Cancer Detection

PancNet-Early

PancNet-Early is a SYNTHETIC/DEMO cancer detection model for early pancreatic cancer risk from ct+labs. Outputs are deterministic demo values — NOT for clinical use. Trained (synthetically) on de-identified multi-modal data.

Multi-modal Genoma Institute License: MIT v2.7.2 RTG 4.6 DL 13,658
SYNTHETIC DEMOAll outputs are deterministic demo data — not for clinical use, not real medical inference.

Metrics

MetricValueSplit
AUC0.891Synthetic hold-out
Calibration (ECE)0.057Synthetic
InputsOutputs
CT + serum panelRisk score + drivers

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-010-pancnet-early/predict",
    headers={"Authorization": "Bearer <API_KEY>"},
    json={"input": "<ct + serum panel>"})
print(r.json())  # -> synthetic demo prediction

See the API reference · JSON: /api/models/bf-010-pancnet-early

Version history

VersionStatusNotes
v2.7.0ArchivedSynthetic release note 0
v2.7.1ArchivedSynthetic release note 1
v2.7.2CurrentSynthetic release note 2

Community contributions: 141 synthetic contributors have submitted evaluations and fine-tunes.