Skip to content

Latest commit

 

History

History
56 lines (43 loc) · 2.47 KB

README.md

File metadata and controls

56 lines (43 loc) · 2.47 KB

Odyssey

A library for developing foundation models using Electronic Health Records (EHR) data.

Visit our recent EHRMamba paper

Introduction

Odyssey is a comprehensive library designed to facilitate the development, training, and deployment of foundation models for Electronic Health Records (EHR). Recently, we used this toolkit to develop EHRMamba, a cutting-edge EHR foundation model that leverages the Mamba architecture and Multitask Prompted Finetuning (MPF) to overcome the limitations of existing transformer-based models. EHRMamba excels in processing long temporal sequences, simultaneously learning multiple clinical tasks, and performing EHR forecasting, significantly advancing the state of the art in EHR modeling.

Key Features

The toolkit is structured into four main modules to streamline the development process:

  1. data:

    • Gathers EHR datasets from HL7 FHIR resources.
    • Processes patient sequences for clinical tasks.
    • Tokenizes data and creates data splits for model training.
    • Provides a dataset class for model training.
  2. models:

    • Implements models including XGBoost, LSTM, CEHR-BERT, BigBird, MultiBird, and EHRMamba.
    • Offers various embedding classes necessary for the models.
  3. evals:

    • Includes tools for testing models on clinical prediction tasks and forecasting.
    • Provides evaluation metrics for thorough assessment of model performance.
  4. interp:

    • Contains methods for interpreting model decisions.
    • Features interactive visualization of attention matrices for Transformer-based models.
    • Includes novel interpretability techniques for EHRMamba and gradient attribution methods.

Contributing

We welcome contributions from the community! Please open an issue.

Citation

If you use EHRMamba or Odyssey in your research, please cite our paper:

@misc{fallahpour2024ehrmamba,
      title={EHRMamba: Towards Generalizable and Scalable Foundation Models for Electronic Health Records},
      author={Adibvafa Fallahpour and Mahshid Alinoori and Arash Afkanpour and Amrit Krishnan},
      year={2024},
      eprint={2405.14567},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}