StrokeCT-Triage
StrokeCT-Triage is a SYNTHETIC/DEMO medical imaging model for acute stroke large-vessel occlusion triage. Outputs are deterministic demo values — NOT for clinical use. Trained (synthetically) on de-identified imaging data.
Imaging
DeepCell AI
License: BSD-3-Clause
v3.4.2
RTG 4.8
DL 136,806
Metrics
| Metric | Value | Split |
|---|---|---|
| AUC | 0.951 | Synthetic hold-out |
| Calibration (ECE) | 0.062 | Synthetic |
| Inputs | Outputs |
|---|---|
| Head CTA | LVO probability + laterality |
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-039-strokect-triage/predict",
headers={"Authorization": "Bearer <API_KEY>"},
json={"input": "<head cta>"})
print(r.json()) # -> synthetic demo prediction
See the API reference · JSON: /api/models/bf-039-strokect-triage
Version history
| Version | Status | Notes |
|---|---|---|
| v3.4.0 | Archived | Synthetic release note 0 |
| v3.4.1 | Archived | Synthetic release note 1 |
| v3.4.2 | Current | Synthetic release note 2 |
Community contributions: 102 synthetic contributors have submitted evaluations and fine-tunes.