time Series Data](https://mlsanity.com/paper/2606.06328/) (2026)
- [Tyan-WP: A Wind Power Foundation Model for Ultra-Short-Term Probabilistic Forecasting](https://mlsanity.com/paper/2606.08630/) (2026)
- [Are Time-Series Foundation Models Ready for E-Nose Data? An Empirical Assessment of Their Embeddings](https://mlsanity.com/paper/2606.27672/) (2026)
- [GLAIM: Learning Global and Local Adaptive Inter-Variable Dependency for Multivariate Time Series Imputation](https://mlsanity.com/paper/2608.02366/) (2026)
- [TSPFN: A Temporal Tabular Foundation Model for Physiological Time Series Classification](https://mlsanity.com/paper/2608.31013/) (2026)
- [Large language models in medical time series analysis](https://mlsanity.com/paper/2609.22262/) (2026)
- [BITS: Rethinking Fair and Comprehensive Evaluation for Irregular Time Series Forecasting](https://mlsanity.com/paper/2609.33303/) (2026)
- [QiYao-I: A Manifold Based Foundation Model for Irregular Multivariate Time Series Forecasting](https://mlsanity.com/paper/2610.06936/) (2026)

## Abstract (arXiv)

A unified foundation model for medical time series -- pretrained on open access and ethics board-approved medical corpora -- offers the potential to reduce annotation burdens, minimize model customization, and enable robust transfer across clinical institutions, modalities, and tasks, particularly in data-scarce or privacy-constrained environments. However, existing generalist time series foundation models struggle to handle medical time series data due to their inherent challenges, including irregular intervals, heterogeneous sampling rates, and frequent missing values. To address these challenges, we introduce MIRA, a unified foundation model specifically designed for medical time series forecasting. MIRA incorporates a Continuous-Time Rotary Positional Encoding that enables fine-grained modeling of variable time intervals, a frequency-specific mixture-of-experts layer that routes computation across latent frequency regimes to further promote temporal specialization, and a Continuous Dynamics Extrapolation Block based on Neural ODE that models the continuous trajectory of latent states, enabling accurate forecasting at arbitrary target timestamps. Pretrained on a large-scale and diverse medical corpus comprising over 454 billion time points collect from publicly available datasets, MIRA achieves reductions in forecasting errors by an average of 10% and 7% in out-of-distribution and in-distribution scenarios, respectively, when compared to other zero-shot and fine-tuned baselines. We also introduce a comprehensive benchmark spanning multiple downstream clinical tasks, establishing a foundation for future research in medical time series modeling.