SepsisEarly-Lab
SepsisEarly-Lab is a SYNTHETIC/DEMO blood analysis model for early sepsis risk from serial labs. Outputs are deterministic demo values — NOT for clinical use. Trained (synthetically) on de-identified tabular data.
Tabular
Helix Diagnostics
License: MIT
v3.3.2
RTG 4.6
DL 305,907
Metrics
| Metric | Value | Split |
|---|---|---|
| AUROC | 0.896 | Synthetic hold-out |
| Calibration (ECE) | 0.028 | Synthetic |
| Inputs | Outputs |
|---|---|
| Time-series vitals + labs | Sepsis risk trajectory |
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-032-sepsisearly-lab/predict",
headers={"Authorization": "Bearer <API_KEY>"},
json={"input": "<time-series vitals + labs>"})
print(r.json()) # -> synthetic demo prediction
See the API reference · JSON: /api/models/bf-032-sepsisearly-lab
Version history
| Version | Status | Notes |
|---|---|---|
| v3.3.0 | Archived | Synthetic release note 0 |
| v3.3.1 | Archived | Synthetic release note 1 |
| v3.3.2 | Current | Synthetic release note 2 |
Community contributions: 87 synthetic contributors have submitted evaluations and fine-tunes.