GitHub · Python
VectorInstitute/odyssey
An interpretable foundation model of the patient clinical timeline: event forecasting, calibrated time-to-event alerts, and concept-level interpretability, benchmarked head-to-head against tuned GBMs, tabular foundation models, and survival baselines on MIMIC-IV, eICU, and GEMINI via the MEDS standard.
- Stars
- 64
- Forks
- 16
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: foundation-models, mimic-iv, transformers, state-space-models, healthcare, machine-learning, clinical-ai, concept-bottleneck, ehr, eicu
Latest data point: Nov 21, 2026 · 64 stars · 16 forks