ReadmitRisk-30
ReadmitRisk-30 is a SYNTHETIC/DEMO clinical model for 30-day hospital readmission risk. Outputs are deterministic demo values — NOT for clinical use. Trained (synthetically) on de-identified tabular data.
Tabular
Insilico BioFoundry
License: MIT
v4.3.5
RTG 3.8
DL 375,745
Metrics
| Metric | Value | Split |
|---|---|---|
| AUROC | 0.939 | Synthetic hold-out |
| Calibration (ECE) | 0.046 | Synthetic |
| Inputs | Outputs |
|---|---|
| EHR features | Readmission probability |
Run a synthetic prediction
Returns a deterministic synthetic result — clearly labeled, not for clinical use.
API integration
Call this model from your pipeline (demo — no real key required):
import requests
r = requests.post("https://api.biofoundry.ai/v1/models/bf-041-readmitrisk-30/predict",
headers={"Authorization": "Bearer <API_KEY>"},
json={"input": "<ehr features>"})
print(r.json()) # -> synthetic demo prediction
See the API reference · JSON: /api/models/bf-041-readmitrisk-30
Version history
| Version | Status | Notes |
|---|---|---|
| v4.3.0 | Archived | Synthetic release note 0 |
| v4.3.1 | Archived | Synthetic release note 1 |
| v4.3.2 | Archived | Synthetic release note 2 |
| v4.3.3 | Archived | Synthetic release note 3 |
| v4.3.4 | Archived | Synthetic release note 4 |
| v4.3.5 | Current | Synthetic release note 5 |
Community contributions: 13 synthetic contributors have submitted evaluations and fine-tunes.