HemeCount-CBC
HemeCount-CBC is a SYNTHETIC/DEMO blood analysis model for anomaly detection in complete blood count. Outputs are deterministic demo values — NOT for clinical use. Trained (synthetically) on de-identified tabular data.
Tabular
EMBL-Synthetic
License: CC-BY-4.0
v4.0.2
RTG 4.7
DL 367,608
Metrics
| Metric | Value | Split |
|---|---|---|
| F1 | 0.821 | Synthetic hold-out |
| Calibration (ECE) | 0.076 | Synthetic |
| Inputs | Outputs |
|---|---|
| CBC panel | Flagged abnormalities |
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-031-hemecount-cbc/predict",
headers={"Authorization": "Bearer <API_KEY>"},
json={"input": "<cbc panel>"})
print(r.json()) # -> synthetic demo prediction
See the API reference · JSON: /api/models/bf-031-hemecount-cbc
Version history
| Version | Status | Notes |
|---|---|---|
| v4.0.0 | Archived | Synthetic release note 0 |
| v4.0.1 | Archived | Synthetic release note 1 |
| v4.0.2 | Current | Synthetic release note 2 |
Community contributions: 147 synthetic contributors have submitted evaluations and fine-tunes.