TrialMatch-NLP
TrialMatch-NLP is a SYNTHETIC/DEMO clinical model for patient-to-clinical-trial matching. Outputs are deterministic demo values — NOT for clinical use. Trained (synthetically) on de-identified multi-modal data.
Multi-modal
EMBL-Synthetic
License: Apache-2.0
v2.2.8
RTG 4.0
DL 207,743
Metrics
| Metric | Value | Split |
|---|---|---|
| Recall@10 | 0.871 | Synthetic hold-out |
| Calibration (ECE) | 0.025 | Synthetic |
| Inputs | Outputs |
|---|---|
| Patient record + criteria | Ranked eligible trials |
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-043-trialmatch-nlp/predict",
headers={"Authorization": "Bearer <API_KEY>"},
json={"input": "<patient record + criteria>"})
print(r.json()) # -> synthetic demo prediction
See the API reference · JSON: /api/models/bf-043-trialmatch-nlp
Version history
| Version | Status | Notes |
|---|---|---|
| v2.2.0 | Archived | Synthetic release note 0 |
| v2.2.1 | Archived | Synthetic release note 1 |
| v2.2.2 | Archived | Synthetic release note 2 |
| v2.2.3 | Archived | Synthetic release note 3 |
| v2.2.4 | Archived | Synthetic release note 4 |
| v2.2.5 | Archived | Synthetic release note 5 |
| v2.2.6 | Archived | Synthetic release note 6 |
| v2.2.7 | Archived | Synthetic release note 7 |
| v2.2.8 | Current | Synthetic release note 8 |
Community contributions: 77 synthetic contributors have submitted evaluations and fine-tunes.