odyssey
importedsoftware/odyssey
A toolkit for developing foundation models using Electronic Health Record (EHR) data.
Machine-generated from the listed sources and not yet reviewed by a human.
- Category
- Software & Systems
- Subcategory
- unknown
- License
- Apache-2.0(osi)
- Status
- active
- Maturity
- deployed
- Organization
- VectorInstitute
- Country
- unknown
- Repository
- github.com/VectorInstitute/odyssey
- Documentation
- unknown
- Tags
- electronic-health-record · foundation-models · healthcare · machine-learning · mimic-iv · state-space-models · transformers
- Regulatory
- unknown
Top contributors by commit count, from the project’s public repository. Avatars are served by their origin, not stored here. To be removed from this list, open an issue.
Computed from shared tags, weighted so a rare tag counts for more than a common one. These are suggestions, not curated relationships.
- cyclopselectronic-health-record · healthcare · mimic-iv
A toolkit for evaluating and monitoring AI models in clinical settings
- meds_readerelectronic-health-record · foundation-models · healthcare
A high-performance database and Python reader interface for MEDS datasets
- LEADER-pytorchhealthcare · mimic-iv
[arXiv'24] The official implementation code of LEADER.
- DenoMambastate-space-models
Official implementation of DenoMamba: A fused state-space model for low-dose CT denoising
- MambaRollstate-space-models
Official implementation of MambaRoll: A Physics-Driven Autoregressive State Space Model for Medical Image Reconstruction (https://arxiv.org/abs/2412.09331)
- PyHealthelectronic-health-record · healthcare
A Deep Learning Python Toolkit for Healthcare Applications.
- api.github.com/repos/VectorInstitute/odysseyretrieved 2026-08-05 · via github-api
Machine-imported from GitHub search. Last push 2026-08-03, 61 stars, license reported as Apache-2.0. Category and schematic were assigned by keyword heuristics and are unreviewed.
Not yet verified by a human. Correct this record →
/v1/entries/1.json→ .entries["odyssey"]
Entries are sharded 64 ways by a stable hash of the id, so a consumer can find any record without an index.